arXiv:2607. 05375v1 Announce Type: cross Abstract: Occupancy ratios correct distribution shift in offline reinforcement learning and are central to off-policy evaluation.
Occupancy ratios correct distribution shift in offline reinforcement learning and are central to off-policy evaluation. Existing primal-dual and minimax methods typically estimate these ratios by enforcing occupancy-balance moments over a critic class.
arXiv:2608. 14401v1 Announce Type: cross Abstract: In offline RL, estimating the optimal action-value function $Q^*$ can be formulated as solving the optimal Bellman equation based solely on offline observations.
arXiv:2608. 03108v1 Announce Type: new Abstract: Offline reinforcement learning (offline RL) can benefit from nearby out-of-distribution (OOD) actions, but estimation errors at these actions may be amplified by bootstrapping.
arXiv:2603. 09344v3 Announce Type: replace Abstract: Offline reinforcement learning (RL) enables data-efficient and safe policy learning without online exploration, but its performance often degrades under distribution shift.
arXiv:2606. 23932v1 Announce Type: new Abstract: Proximal Policy Optimization (PPO) is the standard policy-gradient algorithm for on-policy reinforcement learning.
arXiv:2607. 28916v1 Announce Type: cross Abstract: Multistep credit assignment is critical for sample-efficient reinforcement learning, yet managing off-policy bias in Q-learning remains a fundamental challenge.
arXiv:2608. 02332v1 Announce Type: new Abstract: In offline reinforcement learning (RL), the distribution shift between behavioral data and the learned policy can lead to erroneous \emph{Q}-value estimation, thereby misguiding the direction of policy optimization.
arXiv:2506. 00818v2 Announce Type: replace-cross Abstract: Offline reinforcement learning for longitudinal studies often faces two linked challenges: rewards may be binary or bounded, and reward observations may be available only for a subset of trajectories or time points even when the corresponding state-action-next-state histories are available.
arXiv:2506. 07040v4 Announce Type: replace-cross Abstract: We study model-free methods for distributionally robust infinite-horizon average-reward Markov decision processes (MDPs).
arXiv:2602. 00781v2 Announce Type: replace Abstract: Online reinforcement learning in non-episodic, finite-horizon MDPs remains underexplored and is challenged by the need to estimate returns to a fixed terminal time.
arXiv:2506. 13862v2 Announce Type: replace-cross Abstract: In Reinforcement Learning (RL), regularization with a Kullback-Leibler divergence that penalizes large deviations between successive policies has emerged as a popular tool both in theory and practice.
arXiv:2607. 17897v1 Announce Type: new Abstract: Distributional soft policy iteration (DSPI) provides an important framework for combining distributional reinforcement learning (DRL) with maximum-entropy control, in which the policy evaluation step is governed by a distributional soft Bellman operator acting on entropy-regularised returns.