Goal-conditioned Imitation Learning
Yiming Ding, Carlos Florensa, Pieter Abbeel, Mariano Phielipp
–Neural Information Processing Systems
Furthermore, we are often interested in being able to reach a wide range of configurations, hence setting up a different reward every time might be unpractical. Methods like Hindsight Experience Replay (HER) have recently shown promise to learn policies able to reach many goals, without the need of a reward.
Neural Information Processing Systems
Aug-20-2025, 02:00:32 GMT
- Country:
- North America
- Canada (0.04)
- United States > California
- Alameda County > Berkeley (0.04)
- North America
- Genre:
- Research Report (0.48)
- Industry:
- Leisure & Entertainment > Games (0.93)
- Technology: