Article

AtomicRL: An Atomic Reinforcement Learning Post-Training Framework for Long-Horizon Robotic Manipulation

The paper proposes AtomicRL, a framework that uses atomic task structure to improve reinforcement learning post-training of vision-language-action (VLA) policies. Its core components include Semantic-Aware Policy Optimization (SAPO), which uses semantic gating to prevent TD residuals from failed atomic subtasks from propagating across tasks, thereby mitigating credit contamination; and Bottleneck-Adaptive Target Exploration (BATE), which dynamically coordinates task sampling and local exploration incentives based on the mastery level of each subtask.

Part of the event: AtomicRL improves VLA policy reinforcement learning post-training with atomic task structure

This page provides a summary and source link only.