A memory-based reinforcement learning algorithm for partially observable Markovian decision processes.
Lei ZhengSiu-Yeung ChoChai QuekPublished in: IJCNN (2008)
Keyphrases
- markovian decision processes
- partially observable
- markov decision problems
- decision problems
- state space
- markov decision processes
- dynamical systems
- reinforcement learning
- partial observability
- infinite horizon
- partial observations
- reward function
- belief state
- optimal policy
- linear programming
- action models
- partially observable environments
- monte carlo
- planning domains
- partially observable markov decision processes
- markov decision process
- decision processes
- model checking