Blockwise Sequential Model Learning for Partially Observable Reinforcement Learning.
Giseung ParkSungho ChoiYoungchul SungPublished in: CoRR (2021)
Keyphrases
- reinforcement learning
- partially observable
- hidden state
- action models
- mathematical model
- model free
- partially observable environments
- knowledge base
- markov decision processes
- state space
- prior knowledge
- decision theoretic
- domain independent
- markov decision process
- partial observability
- partially observable markov decision process
- objective function
- partially observable domains