DeepAI AI Chat
Log In Sign Up

AnyMorph: Learning Transferable Polices By Inferring Agent Morphology

by   Brandon Trabucco, et al.

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 to new 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.


page 1

page 6

page 8


Task-Agnostic Morphology Evolution

Deep reinforcement learning primarily focuses on learning behavior, usua...

Subequivariant Graph Reinforcement Learning in 3D Environments

Learning a shared policy that guides the locomotion of different agents ...

Universal Morphology Control via Contextual Modulation

Learning a universal policy across different robot morphologies can sign...

Learning to Query Internet Text for Informing Reinforcement Learning Agents

Generalization to out of distribution tasks in reinforcement learning is...

A System for Morphology-Task Generalization via Unified Representation and Behavior Distillation

The rise of generalist large-scale models in natural language and vision...

C^2:Co-design of Robots via Concurrent Networks Coupling Online and Offline Reinforcement Learning

With the rise of computing power, using data-driven approaches for co-de...

Learning to Control Self-Assembling Morphologies: A Study of Generalization via Modularity

Contemporary sensorimotor learning approaches typically start with an ex...