Co-authors presented at Robomech2018

At Robomech2018 in Kitakyushu, my two students presented following contents.

“Continuous Learning using Fractal Reservoir Computing”

“Learning of Correlation in Autonomous Decentralized Multi-Agent with Individual Objectives”

The first presentation consists of the following.

  1. Purpose: to mitigate the learning problem using neural network, catastrophic forgetting
  2. Idea: to utilize the modularity of fractal network
  3. Method: to facilitate the activation of each module by adding an appropriate task input corresponding to each module

The second presentation consists of the following.

  1. Purpose: to achieve completely decentralized autonomous systems for multi-agent reinforcement learning (MARL)
  2. Idea: to propose a new problem setting, bottom-up MARL, where individual agent has own reward
  3. Method: to determine the degree of cooperation according to the learned correlation between rewards of other agents and own states