We run the Meta-Learning & Multi-Agent Learning Workshops (MLMA) to bring together world-renowned experts in order to advance the field of meta-learning and multi-agent learning. The 2021 MLMA workshop will be held in a hybrid form at the GoodAI headquarters in Prague and online.
Oranžérie: the office of GoodAI and location of the workshop
Previous editions
Watch talks from MLMA 2020 here.
MLMA 2021 Workshop
The aim of this workshop will be primarily to:
- Bring together the participants of GoodAI Grants program, as well as invited guests and GoodAI team
- Discuss in depth the preliminary findings and experimental results related to the awarded grants and state of GoodAI’s Badger architecture.
When and where?
July 26 – 30, 2021
Same as last year, we plan to hold the workshop in hybrid form: online and at the GoodAI headquarters in Prague – The Oranžérie (or online-only, if COVID situation doesn’t permit travel).
Format
The workshop will feature invited talks, however, the majority will be dedicated to focused discussions and work on experiments in groups.
Due to this format, the number of participants is limited to invited-only. Select sessions will be recorded and published online.
Topics
The concrete topics will crystallize as we approach the workshop date, so the discussion could focus on the specific results achieved by then. General areas of focus:
- Lifelong Learning
- Modular Meta-Learning
- Meta-Learning
- Open-Endedness
- Learned Optimizers
- Program Composition and Synthesis
- Optimization in Modular Systems
- Multi-Agent Reinforcement Learning
- Graph Neural Networks
- Learned Communication
For a detailed description of the areas of focus, please refer to the Research Ideas section on the GoodAI Grants page.
The workshop will take an interdisciplinary approach drawing on the fields of; machine learning, meta-learning, artificial life, network science, dynamical systems, complexity science, collective computation, social intelligence, creativity and communication, and more. The idea for this workshop came from the type of questions we’re solving while working on our Badger Architecture.