Theory of Mind with Guilt Aversion Facilitates Cooperative Reinforcement Learning.
Dung NguyenSvetha VenkateshPhuoc NguyenTruyen TranPublished in: CoRR (2020)
Keyphrases
- cooperative
- reinforcement learning
- multi agent
- multi agent reinforcement learning
- function approximation
- multiagent reinforcement learning
- optimal control
- reinforcement learning algorithms
- distributed problem solving
- state space
- transfer learning
- supervised learning
- evolutionary learning
- markov decision processes
- multi agent systems
- temporal difference
- control problems
- temporal difference learning
- solve complex tasks
- reinforcement learning methods
- relational reinforcement learning
- partially observable
- model free
- game theory
- dynamic programming
- genetic algorithm
- learning capabilities
- risk aversion
- e learning
- decision making
- information retrieval