Evaluating Strategies for Markov Decision Processes in Parallel.
Kevin D. GlazebrookN. A. FayPublished in: Math. Oper. Res. (1990)
Keyphrases
- markov decision processes
- optimal policy
- state space
- finite state
- dynamic programming
- transition matrices
- policy iteration
- reinforcement learning
- reinforcement learning algorithms
- planning under uncertainty
- reachability analysis
- risk sensitive
- decision theoretic planning
- stochastic games
- decision processes
- factored mdps
- model based reinforcement learning
- semi markov decision processes
- average reward
- finite horizon
- average cost
- partially observable
- action space
- real time dynamic programming
- state abstraction
- markov decision problems
- state and action spaces
- decision problems