Reinforcement Learning

Unsupervised Skill Discovery for Robotic Manipulation through Automatic Task Generation

Unsupervised skill discovery approach using automatically generated tasks and asymmetric self-play to learn composable robotic manipulation behaviors.

Oct 7, 2024
SLIM: Skill Learning with Multiple Critics

Multi-critic actor-critic approach that combines multiple reward functions to discover safe, useful robotic manipulation skills.

Feb 1, 2024
Controlling the Solo12 Quadruped Robot with Deep Reinforcement Learning

End-to-end deep reinforcement learning controller for the open-source Solo12 quadruped robot, validated on real hardware.

Aug 2, 2023
LARG, Language-based Automatic Reward and Goal Generation

LLM-based approach that automatically converts text-based task descriptions into reward and goal-generation functions for robotic manipulation.

Jun 19, 2023
Safety-Aware Unsupervised Skill Discovery

Safe skill discovery approach for robotic manipulation combining reinforcement learning with safety constraints.

Jan 1, 2023
Graduate Level Instruction (2017 - Present)

Deep Learning, Reinforcement Learning, NLP, and LLMs - 150+ contact hours

Jan 1, 2023
Demonstration Conditioned Reinforcement Learning for Few-shot Imitation

Demonstration conditioned reinforcement learning approach for efficient few-shot imitation learning.

Jan 1, 2021
Non-Markovian Control with Gated End-to-End Memory Policy Networks

Memory-augmented policy networks for non-Markovian control problems with external memory modules.

Jan 1, 2017