Status-quo Policy Gradient in Multi-Agent Reinforcement Learning.
Pinkesh BadjatiyaMausoom SarkarNikaash PuriJayakumar SubramanianAbhishek SinhaSiddharth SinghBalaji KrishnamurthyPublished in: AAMAS (2022)
Keyphrases
- status quo
- multi agent reinforcement learning
- policy gradient
- reinforcement learning
- reinforcement learning algorithms
- multi agent
- function approximation
- multi agent learning
- stochastic games
- gradient method
- single agent
- average reward
- optimal control
- partially observable markov decision processes
- multi agent systems
- learning agent
- model free
- variance reduction
- learning algorithm
- state space
- temporal difference
- learning automata
- markov decision processes
- dynamic programming
- cooperative
- action selection
- bayesian networks