Search

Rank aggregation through crowdsourcing has recently gained significant attention, particularly in the context of listwise ranking annotations. However, existing methods primarily focus on a single problem and partial ranks, while the aggregation of listwise full ranks across numerous problems remains largely unexplored. This scenario finds relevance in various applications, such as model quality assessment and reinforcement learning with human feedback. In light of practical needs, we propose LAC, a Listwise rank Aggregation method in Crowdsourcing, where the global position information is carefully measured and included. In our design, an especially proposed annotation quality indicator is employed to measure the discrepancy between the annotated rank and the true rank. We also take the difficulty of the ranking problem itself into consideration, as it directly impacts the performance of annotators and consequently influences the final results. To our knowledge, LAC is the first work to directly deal with the full rank aggregation problem in listwise crowdsourcing, and simultaneously infer the difficulty of problems, the ability of annotators, and the ground-truth ranks in an unsupervised way. To evaluate our method, we collect a real-world business-oriented dataset for paragraph ranking. Experimental results on both synthetic and real-world benchmark datasets demonstrate the effectiveness of our proposed LAC method., Comment: 19 pages

In practice, reinforcement learning (RL) agents are often trained with a possibly imperfect proxy reward function, which may lead to a human-agent alignment issue (i.e., the learned policy either converges to non-optimal performance with low cumulative rewards, or achieves high cumulative rewards but in undesired manner). To tackle this issue, we consider a framework where a human labeler can provide additional feedback in the form of corrective actions, which expresses the labeler's action preferences although this feedback may possibly be imperfect as well. In this setting, to obtain a better-aligned policy guided by both learning signals, we propose a novel value-based deep RL algorithm called Iterative learning from Corrective actions and Proxy rewards (ICoPro), which cycles through three phases: (1) Solicit sparse corrective actions from a human labeler on the agent's demonstrated trajectories; (2) Incorporate these corrective actions into the Q-function using a margin loss to enforce adherence to labeler's preferences; (3) Train the agent with standard RL losses regularized with a margin loss to learn from proxy rewards and propagate the Q-values learned from human feedback. Moreover, another novel design in our approach is to integrate pseudo-labels from the target Q-network to reduce human labor and further stabilize training. We experimentally validate our proposition on a variety of tasks (Atari games and autonomous driving on highway). On the one hand, using proxy rewards with different levels of imperfection, our method can better align with human preferences and is more sample-efficient than baseline methods. On the other hand, facing corrective actions with different types of imperfection, our method can overcome the non-optimality of this feedback thanks to the guidance from proxy reward.

Offline reinforcement learning (RL) is crucial for real-world applications where exploration can be costly or unsafe. However, offline learned policies are often suboptimal, and further online fine-tuning is required. In this paper, we tackle the fundamental dilemma of offline-to-online fine-tuning: if the agent remains pessimistic, it may fail to learn a better policy, while if it becomes optimistic directly, performance may suffer from a sudden drop. We show that Bayesian design principles are crucial in solving such a dilemma. Instead of adopting optimistic or pessimistic policies, the agent should act in a way that matches its belief in optimal policies. Such a probability-matching agent can avoid a sudden performance drop while still being guaranteed to find the optimal policy. Based on our theoretical findings, we introduce a novel algorithm that outperforms existing methods on various benchmarks, demonstrating the efficacy of our approach. Overall, the proposed approach provides a new perspective on offline-to-online RL that has the potential to enable more effective learning from offline data., Comment: Forty-first International Conference on Machine Learning (ICML), 2024

Reinforcement Learning (RL) is a widely employed technique in decision-making problems, encompassing two fundamental operations -- policy evaluation and policy improvement. Enhancing learning efficiency remains a key challenge in RL, with many efforts focused on using ensemble critics to boost policy evaluation efficiency. However, when using multiple critics, the actor in the policy improvement process can obtain different gradients. Previous studies have combined these gradients without considering their disagreements. Therefore, optimizing the policy improvement process is crucial to enhance learning efficiency. This study focuses on investigating the impact of gradient disagreements caused by ensemble critics on policy improvement. We introduce the concept of uncertainty of gradient directions as a means to measure the disagreement among gradients utilized in the policy improvement process. Through measuring the disagreement among gradients, we find that transitions with lower uncertainty of gradient directions are more reliable in the policy improvement process. Building on this analysis, we propose a method called von Mises-Fisher Experience Resampling (vMFER), which optimizes the policy improvement process by resampling transitions and assigning higher confidence to transitions with lower uncertainty of gradient directions. Our experiments demonstrate that vMFER significantly outperforms the benchmark and is particularly well-suited for ensemble structures in RL., Comment: Accepted by IJCAI 2024, with appendix

