Augmenting Reinforcement Learning to Enhance Cooperation in the Iterated Prisoner's Dilemma.
Grace FeehanShaheen FatimaPublished in: ICAART (3) (2022)
Keyphrases
- reinforcement learning
- cooperative
- multi agent
- exploration exploitation dilemma
- optimal policy
- function approximation
- reinforcement learning algorithms
- model free
- state space
- markov decision processes
- robotic control
- information exchange
- machine learning
- learning process
- learning algorithm
- learning problems
- temporal difference
- multi agent systems
- temporal difference learning
- multi agent reinforcement learning
- information retrieval