Reinforcement Learning of Non-Markov Decision Processes.
Steven D. WhiteheadLong Ji LinPublished in: Artif. Intell. (1995)
Keyphrases
- markov decision processes
- reinforcement learning
- reinforcement learning algorithms
- optimal policy
- state space
- policy iteration
- finite state
- model based reinforcement learning
- dynamic programming
- action space
- reachability analysis
- state and action spaces
- partially observable
- markov decision process
- transition matrices
- state abstraction
- average cost
- planning under uncertainty
- factored mdps
- finite horizon
- decision processes
- function approximation
- machine learning
- learning algorithm
- infinite horizon
- average reward
- decentralized control
- temporal difference
- multi agent
- action sets
- supervised learning
- continuous state spaces
- policy evaluation
- stochastic games
- reward function
- markov chain
- decision theoretic planning
- markov decision problems
- optimal control
- semi markov decision processes
- partially observable markov decision processes