Hierarchical Representation Learning for Markov Decision Processes.
Lorenzo SteccanellaSimone TotaroAnders JonssonPublished in: CoRR (2021)
Keyphrases
- markov decision processes
- reinforcement learning
- hierarchical representation
- state space
- model based reinforcement learning
- decision theoretic planning
- stochastic games
- learning algorithm
- macro actions
- optimal policy
- finite state
- partially observable
- computer vision
- transition matrices
- planning under uncertainty
- learning tasks
- finite horizon
- policy iteration
- infinite horizon
- lead time
- partially observed
- supervised learning
- reachability analysis
- object detection
- image processing
- real time dynamic programming