Learning Cooperative Multi-Agent Policies with Partial Reward Decoupling.
Benjamin FreedAditya KapoorIan AbrahamJeff G. SchneiderHowie ChosetPublished in: CoRR (2021)
Keyphrases
- reinforcement learning
- learning algorithm
- learning systems
- knowledge base
- neural network
- learning tasks
- learning process
- inverse reinforcement learning
- input output
- mobile learning
- background knowledge
- knowledge acquisition
- general purpose
- supervised learning
- software engineering
- multi agent systems
- multi agent
- training data