ELIGN: Expectation Alignment as a Multi-Agent Intrinsic Reward

Modern multi-agent reinforcement learning frameworks rely on centralized training and reward shaping to perform well. However, centralized training and dense rewards are not readily available in the real world. Current multi-agent algorithms struggle to learn in the alternative setup of decentralized training or sparse rewards.

Data and Resources

Cite this as

Zixian Ma, Rose Wang, Li Fei-Fei, Michael Bernstein, Ranjay Krishna (2024). Dataset: ELIGN: Expectation Alignment as a Multi-Agent Intrinsic Reward. https://doi.org/10.57702/n0g1w01t

DOI retrieved: December 2, 2024

Additional Info

Field Value
Created December 2, 2024
Last update December 2, 2024
Author Zixian Ma
More Authors
Rose Wang
Li Fei-Fei
Michael Bernstein
Ranjay Krishna