A Structure-aware Online Learning Algorithm for Markov Decision Processes.
Arghyadip RoyVivek S. BorkarAbhay KarandikarPrasanna ChaporkarPublished in: CoRR (2018)
Keyphrases
- markov decision processes
- reinforcement learning
- learning algorithm
- reinforcement learning algorithms
- state space
- optimal policy
- finite state
- decision processes
- finite horizon
- policy iteration
- planning under uncertainty
- risk sensitive
- dynamic programming
- transition matrices
- policy evaluation
- action sets
- model based reinforcement learning
- markov decision process
- average reward
- partially observable
- factored mdps
- infinite horizon
- reachability analysis
- temporal difference
- learning tasks
- collaborative filtering
- interval estimation