Review for NeurIPS paper: Efficient Model-Based Reinforcement Learning through Optimistic Policy Search and Planning
–Neural Information Processing Systems
In particular they convert epistemic uncertainty into "hallucinated controls" that are optimized, thereby leading to optimistic behavior.
efficient model-based reinforcement learning, neurips paper, optimistic policy search and planning, (2 more...)
Neural Information Processing Systems
Jan-27-2025, 05:32:22 GMT
- Technology: