A Conservative Approach For Few-shot Transfer In Off-dynamics Reinforcement Learning

Abstract

Off-dynamics Reinforcement Learning (ODRL) seeks to transfer a policy from a source environment to a target environment characterized by distinct yet similar dynamics. In this context, traditional RL agents depend excessively on the dynamics of the source environment, resulting in the discovery of policies that excel in this environment but fail to provide reasonable performance in the target one. In the few-shot framework, a limited number of transitions from the target environment are introduced to facilitate a more effective transfer. Addressing this challenge, we propose an innovative approach inspired by recent advancements in Imitation Learning and conservative RL algorithms. The proposed method introduces a penalty to regulate the trajectories generated by the source-trained policy. We evaluate our method across various environments representing diverse off-dynamics conditions, where access to the target environment is extremely limited. These experiments include high-dimensiona

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keydaoudi2023a

Related papers

• Policy Learning For Off-dynamics RL With Deficient Support (2024)0.00
• Off-dynamics Reinforcement Learning: Training For Transfer With Domain Classifiers (2020)0.00
• MOBODY: Model Based Off-dynamics Offline Reinforcement Learning (2025)0.00
• Return Augmented Decision Transformer For Off-dynamics Reinforcement Learning (2024)0.00
• Single Episode Policy Transfer In Reinforcement Learning (2019)0.00
• IOB: Integrating Optimization Transfer And Behavior Transfer For Multi-policy Reuse (2023)5.24
• Diversity For Contingency: Learning Diverse Behaviors For Efficient Adaptation And Transfer (2023)0.00
• Conservative Exploration For Policy Optimization Via Off-policy Policy Evaluation (2023)0.00