Reinforcement Learning

Learning Diverse Skills for Local Navigation under Multi-constraint Optimality
Proposing a constraint grouping method for diversity optimization maintaining near optimality.
Learning Diverse Skills for Local Navigation under Multi-constraint Optimality
FLD: Fourier Latent Dynamics for Structured Motion Representation and Learning
Proposing a self-supervised, structured representation and generation method that extracts spatial-temporal relationships in periodic or quasi-periodic motions.
FLD: Fourier Latent Dynamics for Structured Motion Representation and Learning
Legged Locomotion with Graph Neural Network Policies
Proposing structured control policies for locomotion tasks via graph neural networks based on the robot configuration morphology.
Legged Locomotion with Graph Neural Network Policies
Versatile Skill Control via Self-supervised Adversarial Imitation of Unlabeled Mixed Motions
Proposing a cooperative generative adversarial method for obtaining controllable skill sets from unlabeled datasets containing diverse state transition patterns.
Versatile Skill Control via Self-supervised Adversarial Imitation of Unlabeled Mixed Motions
Learning Agile Skills via Adversarial Imitation of Rough Partial Demonstrations
Proposing a generative adversarial method for inferring reward functions from partial and potentially physically incompatible demonstrations for successful skill acquirement where reference or expert demonstrations are not easily accessible.
Learning Agile Skills via Adversarial Imitation of Rough Partial Demonstrations
Object Manipulation via Hierarchical Reinforcement Learning Control
Employing a hierarchical control method to achieve complex high-level tasks by integrating locomotion and manipulation skills.
Object Manipulation via Hierarchical Reinforcement Learning Control
Autonomous Pose Tracking with Compositional Reinforcement Learning Policies
Employing a novel compositional control structure to allow legged systems to achieve full-pose trajectory tracking in a global coordinate system by integrating learned skills.
Autonomous Pose Tracking with Compositional Reinforcement Learning Policies
Hierarchical Deep Reinforcement Learning for Legged Robot Navigation
Learning to utilize learned low-level skills in high-level tasks by considering only high-level objectives.
Code
Hierarchical Deep Reinforcement Learning for Legged Robot Navigation
Actor-Critic Reinforcement Learning for a Lunar Lander
Extending vanilla policy gradients with advantage estimation.
Code
Actor-Critic Reinforcement Learning for a Lunar Lander