Causal Markov Decision Processes: Learning Good Interventions Efficiently.
Yangyi LuAmirhossein MeisamiAmbuj TewariPublished in: CoRR (2021)
Keyphrases
- markov decision processes
- reinforcement learning
- dynamic programming
- learning algorithm
- stochastic games
- learning tasks
- model based reinforcement learning
- macro actions
- optimal policy
- reward function
- policy iteration
- state space
- reachability analysis
- infinite horizon
- average reward
- supervised learning
- state abstraction
- discounted reward
- optimal solution