Leveraging Fully Observable Policies for Learning under Partial Observability.
Hai NguyenAndrea BaiseroDian WangChristopher AmatoRobert PlattPublished in: CoRR (2022)
Keyphrases
- partial observability
- fully observable
- partially observable
- reinforcement learning
- learning process
- learning tasks
- learning algorithm
- search algorithm
- hidden state
- supervised learning
- planning domains
- partially observable markov decision processes
- belief state
- reward function
- solving problems
- state space
- bayesian networks