Bisimulation for Markov Decision Processes through Families of Functional Expressions.
Norm FernsDoina PrecupSophia KnightPublished in: Horizons of the Mind (2014)
Keyphrases
- markov decision processes
- optimal policy
- finite state
- transition matrices
- reinforcement learning
- state space
- policy iteration
- dynamic programming
- average cost
- reachability analysis
- reinforcement learning algorithms
- decision theoretic planning
- planning under uncertainty
- model based reinforcement learning
- factored mdps
- state and action spaces
- action space
- finite horizon
- infinite horizon
- markov decision process
- risk sensitive
- action sets
- partially observable markov decision processes
- partially observable
- multistage
- sufficient conditions
- search space