The paper introduces Bidirectional Behavior Prior Distillation (B2PD), a method that uses action‑value priors to train a conditional variational autoencoder for generating high‑value behavior support. These expert behavior priors are then distilled into the online reinforcement learning agent, reducing inefficient exploration and stabilizing policy updates. Experiments on state‑ and pixel‑based tasks show that B2PD improves sample efficiency while maintaining stable learning dynamics.
arXiv:2607. 21302v1 Announce Type: new Abstract: Behavior prior reinforcement learning (BPRL) has emerged as a promising paradigm to improve sample efficiency in online reinforcement learning (RL) by leveraging policy priors derived from offline demonstrations.
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...
The paper introduces a minimal‑data adaptation regime where a pretrained robot policy learns a new task from a single demonstration followed by autonomous online interaction. It shows that while zero‑shot performance is poor, one demonstration can guide the policy toward coarse task‑following, and identifies key design principles—pretrained VLA representations for sample‑efficient value learning, residual policy learning for corrective behavior, and data‑balancing to avoid exploration collapse. The proposed MiDAS method, combining few‑demonstration behavior cloning with value‑based residual learning over frozen VLA representations, significantly boosts task success on LIBERO, RoboCasa, and a bimanual YAM platform after only a few hours of online interaction.
MInTRL (Minimal Intervention Reinforcement Learning) expands exploration in on-policy reinforcement learning by inserting sparse, local corrections into rollouts via a judge-intervention policy. These interventions replace erroneous suffixes and immediately return control to the main policy, allowing the agent to explore beyond its natural trajectory while maintaining on-policy data. The method uses a sequence-level advantage-regression objective, avoiding importance sampling, and demonstrates superior performance on math and code benchmarks compared to standard on-policy and off-policy baselines.
The paper investigates fine‑tuning reinforcement learning agents when offline data cannot be retained. It shows that continuing online behavioral cloning after the offline dataset disappears erodes the pretrained policy, leading to representational collapse and loss of action diversity. By freezing the expressive prior and stopping online behavioral fitting, the authors achieve better performance across several algorithms on seven OGBench domains.
arXiv:2605. 03065v2 Announce Type: replace Abstract: Generative control policies (GCPs), such as diffusion- and flow-based control policies, have emerged as effective parameterizations for robot learning.
arXiv:2610.19783v1 Announce Type: new Abstract: Reinforcement learning (RL) holds the promise of learning a policy that can outperform what is shown in the data. However, in practice, such systems su...
arXiv:2606. 08779v1 Announce Type: new Abstract: Reinforcement Learning (RL) has emerged as a pivotal post-training paradigm, yet it frequently suffers from unpredictable sub-optimum performance or even training collapses.
The paper introduces Cross-Behavior Policy Optimization (CBPO), a method that unifies offline demonstrations and policy-generated rollouts into a single regression loss using a fixed-reference target. CBPO eliminates the need for separate supervised fine‑tuning and reinforcement learning objectives, allowing positive and negative offline completions, reference responses, and current and historical rollouts to share a common reward‑labeled format and replay buffer. Experiments on two model scales and four mathematical reasoning benchmarks show that CBPO, especially the CBPO‑Unified variant, outperforms baseline methods in avg@32 and pass@32 metrics, with historical rollouts providing additional gains.
arXiv:2603. 05296v2 Announce Type: replace-cross Abstract: Offline reinforcement learning (RL) allows robots to learn from offline datasets without risky exploration.
arXiv:2107. 08183v2 Announce Type: replace Abstract: High-dimensional state and action spaces combined with sparse reward structures in reinforcement learning (RL) environments typically require advanced control architectures.
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...