Offline Goal-Conditioned Reinforcement Learning for Safety-Critical Tasks with Recovery Policy

1 code implementation • 4 Mar 2024 • Chenyang Cao, Zichen Yan, Renhao Lu, Junbo Tan, Xueqian Wang

Offline goal-conditioned reinforcement learning (GCRL) aims at solving goal-reaching tasks with sparse rewards from an offline dataset.

Safety Correction from Baseline: Towards the Risk-aware Policy in Robotics via Dual-agent Reinforcement Learning

no code implementations • 14 Dec 2022 • Linrui Zhang, Zichen Yan, Li Shen, Shoujie Li, Xueqian Wang, DaCheng Tao

On the other hand, the safe agent mimics the baseline agent for policy improvement and learns to fulfill safety constraints via off-policy RL tuning.

reinforcement-learning Reinforcement Learning (RL) +1