For the purpose of efficient and cost-effective large-scale data labeling, crowdsourcing is increasingly being utilized. To guarantee the quality of data labeling, multiple annotations need to be collected for each data sample, and truth inference algorithms have been developed to accurately infer the true labels. Despite previous studies having released public datasets to evaluate the efficacy of truth inference algorithms, these have typically focused on a single type of crowdsourcing task and neglected the temporal information associated with workers' annotation activities. These limitations significantly restrict the practical applicability of these algorithms, particularly in the context of long-term and online truth inference. In this paper, we introduce a substantial crowdsourcing annotation dataset collected from a real-world crowdsourcing platform. This dataset comprises approximately two thousand workers, one million tasks, and six million annotations. The data was gathered over a period of approximately six months from various types of tasks, and the timestamps of each annotation were preserved. We analyze the characteristics of the dataset from multiple perspectives and evaluate the effectiveness of several representative truth inference algorithms on this dataset. We anticipate that this dataset will stimulate future research on tracking workers' abilities over time in relation to different types of tasks, as well as enhancing online truth inference.

Efforts to decode deep neural networks (DNNs) often involve mapping their predictions back to the input features. Among these methods, Integrated Gradients (IG) has emerged as a significant technique. The selection of appropriate baselines in IG is crucial for crafting meaningful and unbiased explanations of model predictions in diverse settings. The standard approach of utilizing a single baseline, however, is frequently inadequate, prompting the need for multiple baselines. Leveraging the natural link between IG and the Aumann-Shapley Value, we provide a novel outlook on baseline design. Theoretically, we demonstrate that under certain assumptions, a collection of baselines aligns with the coalitions described by the Shapley Value. Building on this insight, we develop a new baseline method called Shapley Integrated Gradients (SIG), which uses proportional sampling to mirror the Shapley Value computation process. Simulations conducted in GridWorld validate that SIG effectively emulates the distribution of Shapley Values. Moreover, empirical tests on various image processing tasks show that SIG surpasses traditional IG baseline methods by offering more precise estimates of feature contributions, providing consistent explanations across different applications, and ensuring adaptability to diverse data types with negligible additional computational demand., Comment: 12 pages

In this paper, we investigate the problem of learning with noisy labels in real-world annotation scenarios, where noise can be categorized into two types: factual noise and ambiguity noise. To better distinguish these noise types and utilize their semantics, we propose a novel sample selection-based approach for noisy label learning, called Proto-semi. Proto-semi initially divides all samples into the confident and unconfident datasets via warm-up. By leveraging the confident dataset, prototype vectors are constructed to capture class characteristics. Subsequently, the distances between the unconfident samples and the prototype vectors are calculated to facilitate noise classification. Based on these distances, the labels are either corrected or retained, resulting in the refinement of the confident and unconfident datasets. Finally, we introduce a semi-supervised learning method to enhance training. Empirical evaluations on a real-world annotated dataset substantiate the robustness of Proto-semi in handling the problem of learning from noisy labels. Meanwhile, the prototype-based repartitioning strategy is shown to be effective in mitigating the adverse impact of label noise. Our code and data are available at https://github.com/fuxiAIlab/ProtoSemi., Comment: Submitted to AAAI 2024

