Tackling Asymmetric and Circular Sequential Social Dilemmas with Reinforcement Learning and Graph-based Tit-for-Tat.
Tangui Le GléauXavier MarjouTayeb LemloumaBenoit RadierPublished in: CoRR (2022)
Keyphrases
- reinforcement learning
- function approximation
- model free
- state space
- sequential search
- reinforcement learning algorithms
- markov decision processes
- harmonic functions
- optimal policy
- multi agent
- temporal difference
- real time
- robotic control
- hough transform
- database
- learning process
- artificial neural networks
- graph theoretic
- semi supervised
- transfer learning
- partially observable
- function approximators
- polar coordinates
- autonomous learning
- training data
- evolutionary algorithm