Communicating via Markov Decision Processes.
Samuel SokotaChristian A. Schröder de WittMaximilian IglLuisa M. ZintgrafPhilip H. S. TorrMartin StrohmeierJ. Zico KolterShimon WhitesonJakob N. FoersterPublished in: ICML (2022)
Keyphrases
- markov decision processes
- state space
- optimal policy
- finite state
- dynamic programming
- reinforcement learning
- policy iteration
- transition matrices
- infinite horizon
- finite horizon
- reachability analysis
- factored mdps
- risk sensitive
- decision theoretic planning
- planning under uncertainty
- average cost
- reinforcement learning algorithms
- average reward
- markov decision process
- machine learning
- partially observable
- multistage
- model based reinforcement learning
- action space
- decision processes
- reward function
- linear programming
- decision making