arXiv:2608. 09967v1 Announce Type: new Abstract: Deep reinforcement learning (DRL) agents achieve strong performance in complex environments, yet their decision-making processes remain difficult to interpret.
Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.
arXiv:2510. 19244v3 Announce Type: replace Abstract: Deep reinforcement learning (RL) achieves remarkable performance but lacks interpretability, limiting trust in policy behavior.
arXiv:2602. 14169v2 Announce Type: replace-cross Abstract: Effective exploration is a key challenge in reinforcement learning for large language models: discovering high-quality trajectories within a limited sampling budget from the vast natural language sequence space.
arXiv:2507. 15356v2 Announce Type: replace Abstract: Offline reinforcement learning (RL) learns policies from fixed datasets, thereby avoiding costly or unsafe environment interactions.
arXiv:2601. 19612v3 Announce Type: replace-cross Abstract: Safe exploration is a key requirement for reinforcement learning (RL) agents to learn and adapt online, beyond controlled (e.
arXiv:2607. 07235v1 Announce Type: cross Abstract: Explainability remains a key issue in reinforcement learning (RL).
The paper introduces the concept of behavior-consistent deep reinforcement learning, aiming to produce high-performing policies that remain distributionally similar across different training runs. It shows that maximum-entropy RL can control behavioral divergence by anchoring runs to a common prior, and proves that for Boltzmann policies, a temperature proportional to Q‑function disagreement limits pairwise KL divergence. Building on this, the authors propose Q‑value Expectile Disagreement (QED), a state‑dependent temperature schedule that uses double‑critic disagreement to approximate cross‑run disagreement, and demonstrate that QED reduces across‑run divergence by two orders of magnitude on 18 continuous‑control tasks without sacrificing performance.