An ant system approach to Markov decision processes.
Hyeong Soo ChangWalter J. GutjahrJihoon YangSungyong ParkPublished in: ACC (2004)
Keyphrases
- markov decision processes
- optimal policy
- ant colony optimization
- state space
- policy iteration
- finite state
- reinforcement learning
- transition matrices
- reachability analysis
- finite horizon
- dynamic programming
- factored mdps
- reinforcement learning algorithms
- planning under uncertainty
- markov decision process
- decision theoretic planning
- average cost
- average reward
- action sets
- infinite horizon
- model based reinforcement learning
- decision processes
- reward function
- semi markov decision processes
- partially observable markov decision processes
- partially observable
- state and action spaces
- objective function