Entropy Controlled Non-Stationarity for Improving Performance of Independent Learners in Anonymous MARL Settings.
Tanvi VermaPradeep VarakanthamHoong Chuin LauPublished in: CoRR (2018)
Keyphrases
- multi agent reinforcement learning
- learning process
- learning experience
- multi agent
- learning environment
- e learning
- learning activities
- learning systems
- learning materials
- peer to peer
- collaborative learning
- non stationary
- learning strategies
- information theoretic
- information theory
- mutual information
- learning resources
- knowledge acquisition
- intelligent agents
- multi agent systems
- distributed control
- neural network