How to Play in Infinite MDPs (Invited Talk).
Stefan KieferRichard MayrMahsa ShirmohammadiPatrick TotzkeDominik WojtczakPublished in: ICALP (2020)
Keyphrases
- invited talk
- markov decision processes
- knowledge discovery and data mining
- selected papers
- reinforcement learning
- state space
- factored mdps
- markov decision process
- program committee
- dynamic programming
- database
- game playing
- average reward
- finite horizon
- policy iteration
- average cost
- optimal policy
- artificial neural networks
- decision making