In recent years, data-driven reinforcement learning (RL), also known as offline RL, have gained significant attention. However, the role of data sampling techniques in offline RL has been overlooked despite its potential to enhance online RL performance. Recent research suggests applying sampling techniques directly to state-transitions does not consistently improve performance in offline RL. Therefore, in this study, we propose a memory technique, (Prioritized) Trajectory Replay (TR/PTR), which extends the sampling perspective to trajectories for more comprehensive information extraction from limited data. TR enhances learning efficiency by backward sampling of trajectories that optimizes the use of subsequent state information. Building on TR, we build the weighted critic target to avoid sampling unseen actions in offline training, and Prioritized Trajectory Replay (PTR) that enables more efficient trajectory sampling, prioritized by various trajectory priority metrics. We demonstrate the benefits of integrating TR and PTR with existing offline RL algorithms on D4RL. In summary, our research emphasizes the significance of trajectory-based data sampling techniques in enhancing the efficiency and performance of offline RL algorithms.

Recent advances in multi-agent reinforcement learning (MARL) allow agents to coordinate their behaviors in complex environments. However, common MARL algorithms still suffer from scalability and sparse reward issues. One promising approach to resolving them is automatic curriculum learning (ACL). ACL involves a student (curriculum learner) training on tasks of increasing difficulty controlled by a teacher (curriculum generator). Despite its success, ACL's applicability is limited by (1) the lack of a general student framework for dealing with the varying number of agents across tasks and the sparse reward problem, and (2) the non-stationarity of the teacher's task due to ever-changing student strategies. As a remedy for ACL, we introduce a novel automatic curriculum learning framework, Skilled Population Curriculum (SPC), which adapts curriculum learning to multi-agent coordination. Specifically, we endow the student with population-invariant communication and a hierarchical skill set, allowing it to learn cooperation and behavior skills from distinct tasks with varying numbers of agents. In addition, we model the teacher as a contextual bandit conditioned by student policies, enabling a team of agents to change its size while still retaining previously acquired skills. We also analyze the inherent non-stationarity of this multi-agent automatic curriculum teaching problem and provide a corresponding regret bound. Empirical results show that our method improves the performance, scalability and sample efficiency in several MARL environments.

Determining causal effects of temporal multi-intervention assists decision-making. Restricted by time-varying bias, selection bias, and interactions of multiple interventions, the disentanglement and estimation of multiple treatment effects from individual temporal data is still rare. To tackle these challenges, we propose a comprehensive framework of temporal counterfactual forecasting from an individual multiple treatment perspective (TCFimt). TCFimt constructs adversarial tasks in a seq2seq framework to alleviate selection and time-varying bias and designs a contrastive learning-based block to decouple a mixed treatment effect into separated main treatment effects and causal interactions which further improves estimation accuracy. Through implementing experiments on two real-world datasets from distinct fields, the proposed method shows satisfactory performance in predicting future outcomes with specific treatments and in choosing optimal treatment type and timing than state-of-the-art methods.

Unsupervised reinforcement learning (URL) poses a promising paradigm to learn useful behaviors in a task-agnostic environment without the guidance of extrinsic rewards to facilitate the fast adaptation of various downstream tasks. Previous works focused on the pre-training in a model-free manner while lacking the study of transition dynamics modeling that leaves a large space for the improvement of sample efficiency in downstream tasks. To this end, we propose an Efficient Unsupervised Reinforcement Learning Framework with Multi-choice Dynamics model (EUCLID), which introduces a novel model-fused paradigm to jointly pre-train the dynamics model and unsupervised exploration policy in the pre-training phase, thus better leveraging the environmental samples and improving the downstream task sampling efficiency. However, constructing a generalizable model which captures the local dynamics under different behaviors remains a challenging problem. We introduce the multi-choice dynamics model that covers different local dynamics under different behaviors concurrently, which uses different heads to learn the state transition under different behaviors during unsupervised pre-training and selects the most appropriate head for prediction in the downstream task. Experimental results in the manipulation and locomotion domains demonstrate that EUCLID achieves state-of-the-art performance with high sample efficiency, basically solving the state-based URLB benchmark and reaching a mean normalized score of 104.0$\pm$1.2$\%$ in downstream tasks with 100k fine-tuning steps, which is equivalent to DDPG's performance at 2M interactive steps with 20x more data., Comment: Published as a conference paper at ICLR 2023

