Hybrid Hierarchical Reinforcement Learning for online guidance and navigation with partial observability.
Ye ZhouErik-Jan van KampenQiping ChuPublished in: Neurocomputing (2019)
Keyphrases
- partial observability
- hierarchical reinforcement learning
- reinforcement learning
- markov decision process
- belief state
- partially observable
- partially observable markov decision processes
- belief space
- probabilistic model
- state abstraction
- state space
- finite state
- learning agent
- planning under partial observability