TeXDYNA: Hierarchical Reinforcement Learning in Factored MDPs.
Olga KozlovaOlivier SigaudChristophe MeyerPublished in: SAB (2010)
Keyphrases
- factored mdps
- hierarchical reinforcement learning
- markov decision processes
- state space
- reinforcement learning
- state abstraction
- policy iteration
- reward function
- average reward
- context specific
- model free
- approximate dynamic programming
- algebraic decision diagrams
- markov decision process
- markov decision problems
- basis functions
- heuristic search
- stochastic processes
- reinforcement learning algorithms
- linear program
- least squares
- fixed point
- planning under uncertainty
- finite state
- temporal difference
- markov chain
- domain specific