Solving Decentralized Continuous Markov Decision Problems with Structured Reward.
Emmanuel BenazeraPublished in: KI (2007)
Keyphrases
- markov decision problems
- reinforcement learning
- linear programming
- action space
- reward function
- state space
- partially observable
- optimal policy
- reward shaping
- decision theoretic
- multi agent
- expected utility
- markov decision processes
- decision processes
- policy iteration
- function approximation
- average reward
- stochastic shortest path
- transition probabilities
- utility function
- queueing networks
- average cost
- long run
- dynamic programming
- machine learning
- model free
- reinforcement learning algorithms
- solving problems
- function approximators