DoorGym: A Scalable Door Opening Environment And Baseline Agent
It provides a scalable environment for training agents on a practical robotics task, though it is incremental as it builds on existing domain randomization techniques.
The paper tackles the problem of training robust reinforcement learning policies for door opening by introducing DoorGym, an open-source simulation framework that uses domain randomization, achieving success rates from 0% to 95% on various doors and demonstrating real-world transfer.
In order to practically implement the door opening task, a policy ought to be robust to a wide distribution of door types and environment settings. Reinforcement Learning (RL) with Domain Randomization (DR) is a promising technique to enforce policy generalization, however, there are only a few accessible training environments that are inherently designed to train agents in domain randomized environments. We introduce DoorGym, an open-source door opening simulation framework designed to utilize domain randomization to train a stable policy. We intend for our environment to lie at the intersection of domain transfer, practical tasks, and realism. We also provide baseline Proximal Policy Optimization and Soft Actor-Critic implementations, which achieves success rates between 0% up to 95% for opening various types of doors in this environment. Moreover, the real-world transfer experiment shows the trained policy is able to work in the real world. Environment kit available here: https://github.com/PSVL/DoorGym/