Planning with Abstract Markov Decision Processes.
Nakul GopalanMarie desJardinsMichael L. LittmanJames MacGlashanShawn SquireStefanie TellexJohn WinderLawson L. S. WongPublished in: ICAPS (2017)
Keyphrases
- markov decision processes
- macro actions
- planning under uncertainty
- decision theoretic planning
- partially observable
- state space
- optimal policy
- reinforcement learning
- transition matrices
- finite state
- policy iteration
- reachability analysis
- dynamic programming
- reinforcement learning algorithms
- partially observable markov decision processes
- planning problems
- probabilistic planning
- heuristic search
- action sets
- markov decision process
- finite horizon
- decision processes
- average reward
- infinite horizon
- markov decision problems
- model based reinforcement learning
- risk sensitive
- factored mdps
- state and action spaces
- average cost
- decision theoretic
- goal oriented
- reward function
- initial state
- domain independent
- temporal difference
- action space
- action selection