Back to Search
Start Over
A Consciousness-Inspired Planning Agent for Model-Based Reinforcement Learning
- Publication Year :
- 2021
-
Abstract
- 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.<br />Comment: NeurIPS camera-ready version
- Subjects :
- Computer Science - Artificial Intelligence
Computer Science - Machine Learning
Subjects
Details
- Database :
- arXiv
- Publication Type :
- Report
- Accession number :
- edsarx.2106.02097
- Document Type :
- Working Paper