Search

Safety is a critical concern when deploying reinforcement learning agents for realistic tasks. Recently, safe reinforcement learning algorithms have been developed to optimize the agent's performance while avoiding violations of safety constraints. However, few studies have addressed the non-stationary disturbances in the environments, which may cause catastrophic outcomes. In this paper, we propose the context-aware safe reinforcement learning (CASRL) method, a meta-learning framework to realize safe adaptation in non-stationary environments. We use a probabilistic latent variable model to achieve fast inference of the posterior environment transition distribution given the context data. Safety constraints are then evaluated with uncertainty-aware trajectory sampling. The high cost of safety violations leads to the rareness of unsafe records in the dataset. We address this issue by enabling prioritized sampling during model training and formulating prior safety constraints with domain knowledge during constrained planning. The algorithm is evaluated in realistic safety-critical environments with non-stationary disturbances. Results show that the proposed algorithm significantly outperforms existing baselines in terms of safety and robustness.

This paper studies the constrained/safe reinforcement learning (RL) problem with sparse indicator signals for constraint violations. We propose a model-based approach to enable RL agents to effectively explore the environment with unknown system dynamics and environment constraints given a significantly small number of violation budgets. We employ the neural network ensemble model to estimate the prediction uncertainty and use model predictive control as the basic control framework. We propose the robust cross-entropy method to optimize the control sequence considering the model uncertainty and constraints. We evaluate our methods in the Safety Gym environment. The results show that our approach learns to complete the tasks with a much smaller number of constraint violations than state-of-the-art baselines. Additionally, we are able to achieve several orders of magnitude better sample efficiency when compared with constrained model-free RL approaches. The code is available at \url{https://github.com/liuzuxin/safe-mbrl}., Comment: 8 pages, 5 figures

Existing neural network-based autonomous systems are shown to be vulnerable against adversarial attacks, therefore sophisticated evaluation on their robustness is of great importance. However, evaluating the robustness only under the worst-case scenarios based on known attacks is not comprehensive, not to mention that some of them even rarely occur in the real world. In addition, the distribution of safety-critical data is usually multimodal, while most traditional attacks and evaluation methods focus on a single modality. To solve the above challenges, we propose a flow-based multimodal safety-critical scenario generator for evaluating decisionmaking algorithms. The proposed generative model is optimized with weighted likelihood maximization and a gradient-based sampling procedure is integrated to improve the sampling efficiency. The safety-critical scenarios are generated by querying the task algorithms and the log-likelihood of the generated scenarios is in proportion to the risk level. Experiments on a self-driving task demonstrate our advantages in terms of testing efficiency and multimodal modeling capability. We evaluate six Reinforcement Learning algorithms with our generated traffic scenarios and provide empirical conclusions about their robustness., Comment: 8 pages, 7 figures

Multi-agent navigation in dynamic environments is of great industrial value when deploying a large scale fleet of robot to real-world applications. This paper proposes a decentralized partially observable multi-agent path planning with evolutionary reinforcement learning (MAPPER) method to learn an effective local planning policy in mixed dynamic environments. Reinforcement learning-based methods usually suffer performance degradation on long-horizon tasks with goal-conditioned sparse rewards, so we decompose the long-range navigation task into many easier sub-tasks under the guidance of a global planner, which increases agents' performance in large environments. Moreover, most existing multi-agent planning approaches assume either perfect information of the surrounding environment or homogeneity of nearby dynamic agents, which may not hold in practice. Our approach models dynamic obstacles' behavior with an image-based representation and trains a policy in mixed dynamic environments without homogeneity assumption. To ensure multi-agent training stability and performance, we propose an evolutionary training approach that can be easily scaled to large and complex environments. Experiments show that MAPPER is able to achieve higher success rates and more stable performance when exposed to a large number of non-cooperative dynamic obstacles compared with traditional reaction-based planner LRA* and the state-of-the-art learning-based method., Comment: 6 pages, accepted at the 2020 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2020)

Continuously learning to solve unseen tasks with limited experience has been extensively pursued in meta-learning and continual learning, but with restricted assumptions such as accessible task distributions, independently and identically distributed tasks, and clear task delineations. However, real-world physical tasks frequently violate these assumptions, resulting in performance degradation. This paper proposes a continual online model-based reinforcement learning approach that does not require pre-training to solve task-agnostic problems with unknown task boundaries. We maintain a mixture of experts to handle nonstationarity, and represent each different type of dynamics with a Gaussian Process to efficiently leverage collected data and expressively model uncertainty. We propose a transition prior to account for the temporal dependencies in streaming data and update the mixture online via sequential variational inference. Our approach reliably handles the task distribution shift by generating new models for never-before-seen dynamics and reusing old models for previously seen dynamics. In experiments, our approach outperforms alternative methods in non-stationary tasks, including classic control with changing dynamics and decision making in different driving scenarios., Comment: 16 pages, 6 figures

Action and observation delays exist prevalently in the real-world cyber-physical systems which may pose challenges in reinforcement learning design. It is particularly an arduous task when handling multi-agent systems where the delay of one agent could spread to other agents. To resolve this problem, this paper proposes a novel framework to deal with delays as well as the non-stationary training issue of multi-agent tasks with model-free deep reinforcement learning. We formally define the Delay-Aware Markov Game that incorporates the delays of all agents in the environment. To solve Delay-Aware Markov Games, we apply centralized training and decentralized execution that allows agents to use extra information to ease the non-stationarity issue of the multi-agent systems during training, without the need of a centralized controller during execution. Experiments are conducted in multi-agent particle environments including cooperative communication, cooperative navigation, and competitive experiments. We also test the proposed algorithm in traffic scenarios that require coordination of all autonomous vehicles to show the practical value of delay-awareness. Results show that the proposed delay-aware multi-agent reinforcement learning algorithm greatly alleviates the performance degradation introduced by delay. Codes and demo videos are available at: https://github.com/baimingc/delay-aware-MARL.

Action delays degrade the performance of reinforcement learning in many real-world systems. This paper proposes a formal definition of delay-aware Markov Decision Process and proves it can be transformed into standard MDP with augmented states using the Markov reward process. We develop a delay-aware model-based reinforcement learning framework that can incorporate the multi-step delay into the learned system models without learning effort. Experiments with the Gym and MuJoCo platforms show that the proposed delay-aware model-based algorithm is more efficient in training and transferable between systems with various durations of delay compared with off-policy model-free reinforcement learning methods. Codes available at: https://github.com/baimingc/dambrl.

Autonomous vehicles must be comprehensively evaluated before deployed in cities and highways. However, most existing evaluation approaches for autonomous vehicles are static and lack adaptability, so they are usually inefficient in generating challenging scenarios for tested vehicles. In this paper, we propose an adaptive evaluation framework to efficiently evaluate autonomous vehicles in adversarial environments generated by deep reinforcement learning. Considering the multimodal nature of dangerous scenarios, we use ensemble models to represent different local optimums for diversity. We then utilize a nonparametric Bayesian method to cluster the adversarial policies. The proposed method is validated in a typical lane-change scenario that involves frequent interactions between the ego vehicle and the surrounding vehicles. Results show that the adversarial scenarios generated by our method significantly degrade the performance of the tested vehicles. We also illustrate different patterns of generated adversarial environments, which can be used to infer the weaknesses of the tested vehicles.

Long-tail and rare event problems become crucial when autonomous driving algorithms are applied in the real world. For the purpose of evaluating systems in challenging settings, we propose a generative framework to create safety-critical scenarios for evaluating specific task algorithms. We first represent the traffic scenarios with a series of autoregressive building blocks and generate diverse scenarios by sampling from the joint distribution of these blocks. We then train the generative model as an agent (or a generator) to investigate the risky distribution parameters for a given driving algorithm being evaluated. We regard the task algorithm as an environment (or a discriminator) that returns a reward to the agent when a risky scenario is generated. Through the experiments conducted on several scenarios in the simulation, we demonstrate that the proposed framework generates safety-critical scenarios more efficiently than grid search or human design methods. Another advantage of this method is its adaptiveness to the routes and parameters., Comment: Accepted to IROS 2020

Interactions between vehicles and pedestrians have always been a major problem in traffic safety. Experienced human drivers are able to analyze the environment and choose driving strategies that will help them avoid crashes. What is not yet clear, however, is how automated vehicles will interact with pedestrians. This paper proposes a new method for evaluating the safety and feasibility of the driving strategy of automated vehicles when encountering unsignalized crossings. MobilEye sensors installed on buses in Ann Arbor, Michigan, collected data on 2,973 valid crossing events. A stochastic interaction model was then created using a multivariate Gaussian mixture model. This model allowed us to simulate the movements of pedestrians reacting to an oncoming vehicle when approaching unsignalized crossings, and to evaluate the passing strategies of automated vehicles. A simulation was then conducted to demonstrate the evaluation procedure.