Causal Reinforcement Learning in Iterated Prisoner's Dilemma.
Yosra KazemiCaroline P. C. ChanelSidney GivigiPublished in: IEEE Trans. Comput. Soc. Syst. (2024)
Keyphrases
- reinforcement learning
- exploration exploitation dilemma
- function approximation
- markov decision processes
- causal networks
- causal relationships
- reinforcement learning algorithms
- optimal policy
- model free
- state space
- learning process
- bayesian networks
- causal independence
- robotic control
- learning algorithm
- learning problems
- real time
- causal reasoning
- causal relations
- temporal difference learning
- supervised learning
- function approximators
- policy search