Happiness as an intrinsic motivator in reinforcement learning.
Yue GaoShimon EdelmanPublished in: Adapt. Behav. (2016)
Keyphrases
- reinforcement learning
- reinforcement learning algorithms
- model free
- function approximation
- state space
- learning algorithm
- machine learning
- database
- multi agent reinforcement learning
- web retrieval
- control problems
- decision trees
- dynamic programming
- optimal policy
- transfer learning
- temporal difference learning
- neural network
- real time
- direct policy search
- partially observable
- learning capabilities
- action selection
- geometric structure
- markov decision processes
- dynamical systems
- supervised learning
- learning process
- multi agent