摘要: Policy Reuse (PR) provides Reinforcement Learning algorithms with a mechanism to bias an exploration process by reusing a set of past policies. Policy Reuse offers the challenge of balancing the exploitation of the ongoing learned... 展开
作者 | Fernandez, F. Veloso, M. | ||
---|---|---|---|
原报告号 | ADA456794 | 总页数 | 15 |
报告类别/文献类型 | AD / NTIS科技报告 | ||
关键词 | Software engineering Policies Robots Learning machines Artificial intelligence Markov processes Libraries Algorithms Decision making Random variables Bias Autonomous navigation Problem solving Efficiency Comparison Performance(Engineering) Robotics Neural nets |