Search

The production of multiple Higgs bosons at the CERN LHC provides a direct way to measure the trilinear and quartic Higgs self-interaction strengths as well as potential access to beyond the standard model effects that can enhance production at large transverse momentum $p_{\mathrm{T}}$. The largest event fraction arises from the fully hadronic final state in which every Higgs boson decays to a bottom quark-antiquark pair ($b\bar{b}$). This introduces a combinatorial challenge known as the \emph{jet assignment problem}: assigning jets to sets representing Higgs boson candidates. Symmetry-preserving attention networks (SPA-Nets) have been been developed to address this challenge. However, the complexity of jet assignment increases when simultaneously considering both $H\rightarrow b\bar{b}$ reconstruction possibilities, i.e., two "resolved" small-radius jets each containing a shower initiated by a $b$-quark or one "boosted" large-radius jet containing a merged shower initiated by a $b\bar{b}$ pair. The latter improves the reconstruction efficiency at high $p_{\mathrm{T}}$. In this work, we introduce a generalization to the SPA-Net approach to simultaneously consider both boosted and resolved reconstruction possibilities and unambiguously interpret an event as "fully resolved'', "fully boosted", or in between. We report the performance of baseline methods, the original SPA-Net approach, and our generalized version on nonresonant $HH$ and $HHH$ production at the LHC. Considering both boosted and resolved topologies, our SPA-Net approach increases the Higgs boson reconstruction purity by 57--62\% and the efficiency by 23--38\% compared to the baseline method depending on the final state.

The simulation of detector response is a vital aspect of data analysis in particle physics, but current Monte Carlo methods are computationally expensive. Machine learning methods, which learn a mapping from incident particle to detector response, are much faster but require a model for every detector element with unique geometry. Complex geometries may require many models, each with their own training samples and hyperparameter tuning tasks. A promising approach is the use of geometry-aware models, which condition the response on the geometry, but current efforts typically require cumbersome full geometry specification. We present a geometry-aware model that takes advantage of the regularity of detector segments, requiring only the definition of cell sizes across regular segments. This model outperforms the current state of the art by over 70% across several key metrics including the Wasserstein distance metric.

Recent advancements in Model-Based Reinforcement Learning (MBRL) have made it a powerful tool for visual control tasks. Despite improved data efficiency, it remains challenging to train MBRL agents with generalizable perception. Training in the presence of visual distractions is particularly difficult due to the high variation they introduce to representation learning. Building on DREAMER, a popular MBRL method, we propose a simple yet effective auxiliary task to facilitate representation learning in distracting environments. Under the assumption that task-relevant components of image observations are straightforward to identify with prior knowledge in a given task, we use a segmentation mask on image observations to only reconstruct task-relevant components. In doing so, we greatly reduce the complexity of representation learning by removing the need to encode task-irrelevant objects in the latent representation. Our method, Segmentation Dreamer (SD), can be used either with ground-truth masks easily accessible in simulation or by leveraging potentially imperfect segmentation foundation models. The latter is further improved by selectively applying the reconstruction loss to avoid providing misleading learning signals due to mask prediction errors. In modified DeepMind Control suite (DMC) and Meta-World tasks with added visual distractions, SD achieves significantly better sample efficiency and greater final performance than prior work. We find that SD is especially helpful in sparse reward tasks otherwise unsolvable by prior work, enabling the training of visually robust agents without the need for extensive reward engineering.

