Rewriting History with Inverse RL: Hindsight Inference for Policy Improvement Benjamin Eysenbach
–Neural Information Processing Systems
Several prior works have found that relabeling past experience with different reward functions can improve sample efficiency.
Neural Information Processing Systems
Aug-15-2025, 16:31:18 GMT
- Country:
- North America
- Canada (0.04)
- United States > Pennsylvania
- Allegheny County > Pittsburgh (0.04)
- North America
- Technology: