Exploiting Expert-guided Symmetry Detection in Markov Decision Processes.
Giorgio AngelottiNicolas DrougardCaroline P. C. ChanelPublished in: CoRR (2021)
Keyphrases
- markov decision processes
- symmetry detection
- optimal policy
- state space
- reinforcement learning
- policy iteration
- finite state
- transition matrices
- dynamic programming
- infinite horizon
- reachability analysis
- finite horizon
- action space
- reinforcement learning algorithms
- model based reinforcement learning
- average cost
- decision theoretic planning
- risk sensitive
- rotational symmetry
- planning under uncertainty
- average reward
- action sets
- decision processes
- state and action spaces
- partially observable
- real time dynamic programming
- learning rate
- function approximation
- objective function