Off-Dynamics Reinforcement Learning via Domain Adaptation and Reward Augmented Imitation
–Neural Information Processing Systems
Training a policy in a source domain for deployment in the target domain under a dynamics shift can be challenging, often resulting in performance degradation.
Neural Information Processing Systems
Feb-18-2026, 17:36:54 GMT
- Country:
- Asia > Japan
- Honshū > Chūbu > Ishikawa Prefecture > Kanazawa (0.04)
- North America
- Canada > Quebec
- Montreal (0.04)
- United States > California
- San Diego County > San Diego (0.04)
- Canada > Quebec
- Asia > Japan
- Genre:
- Research Report > Experimental Study (0.93)
- Industry:
- Health & Medicine (0.67)
- Information Technology (0.46)
- Technology: