The Linear Programming Approach to Reach-Avoid Problems for Markov Decision Processes.
Nikolaos KariotoglouMaryam KamgarpourTyler H. SummersJohn LygerosPublished in: J. Artif. Intell. Res. (2017)
Keyphrases
- markov decision processes
- linear programming
- dynamic programming
- stochastic shortest path
- planning under uncertainty
- state space
- reinforcement learning
- optimal policy
- probabilistic planning
- action space
- policy iteration
- markov decision process
- average cost
- finite state
- decision processes
- transition matrices
- markov decision problems
- partially observable
- decision problems
- reinforcement learning algorithms
- decision theoretic planning
- state and action spaces
- continuous state spaces
- reachability analysis
- action sets
- partially observable markov decision processes
- infinite horizon
- average reward
- finite horizon
- factored mdps
- real time dynamic programming