Complexity Issues in Markov Decision Processes.
Judy GoldsmithMartin MundhenkPublished in: Computational Complexity Conference (1998)
Keyphrases
- markov decision processes
- state space
- optimal policy
- decision theoretic planning
- finite state
- reinforcement learning
- dynamic programming
- policy iteration
- transition matrices
- average reward
- infinite horizon
- reachability analysis
- average cost
- computational complexity
- finite horizon
- partially observable
- model based reinforcement learning
- reinforcement learning algorithms
- action space
- risk sensitive
- planning under uncertainty
- factored mdps
- decision processes
- continuous state spaces
- total reward
- semi markov decision processes
- interval estimation