CausalWorld: A Robotic Manipulation Benchmark for Causal Structure and Transfer Learning

TL;DR

CausalWorld is a robotic manipulation benchmark designed to evaluate causal structure understanding and transfer learning, featuring customizable tasks with causal variables, intervention capabilities, and a range of difficulty levels for sim-to-real research.

Contribution

This paper introduces CausalWorld, a novel simulation environment with diverse, customizable tasks for studying causal transfer learning in robotics, including intervention and curriculum design features.

Findings

Baseline results demonstrate task feasibility and transfer potential.

Eight benchmark distributions cover a range of difficulty levels.

Intervention capabilities enable detailed causal analysis.

Abstract

Despite recent successes of reinforcement learning (RL), it remains a challenge for agents to transfer learned skills to related environments. To facilitate research addressing this problem, we propose CausalWorld, a benchmark for causal structure and transfer learning in a robotic manipulation environment. The environment is a simulation of an open-source robotic platform, hence offering the possibility of sim-to-real transfer. Tasks consist of constructing 3D shapes from a given set of blocks - inspired by how children learn to build complex structures. The key strength of CausalWorld is that it provides a combinatorial family of such tasks with common causal structure and underlying factors (including, e.g., robot and object masses, colors, sizes). The user (or the agent) may intervene on all causal variables, which allows for fine-grained control over how similar different tasks (or task distributions) are. One can thus easily define training and evaluation distributions of a desired difficulty level, targeting a specific form of generalization (e.g., only changes in appearance or object mass). Further, this common parametrization facilitates defining curricula by interpolating between an initial and a target task. While users may define their own task distributions, we present eight meaningful distributions as concrete benchmarks, ranging from simple to very challenging, all of which require long-horizon planning as well as precise low-level motor control. Finally, we provide baseline results for a subset of these tasks on distinct training curricula and corresponding evaluation protocols, verifying the feasibility of the tasks in this benchmark.