Mixing differential inclusions with Markov decision processes.
Nelson GonçalvesJoão SequeiraPublished in: IROS (2010)
Keyphrases
- markov decision processes
- state space
- finite state
- optimal policy
- dynamic programming
- transition matrices
- decision theoretic planning
- policy iteration
- planning under uncertainty
- finite horizon
- reachability analysis
- partially observable
- factored mdps
- reinforcement learning
- average cost
- reinforcement learning algorithms
- decision processes
- risk sensitive
- reward function
- model based reinforcement learning
- infinite horizon
- action sets
- state and action spaces