arXiv:2601. 22823v2 Announce Type: replace-cross Abstract: We study offline reinforcement learning of style-conditioned policies using explicit style supervision via subtrajectory labeling functions.
arXiv:2607. 07859v1 Announce Type: new Abstract: Reinforcement learning (RL) research has increasingly shifted focus towards alignment, ensuring agents learn behaviors adhering to human values.
arXiv:2506. 12529v2 Announce Type: replace-cross Abstract: Preference-based Reinforcement Learning (PbRL) entails a variety of approaches for aligning models with human intent to alleviate the burden of reward engineering.
arXiv:2607. 20834v1 Announce Type: new Abstract: Offline goal-conditioned reinforcement learning (RL) holds the promise of learning general-purpose policies from static datasets.
arXiv:2502. 17666v5 Announce Type: replace-cross Abstract: Existing offline in-context reinforcement learning (ICRL) methods have predominantly relied on supervised training objectives, which are known to have limitations in offline RL settings.
arXiv:2509. 02522v3 Announce Type: replace-cross Abstract: Recent advances in Reinforcement Learning with Verifiable Rewards (RLVR) have empowered large language models (LLMs) to tackle challenging reasoning tasks such as mathematics and programming, however existing RLVR methods often suffer from sparse reward signals and unstable policy gradient updates inherent to RL-based approaches.
Pre-training followed by fine-tuning has become the dominant recipe for learning performant policies, and in value-based reinforcement learning (RL) this raises a natural question: given a pretrained policy, should the Q-function be pretrained on offline data too? Conventional wisdom suggests it should, but recent results show that online RL with a randomly-initialized Q-function can result in highly performant and reliable policies without needing to pretrain the Q-function.
arXiv:2607. 27203v1 Announce Type: new Abstract: Pre-training followed by fine-tuning has become the dominant recipe for learning performant policies, and in value-based reinforcement learning (RL) this raises a natural question: given a pretrained policy, should the Q-function be pretrained on offline data too?
arXiv:2502. 19544v3 Announce Type: replace Abstract: Leveraging offline data is a promising way to improve the sample efficiency of online reinforcement learning (RL).
arXiv:2306. 09712v2 Announce Type: replace Abstract: In reinforcement learning (RL), there are two major settings for interacting with the environment: online and offline.
arXiv:2605. 05172v2 Announce Type: replace-cross Abstract: Behavior Cloning (BC) has emerged as a highly effective paradigm for robot learning.
arXiv:2602. 17632v3 Announce Type: replace-cross Abstract: Modern offline Reinforcement Learning (RL) methods find performant actor-critics, however, fine-tuning these actor-critics online with value-based RL algorithms typically causes immediate drops in performance.
arXiv:2606. 27608v1 Announce Type: cross Abstract: We present Qwen-Image-2.