Asymmetric and adaptive reward coding via normalized reinforcement learning.
Kenway LouiePublished in: PLoS Comput. Biol. (2022)
Keyphrases
- reinforcement learning
- coding scheme
- state space
- function approximation
- adaptive control
- reinforcement learning algorithms
- model free
- learning capabilities
- eligibility traces
- markov decision processes
- learning process
- partially observable
- transfer learning
- action selection
- reward function
- coding method
- temporal difference
- machine learning
- optimal policy
- multi agent
- learning agent
- adaptive filtering
- actor critic
- partially observable environments