Modelling Emotion Based Reward Valuation with Computational Reinforcement Learning.
Can KolumanChristopher ChildTillman WeydePublished in: CogSci (2019)
Keyphrases
- reinforcement learning
- function approximation
- temporal difference
- state space
- reinforcement learning algorithms
- partially observable environments
- transfer learning
- model free
- learning process
- total reward
- policy search
- action selection
- mathematical programming
- optimal policy
- supervised learning
- facial expressions
- dynamic programming
- reward function
- policy iteration
- action space
- control policy
- eligibility traces
- robotic control
- interactive computer