Achieving Fairness in Multi-Agent Markov Decision Processes Using Reinforcement Learning.
Peizhong JuArnob GhoshNess B. ShroffPublished in: CoRR (2023)
Keyphrases
- markov decision processes
- reinforcement learning
- multi agent
- state space
- optimal policy
- finite state
- function approximation
- policy iteration
- reinforcement learning algorithms
- partially observable
- markov games
- planning under uncertainty
- action sets
- transition matrices
- action space
- decision theoretic planning
- model free
- stochastic games
- average reward
- finite horizon
- infinite horizon
- dynamic programming
- state and action spaces
- reachability analysis
- control problems
- single agent
- markov decision process
- decision processes
- machine learning
- average cost
- state abstraction
- temporal difference
- multi agent systems
- model based reinforcement learning
- factored mdps
- action selection
- game theory
- continuous state
- approximate dynamic programming
- actor critic
- optimal control
- learning algorithm