Deep Hierarchical Reinforcement Learning Algorithm in Partially Observable Markov Decision Processes.
Le Pham TuyenNgo Anh VienMd. Abu LayekTaeChoong ChungPublished in: CoRR (2018)
Keyphrases
- partially observable markov decision processes
- finite state
- reinforcement learning
- planning under uncertainty
- belief state
- decision problems
- belief space
- optimal policy
- dynamical systems
- stochastic domains
- dynamic programming
- partial observability
- partially observable domains
- multi agent
- state space
- continuous state
- planning problems
- sequential decision making problems
- partially observable stochastic games
- partially observable
- markov decision processes
- single agent
- infinite horizon
- approximate solutions
- machine learning
- linear programming
- decision making