We investigate model-free multi-agent reinforcement learning (MARL) in environments where off-beat actions are prevalent, i.e., all actions have pre-set execution durations. During execution durations, the environment changes are influenced by, but not synchronised with, action execution. Such a setting is ubiquitous in many real-world problems. However, most MARL methods assume actions are executed immediately after inference, which is often unrealistic and can lead to catastrophic failure for multi-agent coordination with off-beat actions. In order to fill this gap, we develop an algorithmic framework for MARL with off-beat actions. We then propose a novel episodic memory, LeGEM, for model-free MARL algorithms. LeGEM builds agents' episodic memories by utilizing agents' individual experiences. It boosts multi-agent learning by addressing the challenging temporal credit assignment problem raised by the off-beat actions via our novel reward redistribution scheme, alleviating the issue of non-Markovian reward. We evaluate LeGEM on various multi-agent scenarios with off-beat actions, including Stag-Hunter Game, Quarry Game, Afforestation Game, and StarCraft II micromanagement tasks. Empirical results show that LeGEM significantly boosts multi-agent coordination and achieves leading performance and improved sample efficiency., Comment: Fix typos

Efficient exploration in deep cooperative multi-agent reinforcement learning (MARL) still remains challenging in complex coordination problems. In this paper, we introduce a novel Episodic Multi-agent reinforcement learning with Curiosity-driven exploration, called EMC. We leverage an insight of popular factorized MARL algorithms that the "induced" individual Q-values, i.e., the individual utility functions used for local execution, are the embeddings of local action-observation histories, and can capture the interaction between agents due to reward backpropagation during centralized training. Therefore, we use prediction errors of individual Q-values as intrinsic rewards for coordinated exploration and utilize episodic memory to exploit explored informative experience to boost policy training. As the dynamics of an agent's individual Q-value function captures the novelty of states and the influence from other agents, our intrinsic reward can induce coordinated exploration to new or promising states. We illustrate the advantages of our method by didactic examples, and demonstrate its significant outperformance over state-of-the-art MARL baselines on challenging tasks in the StarCraft II micromanagement benchmark.

Reinforcement learning based recommender systems (RL-based RS) aim at learning a good policy from a batch of collected data, by casting recommendations to multi-step decision-making tasks. However, current RL-based RS research commonly has a large reality gap. In this paper, we introduce the first open-source real-world dataset, RL4RS, hoping to replace the artificial datasets and semi-simulated RS datasets previous studies used due to the resource limitation of the RL-based RS domain. Unlike academic RL research, RL-based RS suffers from the difficulties of being well-validated before deployment. We attempt to propose a new systematic evaluation framework, including evaluation of environment simulation, evaluation on environments, counterfactual policy evaluation, and evaluation on environments built from test set. In summary, the RL4RS (Reinforcement Learning for Recommender Systems), a new resource with special concerns on the reality gaps, contains two real-world datasets, data understanding tools, tuned simulation environments, related advanced RL baselines, batch RL baselines, and counterfactual policy evaluation algorithms. The RL4RS suite can be found at https://github.com/fuxiAIlab/RL4RS. In addition to the RL-based recommender systems, we expect the resource to contribute to research in applied reinforcement learning., Comment: 4-th version, SIGIR2023

While deep reinforcement learning has achieved promising results in challenging decision-making tasks, the main bones of its success --- deep neural networks are mostly black-boxes. A feasible way to gain insight into a black-box model is to distill it into an interpretable model such as a decision tree, which consists of if-then rules and is easy to grasp and be verified. However, the traditional model distillation is usually a supervised learning task under a stationary data distribution assumption, which is violated in reinforcement learning. Therefore, a typical policy distillation that clones model behaviors with even a small error could bring a data distribution shift, resulting in an unsatisfied distilled policy model with low fidelity or low performance. In this paper, we propose to address this issue by changing the distillation objective from behavior cloning to maximizing an advantage evaluation. The novel distillation objective maximizes an approximated cumulative reward and focuses more on disastrous behaviors in critical states, which controls the data shift effect. We evaluate our method on several Gym tasks, a commercial fight game, and a self-driving car simulator. The empirical results show that the proposed method can preserve a higher cumulative reward than behavior cloning and learn a more consistent policy to the original one. Moreover, by examining the extracted rules from the distilled decision trees, we demonstrate that the proposed method delivers reasonable and robust decisions.

