CRONOS: Benchmarking Non-Episodic Reinforcement Learning for Robotic Manipulation
It is shown that naively fine-tuning pre-trained policies fails in non-episodic settings due to shifts in object configurations and end-effector poses; however, these challenges can be mitigated through targeted reset allocation and by addressing biases in pre-trained models.
Po-Yi Wu, Djengo Cyun-Jyun Fang, Dian-Cheng Cheng et al.
· 0 citations