arXiv:2507. 15356v2 Announce Type: replace Abstract: Offline reinforcement learning (RL) learns policies from fixed datasets, thereby avoiding costly or unsafe environment interactions.
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:2608.20909v1 Announce Type: new Abstract: Offline RL methods commonly jointly train the actor and critic, where the critic is used to guide the actor toward higher-value actions. This coupled l...
arXiv:2606. 09115v1 Announce Type: new Abstract: Offline reinforcement learning (RL) offers a path to policy improvement from logged data alone, using historical returns or other measurable outcomes as world feedback.
arXiv:2608. 11363v1 Announce Type: cross Abstract: A central goal in robot learning is to move beyond task-specific human data collection toward robots that improve through autonomous interaction.
arXiv:2605.13054v2 Announce Type: replace-cross Abstract: Cross-domain offline reinforcement learning learns a target policy from pre-collected source and target datasets with different dynamics. Whe...
The paper introduces BADA, a Boundary-Aware Data Augmentation technique for offline reinforcement learning. By interpolating neighboring states to create synthetic data that respects the original distribution, BADA improves in-distribution generalization and robustness. Experiments on limited offline datasets show that BADA achieves state-of-the-art performance across diverse benchmarks.
arXiv:2606. 02194v1 Announce Type: new Abstract: Distilling expert demonstration data into large generative models using behavioral cloning is a scalable approach to learning capable policies for robotic control, particularly for dexterous manipulation.
TailSFT is a simple modification to supervised fine‑tuning that filters out already well‑modeled sequences, concentrating learning on the tail of the data distribution. On the OLMo‑3 7B model, this approach improves pass@16 performance on math and coding tasks by up to 17% absolute and yields up to 4% absolute gains in subsequent GRPO reinforcement‑learning runs, with only minimal computational overhead. The authors also provide a lightweight diagnostic to identify settings where TailSFT is most beneficial and argue for a stage‑aware development strategy that evaluates intermediate checkpoints by their support for later training.
The paper introduces Q-Target Pretrained Transformers (QTPT), a method that replaces supervised behavior cloning with a Bellman-style Q‑target objective for in‑context reinforcement learning. QTPT retains the context‑conditioned Transformer architecture but learns to estimate action values using rewards and transitions from the context, rather than merely imitating offline actions. The authors provide theoretical analysis in stochastic linear bandits and finite‑horizon MDPs, demonstrating improved robustness to weak or suboptimal data, and empirically show gains over supervised pretraining on controlled RL benchmarks and extensions to D4RL Kitchen and AntMaze.
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:2608. 19684v1 Announce Type: new Abstract: Recent studies investigate how to leverage pre-collected datasets to improve the policy performance and sample efficiency of RL.
arXiv:2605.11151v3 Announce Type: replace Abstract: Offline-to-online reinforcement learning (RL) improves sample efficiency by leveraging pre-collected datasets prior to online interaction. A key ch...