Adaptive reinforcement learning of multi-agent ethically-aligned behaviours: the QSOM and QDSOM algorithms.
Rémy ChaputOlivier BoissierMathieu GuillerminPublished in: CoRR (2023)
Keyphrases
- reinforcement learning
- multi agent
- learning algorithm
- cooperative
- worst case
- orders of magnitude
- theoretical analysis
- computationally efficient
- optimization problems
- computational cost
- computational complexity
- multi agent systems
- benchmark datasets
- data structure
- computational efficiency
- markov decision processes
- times faster