Timezone: »

 
Oral
The Emergence of Individuality
Jiechuan Jiang · Zongqing Lu

Tue Jul 20 06:00 PM -- 06:20 PM (PDT) @
in Reinforcement Learning 5 »

Individuality is essential in human society. It induces the division of labor and thus improves the efficiency and productivity. Similarly, it should also be a key to multi-agent cooperation. Inspired by that individuality is of being an individual separate from others, we propose a simple yet efficient method for the emergence of individuality (EOI) in multi-agent reinforcement learning (MARL). EOI learns a probabilistic classifier that predicts a probability distribution over agents given their observation and gives each agent an intrinsic reward of being correctly predicted by the classifier. The intrinsic reward encourages the agents to visit their own familiar observations, and learning the classifier by such observations makes the intrinsic reward signals stronger and in turn makes the agents more identifiable. To further enhance the intrinsic reward and promote the emergence of individuality, two regularizers are proposed to increase the discriminability of the classifier. We implement EOI on top of popular MARL algorithms. Empirically, we show that EOI outperforms existing methods in a variety of multi-agent cooperative scenarios.

Keywords: Reinforcement Learning and Planning · Multi-Agent RL

Author Information

Jiechuan Jiang (Peking University)
Zongqing Lu (Peking University)

Related Events (a corresponding poster, oral, or spotlight)

More from the Same Authors