Learning Altruistic Behaviours in Reinforcement Learning without External Rewards.
Tim FranzmeyerMateusz MalinowskiJoão F. HenriquesPublished in: CoRR (2021)
Keyphrases
- reinforcement learning
- learning algorithm
- learning process
- reinforcement learning methods
- machine learning
- state space
- online learning
- knowledge acquisition
- neural network
- optimal policy
- reinforcement learning algorithms
- learning tasks
- markov decision processes
- learning systems
- unsupervised learning
- function approximation
- supervised learning
- state action
- learning agents
- temporal difference learning
- dynamic programming
- rl algorithms
- eligibility traces