arXiv research

Addressing RL's agent-environment boundary issues, a novel analysis ensures optimal value functions are invariant.

Learning to cooperate is crucially important in multi-agent environments. The key is to understand the mutual interplay between agents. However, multi-agent environments are highly dynamic, where agents keep moving and their neighbors change quickly. This makes it hard to learn abstract representations of mutual interp…

AutoDIME automates design of multi-agent environments for RL.

AEC Games model represents software MARL environments better than POSGs.

Deep learning has enabled traditional reinforcement learning methods to deal with high-dimensional problems. However, one of the disadvantages of deep reinforcement learning methods is the limited exploration capacity of learning agents. In this paper, we introduce an approach that integrates human strategies to increa…

PettingZoo library accelerates multi-agent reinforcement learning research.

Adversarial policies can defeat RL agents in multi-agent environments.

Deep RL for uncoordinated cognitive radios finds near-optimal policies.

Agents learn to give rewards to others in a shared learning environment.

This work uses reinforcement learning to optimize task scheduling and execution in a dynamic multi-agent warehouse environment.

Reinforcement learning in multi-agent scenarios is important for real-world applications but presents challenges beyond those seen in single-agent settings. We present an actor-critic algorithm that trains decentralized policies in multi-agent settings, using centrally computed critics that share an attention mechanism…

Two algorithms improve Federated RL in diverse environments.

In this paper, we study a multi-step interactive recommendation problem, where the item recommended at current step may affect the quality of future recommendations. To address the problem, we develop a novel and effective approach, named CFRL, which seamlessly integrates the ideas of both collaborative filtering (CF) …

Recent advances in Bayesian reinforcement learning (BRL) have shown that Bayes-optimality is theoretically achievable by modeling the environment's latent dynamics using Flat-Dirichlet-Multinomial (FDM) prior. In self-interested multi-agent environments, the transition dynamics are mainly controlled by the other agent'…

This paper surveys methods to handle non-stationarity in multi-agent deep reinforcement learning.

Federated learning adapts to data and model drifts.

Framework insures AI actions with reserve capital, preventing loss.

This work improves autonomous racing by creating diverse opponents and adapting risk.

PSRL extension for continuing environments reduces regret.

The behavioral dynamics of multi-agent systems have a rich and orderly structure, which can be leveraged to understand these systems, and to improve how artificial agents learn to operate in them. Here we introduce Relational Forward Models (RFM) for multi-agent learning, networks that can learn to make accurate predic…

Sample efficiency is critical in solving real-world reinforcement learning problems, where agent-environment interactions can be costly. Imitation learning from expert advice has proved to be an effective strategy for reducing the number of interactions required to train a policy. Online imitation learning, which inter…

Improved RL algorithm stabilizes unknown linear systems with polynomial regret.

Method models other agents' behaviors without requiring direct observation.

This work improves MARL exploration efficiency using predictive guidance and prioritized experience replay.

New algorithm tracks deep RL value functions with uncertainty.

SARD improves adversarial robustness in two-stage L2D systems.

AI simplifies trading strategies, potentially making markets more efficient.

MARL algorithm uses regularization to avoid explicit structures, improving performance.

This work explains RL policies using causal models, revealing important patterns and failures.

Advances in renewable energy generation and introduction of the government targets to improve energy efficiency gave rise to a concept of a Zero Energy Building (ZEB). A ZEB is a building whose net energy usage over a year is zero, i.e., its energy use is not larger than its overall renewables generation. A collection …

The paper investigates how supervised learning and self-play improve sample efficiency in teaching AI to communicate.

Large-scale computational experiments, often running over weeks and over large datasets, are used extensively in fields such as epidemiology, meteorology, computational biology, and healthcare to understand phenomena, and design high-stakes policies affecting everyday health and economy. For instance, the OpenMalaria f…

Agents learn social skills from each other, improving performance.

DESTRESS optimizes decentralized nonconvex optimization with optimal IFO complexity and efficient communication.

Paper proposes a reinforcement learning method for trading using expert trajectories.

This paper uses deep reinforcement learning to optimize stock liquidation strategies.

ARPs improve exploration and sample efficiency in continuous control tasks.

This work tackles robust RL in multi-agent settings, improving sample efficiency.

AdaptOn achieves logarithmic regret in adaptive control of unknown partially observable linear systems.

PFedRL-Rep learns shared and personalized policies for heterogeneous environments.

New approach uses RS levels to improve stock trading RL model efficiency and stability.

Survey of RL methods for control systems with time delays.

ReOPD uses pre-collected teacher trajectories to distill knowledge from multi-turn interactions.

Recent progress in artificial intelligence through reinforcement learning (RL) has shown great success on increasingly complex single-agent environments and two-player turn-based games. However, the real-world contains multiple agents, each learning and acting independently to cooperate and compete with other agents, a…

INTAGS uses interactive simulation to improve realism in multi-agent systems.

Paper proposes DEMER to reconstruct hidden confounders for better reinforcement learning in recommendation.

Proves equivalence of two types of boundaries in metric spaces.

Study boundary value problems for elliptic operators on manifolds.