arXiv:2610.20486v1 Announce Type: new Abstract: In reinforcement learning, an agent must explore an unknown environment to learn how to make good decisions. Unlike methods that can freely sample any...
The paper investigates learning Nash equilibria in partially observable Markov games (POMGs) where agents cannot fully observe the state. By focusing on a subclass with independent state transitions and a Markov potential game structure, the authors propose an independent learning algorithm that allows agents to converge to an approximate Nash equilibrium using only their own observations and actions, without communication. Under a filter stability assumption, finite‑history policies are shown to approximate the POMG sufficiently, enabling a surrogate near‑potential Markov game and yielding quasi‑polynomial sample and computational complexity.
arXiv:2602. 16965v2 Announce Type: replace Abstract: We study the decentralized multi-player stochastic bandit problem over a continuous, Lipschitz-structured action space where hard collisions yield zero reward.
The paper introduces two algorithms for safe multi‑objective reinforcement learning that guarantee zero constraint violation during learning. The first algorithm learns a safe Pareto‑optimal policy for a given preference by combining optimistic reward estimates with pessimistic cost bounds, achieving an ×O(1/√T) suboptimality gap. The second, preference‑free algorithm safely explores first and then computes a safe policy for any preference, retaining the same safety guarantee and achieving an ×O(1/√T+1/√K) suboptimality gap.
arXiv:2603.18965v2 Announce Type: replace Abstract: Maximum entropy reinforcement learning motivates agents to explore states and actions to maximize the entropy of some distribution, typically by pr...
arXiv:2606. 11284v1 Announce Type: cross Abstract: Real-world multi-agent systems, from traffic coordination to resource allocation, are often modeled as general-sum games where individual incentives conflict with collective welfare.
arXiv:2605. 14982v2 Announce Type: replace-cross Abstract: We address the discounted reward setting in reinforcement learning (RL).
The paper introduces Fed‑LSVI, a federated online reinforcement learning algorithm that uses linear function approximation in episodic Markov decision processes. It achieves a regret bound of ≥O(√{Md^3H^4T}) while only exchanging compressed sufficient statistics, thereby meeting privacy constraints. The method reduces communication cost to logarithmic in the number of episodes, a marked improvement over previous approaches that required linear communication.
Finding policies for Markov Decision Processes (MDPs) is a central problem in areas such as Reinforcement Learning and Operations Research. Here, we have to repeatedly choose an action that should be...
arXiv:2609.06586v1 Announce Type: cross Abstract: A shared reward gives agents a common objective, but leaves open when, how and even whether they must cooperate to succeed. We address these question...
We study infinite-horizon average-reward constrained Markov decision processes (CMDPs) under the weakly communicating assumption. Existing high-probability guarantees for this setting either require c...
arXiv:2602. 12963v2 Announce Type: replace Abstract: An important question in the field of AI is the extent to which successful behaviour requires an internal representation of the world.