Header menu link for other important links
MAMIC: Macro and micro curriculum for robotic reinforcement learning
Published in International Foundation for Autonomous Agents and Multiagent Systems (IFAAMAS)
Volume: 4
Pages: 2226 - 2228
Shaping in humans and animals has been shown to be a powerful tool for learning complex tasks as compared to learning in a randomized fashion. This makes the problem less complex and enables one to solve the easier sub task at hand first. Generating a curriculum for such guided learning involves subjecting the agent to easier goals first, and then gradually increasing their difficulty. This paper takes a similar direction and proposes a dual curriculum scheme for solving robotic manipulation tasks with sparse rewards, called MaMiC. It includes a macro curriculum scheme which divides the task into multiple sub-tasks followed by a micro curriculum scheme which enables the agent to learn between such discovered sub-tasks. We show how combining macro and micro curriculum strategies help in overcoming major exploratory constraints considered in robot manipulation tasks without having to engineer any complex rewards. The performance of such a dual curriculum scheme is analyzed on the Fetch environments. © 2019 International Foundation for Autonomous Agents and Multiagent Systems (IFAAMAS). All rights reserved.
About the journal
JournalProceedings of the International Joint Conference on Autonomous Agents and Multiagent Systems, AAMAS
PublisherInternational Foundation for Autonomous Agents and Multiagent Systems (IFAAMAS)
Open AccessNo
Concepts (10)
  •  related image
  •  related image
    Machine learning
  •  related image
    Multi agent systems
  •  related image
    Reinforcement learning
  •  related image
  •  related image
  •  related image
  •  related image
  •  related image
  •  related image
    Autonomous agents