Graphically-rich applications such as games are ubiquitous with attractive visual effects of Graphical User Interface (GUI) that offers a bridge between software applications and end-users. However, various types of graphical glitches may arise from such GUI complexity and have become one of the main component of software compatibility issues. Our study on bug reports from game development teams in NetEase Inc. indicates that graphical glitches frequently occur during the GUI rendering and severely degrade the quality of graphically-rich applications such as video games. Existing automated testing techniques for such applications focus mainly on generating various GUI test sequences and check whether the test sequences can cause crashes. These techniques require constant human attention to captures non-crashing bugs such as bugs causing graphical glitches. In this paper, we present the first step in automating the test oracle for detecting non-crashing bugs in graphically-rich applications. Specifically, we propose \texttt{GLIB} based on a code-based data augmentation technique to detect game GUI glitches. We perform an evaluation of \texttt{GLIB} on 20 real-world game apps (with bug reports available) and the result shows that \texttt{GLIB} can achieve 100\% precision and 99.5\% recall in detecting non-crashing bugs such as game GUI glitches. Practical application of \texttt{GLIB} on another 14 real-world games (without bug reports) further demonstrates that \texttt{GLIB} can effectively uncover GUI glitches, with 48 of 53 bugs reported by \texttt{GLIB} having been confirmed and fixed so far., Comment: ESEC/FSE 2021

Measuring and promoting policy diversity is critical for solving games with strong non-transitive dynamics where strategic cycles exist, and there is no consistent winner (e.g., Rock-Paper-Scissors). With that in mind, maintaining a pool of diverse policies via open-ended learning is an attractive solution, which can generate auto-curricula to avoid being exploited. However, in conventional open-ended learning algorithms, there are no widely accepted definitions for diversity, making it hard to construct and evaluate the diverse policies. In this work, we summarize previous concepts of diversity and work towards offering a unified measure of diversity in multi-agent open-ended learning to include all elements in Markov games, based on both Behavioral Diversity (BD) and Response Diversity (RD). At the trajectory distribution level, we re-define BD in the state-action space as the discrepancies of occupancy measures. For the reward dynamics, we propose RD to characterize diversity through the responses of policies when encountering different opponents. We also show that many current diversity measures fall in one of the categories of BD or RD but not both. With this unified diversity measure, we design the corresponding diversity-promoting objective and population effectivity when seeking the best responses in open-ended learning. We validate our methods in both relatively simple games like matrix game, non-transitive mixture model, and the complex \textit{Google Research Football} environment. The population found by our methods reveals the lowest exploitability, highest population effectivity in matrix game and non-transitive mixture model, as well as the largest goal difference when interacting with opponents of various levels in \textit{Google Research Football}., Comment: We investigate a new perspective on unifying diversity measures for open-ended learning in zero-sum games, which shapes an auto-curriculum to induce diverse yet effective behaviors

In business domains, \textit{bundling} is one of the most important marketing strategies to conduct product promotions, which is commonly used in online e-commerce and offline retailers. Existing recommender systems mostly focus on recommending individual items that users may be interested in. In this paper, we target at a practical but less explored recommendation problem named bundle recommendation, which aims to offer a combination of items to users. To tackle this specific recommendation problem in the context of the \emph{virtual mall} in online games, we formalize it as a link prediction problem on a user-item-bundle tripartite graph constructed from the historical interactions, and solve it with a neural network model that can learn directly on the graph-structure data. Extensive experiments on three public datasets and one industrial game dataset demonstrate the effectiveness of the proposed method. Further, the bundle recommendation model has been deployed in production for more than one year in a popular online game developed by Netease Games, and the launch of the model yields more than 60\% improvement on conversion rate of bundles, and a relative improvement of more than 15\% on gross merchandise volume (GMV)., Comment: 8 pages, 10 figures, accepted paper on CIKM 2020

