Reward-Reinforced Reinforcement Learning for Multi-agent Systems.
Changgang ZhengShufan YangJuan Marcelo Parra UllauriAntonio García-DomínguezNelly BencomoPublished in: CoRR (2021)
Keyphrases
- reinforcement learning
- multi agent systems
- multi agent
- multi agent reinforcement learning
- single agent
- state space
- function approximation
- eligibility traces
- learning agent
- model free
- cooperative
- multi agent environments
- markov decision processes
- learning algorithm
- average reward
- reinforcement learning algorithms
- agent architecture
- optimal policy
- coalition formation
- game theory
- autonomous agents
- agent systems
- normative systems
- learning capabilities
- supervised learning
- learning agents
- machine learning
- temporal difference
- agent oriented
- multiagent systems
- computational logic
- neural network
- total reward
- agent platform
- policy evaluation
- distributed problem solving
- reinforcement learning methods
- learning classifier systems
- agent technology
- evaluation function
- transfer learning