While Deep Reinforcement Learning (DRL) has achieved remarkable success across various domains, it remains vulnerable to occasional catastrophic failures without additional safeguards. An effective solution to prevent these failures is to use a shield that validates and adjusts the agent's actions to ensure compliance with a provided set of safety specifications. For real-world robotic domains, it is essential to define safety specifications over continuous state and action spaces to accurately account for system dynamics and compute new actions that minimally deviate from the agent's original decision. In this paper, we present the first shielding approach specifically designed to ensure the satisfaction of safety requirements in continuous state and action spaces, making it suitable for practical robotic applications. Our method builds upon realizability, an essential property that confirms the shield will always be able to generate a safe action for any state in the environment. We formally prove that realizability can be verified for stateful shields, enabling the incorporation of non-Markovian safety requirements, such as loop avoidance. Finally, we demonstrate the effectiveness of our approach in ensuring safety without compromising the policy's success rate by applying it to a navigation problem and a multi-agent particle environment., Comment: Kim, Corsi, and Rodriguez contributed equally

We develop a general theory of synaptic neural balance and how it can emerge or be enforced in neural networks. For a given regularizer, a neuron is said to be in balance if the total cost of its input weights is equal to the total cost of its output weights. The basic example is provided by feedforward networks of ReLU units trained with $L_2$ regularizers, which exhibit balance after proper training. The theory explains this phenomenon and extends it in several directions. The first direction is the extension to bilinear and other activation functions. The second direction is the extension to more general regularizers, including all $L_p$ regularizers. The third direction is the extension to non-layered architectures, recurrent architectures, convolutional architectures, as well as architectures with mixed activation functions. Gradient descent on the error function alone does not converge in general to a balanced state, where every neuron is in balance, even when starting from a balanced state. However, gradient descent on the regularized error function ought to converge to a balanced state, and thus network balance can be used to assess learning progress. The theory is based on two local neuronal operations: scaling which is commutative, and balancing which is not commutative. Given any initial set of weights, when local balancing operations are applied to each neuron in a stochastic manner, global order always emerges through the convergence of the stochastic balancing algorithm to the same unique set of balanced weights. The reason for this is the existence of an underlying strictly convex optimization problem where the relevant variables are constrained to a linear, only architecture-dependent, manifold. Simulations show that balancing neurons prior to learning, or during learning in alternation with gradient descent steps, can improve learning speed and final performance.

The measurements performed by particle physics experiments must account for the imperfect response of the detectors used to observe the interactions. One approach, unfolding, statistically adjusts the experimental data for detector effects. Recently, generative machine learning models have shown promise for performing unbinned unfolding in a high number of dimensions. However, all current generative approaches are limited to unfolding a fixed set of observables, making them unable to perform full-event unfolding in the variable dimensional environment of collider data. A novel modification to the variational latent diffusion model (VLD) approach to generative unfolding is presented, which allows for unfolding of high- and variable-dimensional feature spaces. The performance of this method is evaluated in the context of semi-leptonic top quark pair production at the Large Hadron Collider., Comment: Submission to SciPost

Creating controlled methods to simulate neurodegeneration in artificial intelligence (AI) is crucial for applications that emulate brain function decline and cognitive disorders. We use IQ tests performed by Large Language Models (LLMs) and, more specifically, the LLaMA 2 to introduce the concept of ``neural erosion." This deliberate erosion involves ablating synapses or neurons, or adding Gaussian noise during or after training, resulting in a controlled progressive decline in the LLMs' performance. We are able to describe the neurodegeneration in the IQ tests and show that the LLM first loses its mathematical abilities and then its linguistic abilities, while further losing its ability to understand the questions. To the best of our knowledge, this is the first work that models neurodegeneration with text data, compared to other works that operate in the computer vision domain. Finally, we draw similarities between our study and cognitive decline clinical studies involving test subjects. We find that with the application of neurodegenerative methods, LLMs lose abstract thinking abilities, followed by mathematical degradation, and ultimately, a loss in linguistic ability, responding to prompts incoherently. These findings are in accordance with human studies., Comment: 19 pages, 6 figures in the main text, 5 figures in the Appendix

