Coordinated Exploration via Intrinsic Rewards for Multi-Agent Reinforcement Learning.
Shariq IqbalFei ShaPublished in: CoRR (2019)
Keyphrases
- multi agent reinforcement learning
- reinforcement learning
- multi agent
- cooperative
- markov decision processes
- learning agents
- action selection
- multi agent learning
- stochastic games
- multi agent systems
- state space
- function approximation
- bandit problems
- machine learning
- intelligent agents
- supervised learning
- optimal control
- robot soccer
- software agents
- optimal policy