Smooth Exploration for Robotic Reinforcement Learning

Code

• github.com/DLR-RM/stable-baselines3
  OfficialIn paperpytorch★ 12,962
• github.com/facebookresearch/rl
  jax★ 3,347
• github.com/araffin/sbx
  jax★ 572
• github.com/markub3327/rl-toolkit
  tf★ 21

Abstract

Reinforcement learning (RL) enables robots to learn skills from interactions with the real world. In practice, the unstructured step-based exploration used in Deep RL -- often very successful in simulation -- leads to jerky motion patterns on real robots. Consequences of the resulting shaky behavior are poor exploration, or even damage to the robot. We address these issues by adapting state-dependent exploration (SDE) to current Deep RL algorithms. To enable this adaptation, we propose two extensions to the original SDE, using more general features and re-sampling the noise periodically, which leads to a new exploration method generalized state-dependent exploration (gSDE). We evaluate gSDE both in simulation, on PyBullet continuous control tasks, and directly on three different real robots: a tendon-driven elastic robot, a quadruped and an RC car. The noise sampling interval of gSDE permits to have a compromise between performance and smoothness, which allows training directly on the real robots without loss of performance. The code is available at https://github.com/DLR-RM/stable-baselines3.

Tasks

Benchmark Results

Reproductions