Team-partitioned, opaque-transition reinforcement learning
Proceedings of the third annual conference on Autonomous Agents
Hierarchical multi-agent reinforcement learning
Proceedings of the fifth international conference on Autonomous agents
Policy Invariance Under Reward Transformations: Theory and Application to Reward Shaping
ICML '99 Proceedings of the Sixteenth International Conference on Machine Learning
Learning the task allocation game
AAMAS '06 Proceedings of the fifth international joint conference on Autonomous agents and multiagent systems
Multiagent reinforcement learning and self-organization in a network of agents
Proceedings of the 6th international joint conference on Autonomous agents and multiagent systems
Performance bounded reinforcement learning in strategic interactions
AAAI'04 Proceedings of the 19th national conference on Artifical intelligence
Heuristic selection of actions in multiagent reinforcement learning
IJCAI'07 Proceedings of the 20th international joint conference on Artifical intelligence
| Hi-index | 0.00 |
Multi-Agent Reinforcement Learning (MARL) algorithms suffer from slow convergence and even divergence, especially in large-scale systems. In this work, we develop a supervision framework to speed up the convergence of MARL algorithms in a network of agents. The framework defines an organizational structure for automated supervision and a communication protocol for exchanging information between lower-level agents and higher-level supervising agents. The abstracted states of lower-level agents travel upwards so that higher-level supervising agents generate a broader view of the state of the network. This broader view is used in creating supervisory information which is passed down the hierarchy. We present a generic extension to MARL algorithms that integrates supervisory information into the learning process, guiding agents' exploration of their state-action space.