The deliberate manipulation of ammonium persulfate, methylenebisacrylamide, dimethyleacrylamide, and polyethylene oxide concentrations resulted in the development of a hydrogel with an exceptional stretchability, capable of extending up to 260 times its original length. This study aims to elucidate the molecular architecture underlying this unique phenomenon by exploring potential reaction mechanisms, facilitated by an artificial intelligence prediction system. Artificial intelligence predictor introduces a novel approach to interlinking two polymers, involving the formation of networks interconnected with linear chains following random chain scission. This novel configuration leads to the emergence of a distinct type of hydrogel, herein referred to as a "Span Network." Additionally, Fourier-transform infrared spectroscopy (FTIR) is used to investigate functional groups that may be implicated in the proposed mechanism, with ester formation confirmed among numerous hydroxyl end groups obtained from chain scission of PEO and carboxyl groups formed on hydrogel networks.

The generation of natural and high-quality speech from text is a challenging problem in the field of natural language processing. In addition to speech generation, speech editing is also a crucial task, which requires the seamless and unnoticeable integration of edited speech into synthesized speech. We propose a novel approach to speech editing by leveraging a pre-trained text-to-speech (TTS) model, such as FastSpeech 2, and incorporating a double attention block network on top of it to automatically merge the synthesized mel-spectrogram with the mel-spectrogram of the edited text. We refer to this model as AttentionStitch, as it harnesses attention to stitch audio samples together. We evaluate the proposed AttentionStitch model against state-of-the-art baselines on both single and multi-speaker datasets, namely LJSpeech and VCTK. We demonstrate its superior performance through an objective and a subjective evaluation test involving 15 human participants. AttentionStitch is capable of producing high-quality speech, even for words not seen during training, while operating automatically without the need for human intervention. Moreover, AttentionStitch is fast during both training and inference and is able to generate human-sounding edited speech., Comment: Accepted in Machine Learning for Audio workship in NeurIPS 2023

This study evaluates the performance of large language models, specifically GPT-3.5 and BARD (supported by Gemini Pro model), in undergraduate admissions exams proposed by the National Polytechnic Institute in Mexico. The exams cover Engineering/Mathematical and Physical Sciences, Biological and Medical Sciences, and Social and Administrative Sciences. Both models demonstrated proficiency, exceeding the minimum acceptance scores for respective academic programs to up to 75% for some academic programs. GPT-3.5 outperformed BARD in Mathematics and Physics, while BARD performed better in History and questions related to factual information. Overall, GPT-3.5 marginally surpassed BARD with scores of 60.94% and 60.42%, respectively., Comment: 11 pages, 1 figure. Submitted to a journal

In Inertial Confinement Fusion (ICF) process, roughly a 2mm spherical shell made of high density carbon is used as target for laser beams, which compress and heat it to energy levels needed for high fusion yield. These shells are polished meticulously to meet the standards for a fusion shot. However, the polishing of these shells involves multiple stages, with each stage taking several hours. To make sure that the polishing process is advancing in the right direction, we are able to measure the shell surface roughness. This measurement, however, is very labor-intensive, time-consuming, and requires a human operator. We propose to use machine learning models that can predict surface roughness based on the data collected from a vibration sensor that is connected to the polisher. Such models can generate surface roughness of the shells in real-time, allowing the operator to make any necessary changes to the polishing for optimal result., Comment: Accepted as Extended Abstract in AIM 2024

Deep learning-based reaction predictors have undergone significant architectural evolution. However, their reliance on reactions from the US Patent Office results in a lack of interpretable predictions and limited generalization capability to other chemistry domains, such as radical and atmospheric chemistry. To address these challenges, we introduce a new reaction predictor system, RMechRP, that leverages contrastive learning in conjunction with mechanistic pathways, the most interpretable representation of chemical reactions. Specifically designed for radical reactions, RMechRP provides different levels of interpretation of chemical reactions. We develop and train multiple deep-learning models using RMechDB, a public database of radical reactions, to establish the first benchmark for predicting radical reactions. Our results demonstrate the effectiveness of RMechRP in providing accurate and interpretable predictions of radical reactions, and its potential for various applications in atmospheric chemistry.

