Asymmetric actor critic for image-based robot learning

Implicit Drifting Policy: One-Step Action Generation via Conditional Expert Geometry

arXiv:2606. 01098v1 Announce Type: cross Abstract: Generative action policies based on diffusion or flow matching excel in behavior cloning, yet their iterative sampling is prohibitive for high-frequency robot control.

Lipschitz-Regularized Critics Lead to Policy Robustness Against Transition Dynamics Uncertainty

arXiv:2404. 13879v5 Announce Type: replace Abstract: Uncertainties in transition dynamics pose a critical challenge in reinforcement learning (RL), often resulting in performance degradation of trained policies when deployed on hardware.

Test-Time Gradient Guidance of Flow Policies in Reinforcement Learning

arXiv:2606. 11087v1 Announce Type: cross Abstract: Expressive continuous control policies, such as diffusion and flow models, form the backbone of recent advances in scaling imitation learning for simulated and real robot control.

Second-Order Actor-Critic Methods for Discounted MDPs via Policy Hessian Decomposition

arXiv:2605. 14982v2 Announce Type: replace-cross Abstract: We address the discounted reward setting in reinforcement learning (RL).

Pretraining in Actor-Critic Reinforcement Learning for Locomotion

arXiv:2510. 12363v4 Announce Type: replace-cross Abstract: The pretraining-finetuning paradigm has facilitated numerous transformative advancements in artificial intelligence research in recent years.

From Demonstrations to Rewards: Test-Time Prompt Optimization for VLM Reward Models

arXiv:2606. 00083v1 Announce Type: cross Abstract: Reinforcement learning relies on accurate reward functions, which are often hand-crafted or even unavailable in real-world applications, such as robotics.

One-shot imitation learning

Foundations of Reinforcement Learning and Control:Connections and New Perspectives

arXiv:2608. 02433v1 Announce Type: new Abstract: Reinforcement learning and control theory are two adjacent scientific fields that focus on optimizing the controller of unknown dynamical systems using feedback.

Learning Suffers More Than the Policy Class Under Partial Observability: A Closed-Form Analysis

arXiv:2608. 07228v1 Announce Type: new Abstract: When a reinforcement learning agent cannot observe the full state, we usually blame its policies: it cannot see enough to represent a good one.

Latent Policy Steering through One-Step Flow Policies

arXiv:2603. 05296v2 Announce Type: replace-cross Abstract: Offline reinforcement learning (RL) allows robots to learn from offline datasets without risky exploration.

Stabilizing the Q-Gradient Field for Policy Smoothness in Actor-Critic Methods

arXiv:2601. 22970v2 Announce Type: replace-cross Abstract: Policies learned via continuous actor-critic methods often exhibit erratic, high-frequency oscillations, making them unsuitable for physical deployment.

Training and Evaluating Diffusion Policies with Long Context Lengths

arXiv:2606. 16447v1 Announce Type: cross Abstract: Imitation learning has enabled highly-dexterous robotic manipulation from RGB observations.