In recent years, there are great interests as well as challenges in applying reinforcement learning (RL) to recommendation systems (RS). In this paper, we summarize three key practical challenges of large-scale RL-based recommender systems: massive state and action spaces, high-variance environment, and the unspecific reward setting in recommendation. All these problems remain largely unexplored in the existing literature and make the application of RL challenging. We develop a model-based reinforcement learning framework, called GoalRec. Inspired by the ideas of world model (model-based), value function estimation (model-free), and goal-based RL, a novel disentangled universal value function designed for item recommendation is proposed. It can generalize to various goals that the recommender may have, and disentangle the stochastic environmental dynamics and high-variance reward signals accordingly. As a part of the value function, free from the sparse and high-variance reward signals, a high-capacity reward-independent world model is trained to simulate complex environmental dynamics under a certain goal. Based on the predicted environmental dynamics, the disentangled universal value function is related to the user's future trajectory instead of a monolithic state and a scalar reward. We demonstrate the superiority of GoalRec over previous approaches in terms of the above three practical challenges in a series of simulations and a real application., Comment: 9 pages, 4 figures, to be published in Proceedings of the AAAI Conference on Artificial Intelligence 2021

Reward shaping is an effective technique for incorporating domain knowledge into reinforcement learning (RL). Existing approaches such as potential-based reward shaping normally make full use of a given shaping reward function. However, since the transformation of human knowledge into numeric reward values is often imperfect due to reasons such as human cognitive bias, completely utilizing the shaping reward function may fail to improve the performance of RL algorithms. In this paper, we consider the problem of adaptively utilizing a given shaping reward function. We formulate the utilization of shaping rewards as a bi-level optimization problem, where the lower level is to optimize policy using the shaping rewards and the upper level is to optimize a parameterized shaping weight function for true reward maximization. We formally derive the gradient of the expected true reward with respect to the shaping weight function parameters and accordingly propose three learning algorithms based on different assumptions. Experiments in sparse-reward cartpole and MuJoCo environments show that our algorithms can fully exploit beneficial shaping rewards, and meanwhile ignore unbeneficial shaping rewards or even transform them into beneficial ones., Comment: Accepted by NeurIPS2020

Meta reinforcement learning (meta-RL) extracts knowledge from previous tasks and achieves fast adaptation to new tasks. Despite recent progress, efficient exploration in meta-RL remains a key challenge in sparse-reward tasks, as it requires quickly finding informative task-relevant experiences in both meta-training and adaptation. To address this challenge, we explicitly model an exploration policy learning problem for meta-RL, which is separated from exploitation policy learning, and introduce a novel empowerment-driven exploration objective, which aims to maximize information gain for task identification. We derive a corresponding intrinsic reward and develop a new off-policy meta-RL framework, which efficiently learns separate context-aware exploration and exploitation policies by sharing the knowledge of task inference. Experimental evaluation shows that our meta-RL method significantly outperforms state-of-the-art baselines on various sparse-reward MuJoCo locomotion tasks and more complex sparse-reward Meta-World tasks.

Exploration is a key problem in reinforcement learning. Recently bonus-based methods have achieved considerable successes in environments where exploration is difficult such as Montezuma's Revenge, which assign additional bonuses (e.g., intrinsic rewards) to guide the agent to rarely visited states. Since the bonus is calculated according to the novelty of the next state after performing an action, we call such methods as the next-state bonus methods. However, the next-state bonus methods force the agent to pay overmuch attention in exploring known states and ignore finding unknown states since the exploration is driven by the next state already visited, which may slow the pace of finding reward in some environments. In this paper, we focus on improving the effectiveness of finding unknown states and propose action balance exploration, which balances the frequency of selecting each action at a given state and can be treated as an extension of upper confidence bound (UCB) to deep reinforcement learning. Moreover, we propose action balance RND that combines the next-state bonus methods (e.g., random network distillation exploration, RND) and our action balance exploration to take advantage of both sides. The experiments on the grid world and Atari games demonstrate action balance exploration has a better capability in finding unknown states and can improve the performance of RND in some hard exploration environments respectively.