Large language models (LLMs) are being applied as actors for sequential decision making tasks in domains such as robotics and games, utilizing their general world knowledge and planning abilities. However, previous work does little to explore what environment state information is provided to LLM actors via language. Exhaustively describing high-dimensional states can impair performance and raise inference costs for LLM actors. Previous LLM actors avoid the issue by relying on hand-engineered, task-specific protocols to determine which features to communicate about a state and which to leave out. In this work, we propose Brief Language INputs for DEcision-making Responses (BLINDER), a method for automatically selecting concise state descriptions by learning a value function for task-conditioned state descriptions. We evaluate BLINDER on the challenging video game NetHack and a robotic manipulation task. Our method improves task success rate, reduces input size and compute costs, and generalizes between LLM actors.

Modern climate projections lack adequate spatial and temporal resolution due to computational constraints, leading to inaccuracies in representing critical processes like thunderstorms that occur on the sub-resolution scale. Hybrid methods combining physics with machine learning (ML) offer faster, higher fidelity climate simulations by outsourcing compute-hungry, high-resolution simulations to ML emulators. However, these hybrid ML-physics simulations require domain-specific data and workflows that have been inaccessible to many ML experts. As an extension of the ClimSim dataset (Yu et al., 2024), we present ClimSim-Online, which also includes an end-to-end workflow for developing hybrid ML-physics simulators. The ClimSim dataset includes 5.7 billion pairs of multivariate input/output vectors, capturing the influence of high-resolution, high-fidelity physics on a host climate simulator's macro-scale state. The dataset is global and spans ten years at a high sampling frequency. We provide a cross-platform, containerized pipeline to integrate ML models into operational climate simulators for hybrid testing. We also implement various ML baselines, alongside a hybrid baseline simulator, to highlight the ML challenges of building stable, skillful emulators. The data (https://huggingface.co/datasets/LEAP/ClimSim_high-res) and code (https://leap-stc.github.io/ClimSim and https://github.com/leap-stc/climsim-online) are publicly released to support the development of hybrid ML-physics and high-fidelity climate simulations., Comment: This manuscript is an expanded version of our paper that received the Outstanding Paper Award at the NeurIPS 2023 conference

High-energy collisions at the Large Hadron Collider (LHC) provide valuable insights into open questions in particle physics. However, detector effects must be corrected before measurements can be compared to certain theoretical predictions or measurements from other detectors. Methods to solve this \textit{inverse problem} of mapping detector observations to theoretical quantities of the underlying collision are essential parts of many physics analyses at the LHC. We investigate and compare various generative deep learning methods to approximate this inverse mapping. We introduce a novel unified architecture, termed latent variation diffusion models, which combines the latent learning of cutting-edge generative art approaches with an end-to-end variational framework. We demonstrate the effectiveness of this approach for reconstructing global distributions of theoretical kinematic quantities, as well as for ensuring the adherence of the learned posterior distributions to known physics constraints. Our unified approach achieves a distribution-free distance to the truth of over 20 times less than non-latent state-of-the-art baseline and 3 times less than traditional latent diffusion models.

Agents capable of carrying out general tasks on a computer can improve efficiency and productivity by automating repetitive tasks and assisting in complex problem-solving. Ideally, such agents should be able to solve new computer tasks presented to them through natural language commands. However, previous approaches to this problem require large amounts of expert demonstrations and task-specific reward functions, both of which are impractical for new tasks. In this work, we show that a pre-trained large language model (LLM) agent can execute computer tasks guided by natural language using a simple prompting scheme where the agent Recursively Criticizes and Improves its output (RCI). The RCI approach significantly outperforms existing LLM methods for automating computer tasks and surpasses supervised learning (SL) and reinforcement learning (RL) approaches on the MiniWoB++ benchmark. We compare multiple LLMs and find that RCI with the InstructGPT-3+RLHF LLM is state-of-the-art on MiniWoB++, using only a handful of demonstrations per task rather than tens of thousands, and without a task-specific reward function. Furthermore, we demonstrate RCI prompting's effectiveness in enhancing LLMs' reasoning abilities on a suite of natural language reasoning tasks, outperforming chain of thought (CoT) prompting with external feedback. We find that RCI combined with CoT performs better than either separately. Our code can be found here: https://github.com/posgnu/rci-agent.

