Theory of Mind with Guilt Aversion Facilitates Cooperative Reinforcement Learning.
Dung NguyenSvetha VenkateshPhuoc NguyenTruyen TranPublished in: ACML (2020)
Keyphrases
- cooperative
- reinforcement learning
- multi agent
- function approximation
- multi agent reinforcement learning
- reinforcement learning algorithms
- state space
- multi agent systems
- multiagent reinforcement learning
- learning process
- markov decision processes
- solve complex tasks
- cooperative learning
- model free
- action selection
- temporal difference
- data mining
- cooperating agents
- neural network
- optimal policy
- machine learning
- learning classifier systems
- optimal control
- game theory
- learning capabilities
- partially observable
- real robot
- function approximators
- distributed problem solving
- active learning
- evolutionary algorithm
- robotic control
- direct policy search
- database