Collaborative Adaptation for Recovery from Unforeseen Malfunctions in Discrete and Continuous MARL Domains.
Yasin FindikHunter HasenfusReza AzadehPublished in: CoRR (2024)
Keyphrases
- continuous domains
- multi agent reinforcement learning
- discrete space
- continuous data
- continuous action
- continuous functions
- continuous variables
- discrete data
- discrete variables
- continuous space
- reinforcement learning
- knowledge sharing
- continuous valued
- collaborative learning
- multi agent learning
- state space
- machine learning
- multi agent systems
- multi agent
- learning algorithm