The complex events observed at the NOvA long-baseline neutrino oscillation experiment contain vital information for understanding the most elusive particles in the standard model. The NOvA detectors observe interactions of neutrinos from the NuMI beam at Fermilab. Associating the particles produced in these interaction events to their source particles, a process known as reconstruction, is critical for accurately measuring key parameters of the standard model. Events may contain several particles, each producing sparse high-dimensional spatial observations, and current methods are limited to evaluating individual particles. To accurately label these numerous, high-dimensional observations, we present a novel neural network architecture that combines the spatial learning enabled by convolutions with the contextual learning enabled by attention. This joint approach, TransformerCVN, simultaneously classifies each event and reconstructs every individual particle's identity. TransformerCVN classifies events with 90\% accuracy and improves the reconstruction of individual particles by 6\% over baseline methods which lack the integrated architecture of TransformerCVN. In addition, this architecture enables us to perform several interpretability studies which provide insights into the network's predictions and show that TransformerCVN discovers several fundamental principles that stem from the standard model.

Calorimeter shower simulations are often the bottleneck in simulation time for particle physics detectors. A lot of effort is currently spent on optimizing generative architectures for specific detector geometries, which generalize poorly. We develop a geometry-aware autoregressive model on a range of calorimeter geometries such that the model learns to adapt its energy deposition depending on the size and position of the cells. This is a key proof-of-concept step towards building a model that can generalize to new unseen calorimeter geometries with little to no additional training. Such a model can replace the hundreds of generative models used for calorimeter simulation in a Large Hadron Collider experiment. For the study of future detectors, such a model will dramatically reduce the large upfront investment usually needed to generate simulations., Comment: This paper was submitted to NeurIPS Machine Learning and the Physical Sciences Workshop 2022

Neutron stars provide a unique laboratory for studying matter at extreme pressures and densities. While there is no direct way to explore their interior structure, X-rays emitted from these stars can indirectly provide clues to the equation of state (EOS) of superdense nuclear matter through the inference of the star's mass and radius. However, inference of EOS directly from a star's X-ray spectra is extremely challenging and is complicated by systematic uncertainties. The current state of the art is to use simulation-based likelihoods in a piece-wise method, which first infer the star's mass and radius to reduce the dimensionality of the problem, and from those quantities infer the EOS. We demonstrate a series of enhancements to the state of the art, in terms of realistic uncertainty quantification and improved regression of physical properties with machine learning. We also demonstrate novel inference of the EOS directly from the high-dimensional spectra of observed stars, avoiding the intermediate mass-radius step. Our network is conditioned on the sources of uncertainty of each star, allowing for natural and complete propagation of uncertainties to the EOS., Comment: 24 pages, 20 figures

Robust reinforcement learning (RL) considers the problem of learning policies that perform well in the worst case among a set of possible environment parameter values. In real-world environments, choosing the set of possible values for robust RL can be a difficult task. When that set is specified too narrowly, the agent will be left vulnerable to reasonable parameter values unaccounted for. When specified too broadly, the agent will be too cautious. In this paper, we propose Feasible Adversarial Robust RL (FARR), a novel problem formulation and objective for automatically determining the set of environment parameter values over which to be robust. FARR implicitly defines the set of feasible parameter values as those on which an agent could achieve a benchmark reward given enough training resources. By formulating this problem as a two-player zero-sum game, optimizing the FARR objective jointly produces an adversarial distribution over parameter values with feasible support and a policy robust over this feasible parameter set. We demonstrate that approximate Nash equilibria for this objective can be found using a variation of the PSRO algorithm. Furthermore, we show that an optimal agent trained with FARR is more robust to feasible adversarial parameter selection than with existing minimax, domain-randomization, and regret objectives in a parameterized gridworld and three MuJoCo control environments., Comment: Added new theory sections. Added comparison to self-play. Added adversary mixed-strategy analysis

