A Normative Account of Confirmation Bias During Reinforcement Learning.
Germain LefebvreChristopher SummerfieldRafal BogaczPublished in: Neural Comput. (2022)
Keyphrases
- reinforcement learning
- function approximation
- state space
- multi agent
- model free
- trade off
- reinforcement learning algorithms
- action selection
- markov decision processes
- temporal difference
- optimal policy
- multi agent systems
- temporal difference learning
- real robot
- markov decision process
- databases
- multi agent reinforcement learning
- monte carlo
- semi supervised
- cooperative
- feature selection
- learning algorithm
- machine learning