Sample-Based Planning for Continuous Action Markov Decision Processes.
Christopher R. MansleyAri WeinsteinMichael L. LittmanPublished in: ICAPS (2011)
Keyphrases
- markov decision processes
- partially observable markov decision processes
- continuous action
- action space
- finite state
- planning under uncertainty
- continuous state
- partially observable
- decision theoretic planning
- optimal policy
- reinforcement learning
- state space
- policy search
- dynamic programming
- planning problems
- finite horizon
- reinforcement learning algorithms
- infinite horizon
- policy iteration
- average cost
- markov decision process
- heuristic search
- reward function
- average reward
- markov decision problems
- state action
- stochastic games
- real valued
- long run
- search algorithm
- control policies
- belief state
- decision making