Entropy Maximization for Partially Observable Markov Decision Processes.
Yagiz SavasMichael HibbardBo WuTakashi TanakaUfuk TopcuPublished in: IEEE Trans. Autom. Control. (2022)
Keyphrases
- partially observable markov decision processes
- finite state
- planning under uncertainty
- belief state
- dynamical systems
- reinforcement learning
- belief space
- decision problems
- continuous state
- optimal policy
- partially observable stochastic games
- partial observability
- markov decision processes
- dynamic programming
- stochastic domains
- state space
- partially observable domains
- predictive state representations
- partially observable markov
- planning problems
- objective function
- partially observable
- markov chain
- multi agent
- sequential decision making problems
- partially observable markov decision process
- point based value iteration
- dec pomdps
- data mining