Timezone: »

AnyMorph: Learning Transferable Polices By Inferring Agent Morphology
Brandon Trabucco · mariano phielipp · Glen Berseth

Tue Jul 19 03:30 PM -- 05:30 PM (PDT) @ Hall E #828

The prototypical approach to reinforcement learning involves training policies tailored to a particular agent from scratch for every new morphology.Recent work aims to eliminate the re-training of policies by investigating whether a morphology-agnostic policy, trained on a diverse set of agents with similar task objectives, can be transferred to new agents with unseen morphologies without re-training. This is a challenging problem that required previous approaches to use hand-designed descriptions of the new agent's morphology. Instead of hand-designing this description, we propose a data-driven method that learns a representation of morphology directly from the reinforcement learning objective.Ours is the first reinforcement learning algorithm that can train a policy to generalize tonew agent morphologies without requiring a description of the agent's morphology in advance. We evaluate our approach on the standard benchmark for agent-agnostic control, and improve over the current state of the art in zero-shot generalization to new agents. Importantly, our method attains good performance without an explicit description of morphology.

Author Information

Brandon Trabucco (Carnegie Mellon University)
mariano phielipp (Intel AI Labs)
Glen Berseth (Universite de Montreal/Mila)

Related Events (a corresponding poster, oral, or spotlight)

More from the Same Authors