In competitive two-agent environments, deep reinforcement learning (RL) methods based on the \emph{Double Oracle (DO)} algorithm, such as \emph{Policy Space Response Oracles (PSRO)} and \emph{Anytime PSRO (APSRO)}, iteratively add RL best response policies to a population. Eventually, an optimal mixture of these population policies will approximate a Nash equilibrium. However, these methods might need to add all deterministic policies before converging. In this work, we introduce \emph{Self-Play PSRO (SP-PSRO)}, a method that adds an approximately optimal stochastic policy to the population in each iteration. Instead of adding only deterministic best responses to the opponent's least exploitable population mixture, SP-PSRO also learns an approximately optimal stochastic policy and adds it to the population as well. As a result, SP-PSRO empirically tends to converge much faster than APSRO and in many games converges in just a few iterations.

A significant point-like component from the small scale (or discrete) structure in the H2 interstellar gas might be present in the Fermi-LAT data, but modeling this emission relies on observations of rare gas tracers only available in limited regions of the sky. Identifying this contribution is important to discriminate gamma-ray point sources from interstellar gas, and to better characterize extended gamma-ray sources. We design and train convolutional neural networks to predict this emission where observations of these rare tracers do not exist and discuss the impact of this component on the analysis of the Fermi-LAT data. In particular, we evaluate prospects to exploit this methodology in the characterization of the Fermi-LAT Galactic center excess through accurate modeling of point-like structures in the data to help distinguish between a point-like or smooth nature for the excess. We show that deep learning may be effectively employed to model the gamma-ray emission traced by these rare H2 proxies within statistical significance in data-rich regions, supporting prospects to employ these methods in yet unobserved regions., Comment: Submitted. Companion paper to "Improved modeling of the discrete component of the galactic interstellar gamma-ray emission and implications for the Fermi--LAT galactic center excess"

The aim of this work is to improve models for the gamma-ray discrete or small-scale structure related to H2 interstellar gas. Reliably identifying this contribution is important to disentangle gamma-ray point sources from interstellar gas, and to better characterize extended gamma-ray signals. Notably, the Fermi-LAT Galactic center (GC) excess, whose origin remains unclear, might be smooth or point-like. If the data contain a point-like contribution that is not adequately modeled, a smooth GC excess might be erroneously deemed to be point-like. We improve models for the H2-related gamma-ray discrete emission for a $50^\circ \times 1^\circ$ region along the Galactic plane via H2 proxies better suited to trace these features. We find that these are likely to contribute significantly to the gamma-ray Fermi-LAT data in this region, and the brightest ones are likely associated with detected Fermi-LAT sources, a compelling validation of this methodology. We discuss prospects to extend this methodology to other regions of the sky and implications for the characterization of the GC excess., Comment: Submitted

An early example of the ability of deep networks to improve the statistical power of data collected in particle physics experiments was the demonstration that such networks operating on lists of particle momenta (four-vectors) could outperform shallow networks using features engineered with domain knowledge. A benchmark case is described, with extensions to parameterized networks. A discussion of data handling and architecture is presented, as well as a description of how to incorporate physics knowledge into the network architecture., Comment: To appear in Artificial Intelligence for High Energy Physics, World Scientific Publishing

