Blockwise Sequential Model Learning for Partially Observable Reinforcement Learning.
Giseung ParkSungho ChoiYoungchul SungPublished in: AAAI (2022)
Keyphrases
- reinforcement learning
- partially observable
- hidden state
- probabilistic model
- action models
- learning algorithm
- decision problems
- partial observations
- state space
- partially observable domains
- partially observable environments
- dynamical systems
- mathematical model
- prior knowledge
- markov decision processes
- decision theoretic
- model free
- computational complexity
- machine learning