leonkding

CLIP4MC

An RL-Friendly Vision-Language Model for Minecraft

Cradle

The Cradle framework is a first attempt at General Computer Control (GCC). Cradle supports agents to ace any computer task by enabling strong reasoning abilities, self-improvment, and skill curation, in a standardized general environment with minimal requirements.

EnDi

episodic-transformer-memory-ppo

Clean baseline implementation of PPO using an episodic TransformerXL memory

HLT

Implementation of the transformer from the paper: "Real-World Humanoid Locomotion with Reinforcement Learning"

humanoid-gym

Humanoid-Gym: Reinforcement Learning for Humanoid Robot with Zero-Shot Sim2Real Transfer https://arxiv.org/abs/2404.05695

humanplus

HumanPlus: Humanoid Shadowing and Imitation from Humans

I2C

nao_retarget_motion

This is a retargeting motion from humanoid character to NAO robot

STE-FlowNet

Spatio-Temporal Recurrent Networks for Event-Based Optical Flow Estimation (AAAI 2022)

leonkding/I2C

leonkding/STE-FlowNet

Spatio-Temporal Recurrent Networks for Event-Based Optical Flow Estimation (AAAI 2022)

leonkding/CLIP4MC

An RL-Friendly Vision-Language Model for Minecraft

leonkding/Cradle

The Cradle framework is a first attempt at General Computer Control (GCC). Cradle supports agents to ace any computer task by enabling strong reasoning abilities, self-improvment, and skill curation, in a standardized general environment with minimal requirements.

leonkding/EnDi

leonkding/episodic-transformer-memory-ppo

Clean baseline implementation of PPO using an episodic TransformerXL memory

leonkding/HLT

Implementation of the transformer from the paper: "Real-World Humanoid Locomotion with Reinforcement Learning"

leonkding/humanoid-gym

Humanoid-Gym: Reinforcement Learning for Humanoid Robot with Zero-Shot Sim2Real Transfer https://arxiv.org/abs/2404.05695

leonkding/humanplus

HumanPlus: Humanoid Shadowing and Imitation from Humans

leonkding/nao_retarget_motion

This is a retargeting motion from humanoid character to NAO robot