At this seminar, we will discuss a novel approach, called MAGnet, to multi-agent reinforcement learning (MARL) that utilizes a relevance graph representation of the environment obtained by a self-attention mechanism, and a message-generation technique inspired by the NerveNet architecture.
MAGnet approach was applied to the Pommerman game and the results show that it significantly outperforms state-of-the-art MARL solutions, including DQN, MCTSNet, and MADDPG.
Speaker: Aleksei Shpilman.
Presentation language: Russian.
Date and time: November 27th, 20:30-22:00.
Location: Times, white boards (4th floor).