Transfer Learning (TL) has shown great potential to accelerate Reinforcement Learning (RL) by leveraging prior knowledge from past learned policies of relevant tasks. Existing transfer approaches either explicitly computes the similarity between tasks or select appropriate source policies to provide guided explorations for the target task. However, how to directly optimize the target policy by alternatively utilizing knowledge from appropriate source policies without explicitly measuring the similarity is currently missing. In this paper, we propose a novel Policy Transfer Framework (PTF) to accelerate RL by taking advantage of this idea. Our framework learns when and which source policy is the best to reuse for the target policy and when to terminate it by modeling multi-policy transfer as the option learning problem. PTF can be easily combined with existing deep RL approaches. Experimental results show it significantly accelerates the learning process and surpasses state-of-the-art policy transfer methods in terms of learning efficiency and final performance in both discrete and continuous action spaces., Comment: Accepted by IJCAI'2020

this paper has been withdrawn, Comment: 1. there is some discrepancy between some contributors with respect to the order of the authors; 2. the paper is rather "raw" - significant effort and improvement in terms of the paper's language and structure are needed to make it ready for publication

Transfer learning (TL) is a promising way to improve the sample efficiency of reinforcement learning. However, how to efficiently transfer knowledge across tasks with different state-action spaces is investigated at an early stage. Most previous studies only addressed the inconsistency across different state spaces by learning a common feature space, without considering that similar actions in different action spaces of related tasks share similar semantics. In this paper, we propose a method to learning action embeddings by leveraging this idea, and a framework that learns both state embeddings and action embeddings to transfer policy across tasks with different state and action spaces. Our experimental results on various tasks show that the proposed method can not only learn informative action embeddings but accelerate policy learning.

Experience reuse is key to sample-efficient reinforcement learning. One of the critical issues is how the experience is represented and stored. Previously, the experience can be stored in the forms of features, individual models, and the average model, each lying at a different granularity. However, new tasks may require experience across multiple granularities. In this paper, we propose the policy residual representation (PRR) network, which can extract and store multiple levels of experience. PRR network is trained on a set of tasks with a multi-level architecture, where a module in each level corresponds to a subset of the tasks. Therefore, the PRR network represents the experience in a spectrum-like way. When training on a new task, PRR can provide different levels of experience for accelerating the learning. We experiment with the PRR network on a set of grid world navigation tasks, locomotion tasks, and fighting tasks in a video game. The results show that the PRR network leads to better reuse of experience and thus outperforms some state-of-the-art approaches., Comment: Conference version appears in IJCAI 2019

Deep Reinforcement Learning (DRL) has been applied to address a variety of cooperative multi-agent problems with either discrete action spaces or continuous action spaces. However, to the best of our knowledge, no previous work has ever succeeded in applying DRL to multi-agent problems with discrete-continuous hybrid (or parameterized) action spaces which is very common in practice. Our work fills this gap by proposing two novel algorithms: Deep Multi-Agent Parameterized Q-Networks (Deep MAPQN) and Deep Multi-Agent Hierarchical Hybrid Q-Networks (Deep MAHHQN). We follow the centralized training but decentralized execution paradigm: different levels of communication between different agents are used to facilitate the training process, while each agent executes its policy independently based on local observations during execution. Our empirical results on several challenging tasks (simulated RoboCup Soccer and game Ghost Story) show that both Deep MAPQN and Deep MAHHQN are effective and significantly outperform existing independent deep parameterized Q-learning method.

Multiagent reinforcement learning (MARL) is commonly considered to suffer from non-stationary environments and exponentially increasing policy space. It would be even more challenging when rewards are sparse and delayed over long trajectories. In this paper, we study hierarchical deep MARL in cooperative multiagent problems with sparse and delayed reward. With temporal abstraction, we decompose the problem into a hierarchy of different time scales and investigate how agents can learn high-level coordination based on the independent skills learned at the low level. Three hierarchical deep MARL architectures are proposed to learn hierarchical policies under different MARL paradigms. Besides, we propose a new experience replay mechanism to alleviate the issue of the sparse transitions at the high level of abstraction and the non-stationarity of multiagent learning. We empirically demonstrate the effectiveness of our approaches in two domains with extremely sparse feedback: (1) a variety of Multiagent Trash Collection tasks, and (2) a challenging online mobile game, i.e., Fever Basketball Defense.