DoorGym: A Scalable Door Opening Environment And Baseline Agent

August 05, 2019 · Entered Twilight · 🏛 arXiv.org

"Last commit was 5.0 years ago (≥5 year threshold)"

Evidence collected by the PWNC Scanner

Repo contents: .gitignore, .gitmodules, DoorGym-Unity, LICENSE, README.md, a2c_ppo_acktr, doorenv2, enjoy.py, environment, envs, imgs, logs-dev, main.py, requirements.dev.txt, requirements.txt, rlkit, trained_models-dev, trained_visionmodel, util.py, world_generator

Authors Yusuke Urakami, Alec Hodgkinson, Casey Carlin, Randall Leu, Luca Rigazio, Pieter Abbeel arXiv ID 1908.01887 Category cs.RO: Robotics Cross-listed cs.AI, cs.LG Citations 62 Venue arXiv.org Repository https://github.com/PSVL/DoorGym/ ⭐ 118 Last Checked 1 month ago

Abstract

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/