Reinforcement Learning with Internal Reward for Multi-Agent Cooperation: A Theoretical Approach.
Fumito UwanoNaoki TatebeMasaya NakataKeiki TakadamaTim KovacsPublished in: BICT (2015)
Keyphrases
- reinforcement learning
- multi agent cooperation
- multi agent
- multi agent systems
- state space
- function approximation
- reinforcement learning algorithms
- learning algorithm
- supervised learning
- reward function
- model free
- transfer learning
- optimal policy
- learning agent
- multi armed bandit
- reinforcement learning methods
- average reward
- action space
- markov decision processes
- markov decision process
- partially observable
- theoretical analysis
- optimal control
- learning process
- policy gradient
- reward shaping
- partially observable environments
- cooperative