A Consciousness-Inspired Planning Agent for Model-Based Reinforcement Learning.

Annual Conference on Neural Information Processing Systems(2021)

引用 25|浏览25
暂无评分
摘要
We present an end-to-end, model-based deep reinforcement learning agent which dynamically attends to relevant parts of its state during planning. The agent uses a bottleneck mechanism over a set-based representation to force the number of entities to which the agent attends at each planning step to be small. In experiments, we investigate the bottleneck mechanism with several sets of customized environments featuring different challenges. We consistently observe that the design allows the planning agents to generalize their learned task-solving abilities in compatible unseen environments by attending to the relevant objects, leading to better out-of-distribution generalization performance.
更多
查看译文
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络