Reinforcement Learning,

An Open-Loop Baseline for Reinforcement Learning Locomotion Tasks

*Outstanding Paper Award on Empirical Resourcefulness in RL* In search of a simple baseline for Deep Reinforcement Learning in locomotion tasks, we propose a model-free open-loop strategy. By leveraging prior knowledge and the elegance of simple …

Learning to Exploit Elastic Actuators for Quadruped Locomotion

Spring-based actuators in legged locomotion provide energy-efficiency and improved performance, but increase the difficulty of controller design. While previous work has focused on extensive modeling and simulation to find optimal controllers for …

The 37 Implementation Details of Proximal Policy Optimization

Proximal policy optimization (PPO) has become one of the most popular deep reinforcement learning (DRL) algorithms. Yet, reproducing the PPO's results has been challenging in the community. While recent works conducted ablation studies to provide …

Stable-Baselines3: Reliable Reinforcement Learning Implementations

Stable-Baselines3 provides open-source implementations of deep reinforcement learning (RL) algorithms in Python. The implementations have been benchmarked against reference codebases, and automated unit tests cover 95% of the code. The algorithms …

Smooth Exploration for Robotic Reinforcement Learning

We extend the original state-dependent exploration (SDE) to apply deep reinforcement learning algorithms directly on real robots. The resulting method, gSDE, yields competitive results in simulation but outperforms the unstructured exploration on the real robot.

Decoupling feature extraction from policy learning: assessing benefits of state representation learning in goal based robotics

We evaluate the benefits of decoupling feature extraction from policy learning in robotics and propose a new way of combining state representation learning methods.

S-RL Toolbox: Environments, Datasets and Evaluation Metrics for State Representation Learning

State representation learning aims at learning compact representations from raw observations in robotics and control applications. Approaches used for this objective are auto-encoders, learning forward models, inverse dynamics or learning using …

Unsupervised learning of state representations for multiple tasks

We present an approach for learning state representations in multi-task reinforcement learning. Our method learns multiple low-dimensional state representations from raw observations in an unsupervised fashion, without any knowledge of which task is …