Specification revision for Markov decision processes with optimal trade-off.
Morteza LahijanianMarta Z. KwiatkowskaPublished in: CDC (2016)
Keyphrases
- markov decision processes
- trade off
- dynamic programming
- average cost
- average reward
- action sets
- finite state
- optimal policy
- finite horizon
- state space
- discounted reward
- policy iteration
- transition matrices
- total reward
- decision theoretic planning
- reinforcement learning algorithms
- partially observable
- stationary policies
- infinite horizon
- expected reward
- reinforcement learning
- planning under uncertainty
- risk sensitive
- continuous state spaces
- reachability analysis
- factored mdps
- state and action spaces
- decision processes
- markov decision process
- model based reinforcement learning
- semi markov decision processes
- knowledge base
- optimal solution
- decision problems
- belief revision
- optimal control
- reward function
- decision diagrams
- optimality criterion
- action space