Mix&Match - Agent Curricula for Reinforcement Learning

Understand

We introduce Mix&Match (M&M) - a training framework designed to facilitate rapid and effective learning in RL agents, especially those that would be too slow or too challenging to train otherwise.

• The key innovation is a procedure that allows us to automatically form a curriculum over agents.
• Through such a curriculum we can progressively train more complex agents by, effectively, bootstrapping from solutions found by simpler agents.
• In contradistinction to typical curriculum learning approaches, we do not gradually modify the tasks or environments presented, but instead use a process to gradually alter how the policy is represented internally.