Trace Relations and Logical Preservation for Continuous-Time Markov Decision Processes.
Arpit SharmaPublished in: ICTAC (2017)
Keyphrases
- markov decision processes
- state space
- reinforcement learning
- finite state
- dynamic programming
- optimal policy
- policy iteration
- transition matrices
- risk sensitive
- optimal control
- stationary policies
- planning under uncertainty
- finite horizon
- markov chain
- reachability analysis
- average reward
- markov decision process
- average cost
- infinite horizon
- partially observable
- reinforcement learning algorithms
- model based reinforcement learning
- semi markov decision processes
- decision theoretic planning
- state and action spaces
- state abstraction
- interval estimation
- multi agent
- search algorithm
- action sets
- factored mdps
- heuristic search
- multiple agents
- decision processes
- action space
- multi valued
- data mining