Attention plays a fundamental role in both natural and artificial intelligence systems. In deep learning, attention-based neural architectures, such as transformer architectures, are widely used to tackle problems in natural language processing and beyond. Here we investigate the fundamental building blocks of attention and their computational properties. Within the standard model of deep learning, we classify all possible fundamental building blocks of attention in terms of their source, target, and computational mechanism. We identify and study three most important mechanisms: additive activation attention, multiplicative output attention (output gating), and multiplicative synaptic attention (synaptic gating). The gating mechanisms correspond to multiplicative extensions of the standard model and are used across all current attention-based deep learning architectures. We study their functional properties and estimate the capacity of several attentional building blocks in the case of linear and polynomial threshold gates. Surprisingly, additive activation attention plays a central role in the proofs of the lower bounds. Attention mechanisms reduce the depth of certain basic circuits and leverage the power of quadratic activations without incurring their full cost.

We study the effectiveness of theoretically-motivated high-level jet observables in the extreme context of jets with a large number of hard sub-jets (up to $N=8$). Previous studies indicate that high-level observables are powerful, interpretable tools to probe jet substructure for $N\le 3$ hard sub-jets, but that deep neural networks trained on low-level jet constituents match or slightly exceed their performance. We extend this work for up to $N=8$ hard sub-jets, using deep particle-flow networks (PFNs) and Transformer based networks to estimate a loose upper bound on the classification performance. A fully-connected neural network operating on a standard set of high-level jet observables, 135 $\textrm{N}$-subjetiness observables and jet mass, reach classification accuracy of 86.90\%, but fall short of the PFN and Transformer models, which reach classification accuracies of 89.19\% and 91.27\% respectively, suggesting that the constituent networks utilize information not captured by the set of high-level observables. We then identify additional high-level observables which are able to narrow this gap, and utilize LASSO regularization for feature selection to identify and rank the most relevant observables and provide further insights into the learning strategies used by the constituent-based neural networks. The final model contains only 31 high-level observables and is able to match the performance of the PFN and approximate the performance of the Transformer model to within 2\%.

Policy space response oracles (PSRO) is a multi-agent reinforcement learning algorithm that has achieved state-of-the-art performance in very large two-player zero-sum games. PSRO is based on the tabular double oracle (DO) method, an algorithm that is guaranteed to converge to a Nash equilibrium, but may increase exploitability from one iteration to the next. We propose anytime double oracle (ADO), a tabular double oracle algorithm for 2-player zero-sum games that is guaranteed to converge to a Nash equilibrium while decreasing exploitability from one iteration to the next. Unlike DO, in which the restricted distribution is based on the restricted game formed by each player's strategy sets, ADO finds the restricted distribution for each player that minimizes its exploitability against any policy in the full, unrestricted game. We also propose a method of finding this restricted distribution via a no-regret algorithm updated against best responses, called RM-BR DO. Finally, we propose anytime PSRO (APSRO), a version of ADO that calculates best responses via reinforcement learning. In experiments on Leduc poker and random normal form games, we show that our methods achieve far lower exploitability than DO and PSRO and decrease exploitability monotonically., Comment: Published in AAAI Reinforcement Learning in Games Workshop

It is fundamental for science and technology to be able to predict chemical reactions and their properties. To achieve such skills, it is important to develop good representations of chemical reactions, or good deep learning architectures that can learn such representations automatically from the data. There is currently no universal and widely adopted method for robustly representing chemical reactions. Most existing methods suffer from one or more drawbacks, such as: (1) lacking universality; (2) lacking robustness; (3) lacking interpretability; or (4) requiring excessive manual pre-processing. Here we exploit graph-based representations of molecular structures to develop and test a hypergraph attention neural network approach to solve at once the reaction representation and property-prediction problems, alleviating the aforementioned drawbacks. We evaluate this hypergraph representation in three experiments using three independent data sets of chemical reactions. In all experiments, the hypergraph-based approach matches or outperforms other representations and their corresponding models of chemical reactions while yielding interpretable multi-level representations.