Distributed Dynamic Programming forNetworked Multi-Agent Markov Decision Processes.
Okyong ChoiDonghwan LeePublished in: CoRR (2023)
Keyphrases
- markov decision processes
- multi agent
- dynamic programming
- reinforcement learning
- planning under uncertainty
- optimal policy
- state space
- finite state
- infinite horizon
- cooperative
- multi agent systems
- reachability analysis
- policy iteration
- average reward
- decision theoretic planning
- factored mdps
- finite horizon
- transition matrices
- stochastic games
- multiagent systems
- decentralized control
- decision processes
- partially observable markov decision processes
- risk sensitive
- multistage
- state and action spaces
- markov decision process
- model based reinforcement learning
- partially observable
- reinforcement learning algorithms
- reward function
- stationary policies
- decision diagrams
- probabilistic planning
- action space
- machine learning
- optimal control
- linear programming
- interval estimation