Oases of Cooperation: An Empirical Evaluation of Reinforcement Learning in the Iterated Prisoner's Dilemma.
Peter BarnettJohn BurdenPublished in: SafeAI@AAAI (2022)
Keyphrases
- reinforcement learning
- multi agent
- cooperative
- exploration exploitation dilemma
- function approximation
- distributed problem solving
- state space
- learning algorithm
- multi agent systems
- temporal difference learning
- reinforcement learning algorithms
- markov decision processes
- machine learning
- learning problems
- empirical evaluation
- evolutionary learning
- information sharing
- action selection
- temporal difference
- optimal policy
- control problems
- mobile robot
- learning process
- autonomous learning
- state abstraction
- real time
- human agent interaction