Generalized Hindsight for Reinforcement Learning
–Neural Information Processing Systems
Intuitively, given a behavior generated under one task, Generalized Hindsight returns a different task that the behavior is better suited for. Then, the behavior is relabeled with this new task before being used by an off-policy RL optimizer.
Neural Information Processing Systems
Oct-2-2025, 23:41:12 GMT
- Country:
- North America > United States (0.28)
- Industry:
- Energy (0.93)
- Transportation (0.68)
- Leisure & Entertainment (0.67)
- Technology: