Squint: Fast Visual Reinforcement Learning for Sim-to-Real Robotics

TL;DR

Squint is a novel visual reinforcement learning method that significantly accelerates training for robotic manipulation tasks, enabling rapid sim-to-real transfer with minimal training time.

Contribution

We introduce Squint, a fast, off-policy visual RL algorithm that outperforms existing methods in wall-clock training time for robotics tasks.

Findings

Squint trains policies in under 6 minutes on a single GPU.

Achieves successful sim-to-real transfer on a real robot.

Outperforms prior visual RL methods in training speed.

Abstract

Visual reinforcement learning is appealing for robotics but expensive -- off-policy methods are sample-efficient yet slow; on-policy methods parallelize well but waste samples. Recent work has shown that off-policy methods can train faster than on-policy methods in wall-clock time for state-based control. Extending this to vision remains challenging, where high-dimensional input images complicate training dynamics and introduce substantial storage and encoding overhead. To address these challenges, we introduce Squint, a visual Soft Actor Critic method that achieves faster wall-clock training than prior visual off-policy and on-policy methods. Squint achieves this via parallel simulation, a distributional critic, resolution squinting, layer normalization, a tuned update-to-data ratio, and an optimized implementation. We evaluate on the SO-101 Task Set, a new suite of eight manipulation tasks in ManiSkill3 with heavy domain randomization, and demonstrate sim-to-real transfer to a real SO-101 robot. We train policies for 15 minutes on a single RTX 3090 GPU, with most tasks converging in under 6 minutes.