zhanpenghe
Ph.D student at Columbia University Computer Science. Previously @uscresl.
Columbia University, @rlworkgroup
Pinned Repositories
Metaworld
Collections of robotics environments geared towards benchmarking multi-task and meta reinforcement learning
dowel
A little logger for machine learning research
garage
A toolkit for reproducible reinforcement learning research.
embed2learn
Embedding to Learn
Capsule-Network
Keras and tensorflow implementation of capsule network.
meta_agents
Pytorch implementation of meta-reinforcement-learning algorithms.
ProMP
ProMP: Proximal Meta-Policy Search
rlkit
Collection of reinforcement learning algorithms
SoftQLearning
Implementation of Soft QLearning Algorithm
USC-CS-Courses
Upload some of the assignments or projects for record.
zhanpenghe's Repositories
zhanpenghe/Capsule-Network
Keras and tensorflow implementation of capsule network.
zhanpenghe/USC-CS-Courses
Upload some of the assignments or projects for record.
zhanpenghe/meta_agents
Pytorch implementation of meta-reinforcement-learning algorithms.
zhanpenghe/SoftQLearning
Implementation of Soft QLearning Algorithm
zhanpenghe/rlkit
Collection of reinforcement learning algorithms
zhanpenghe/pallet
A collection of simple worlds
zhanpenghe/visual-pushing-grasping
Train robotic agents to learn to plan pushing and grasping actions for manipulation with deep reinforcement learning.
zhanpenghe/ProMP
ProMP: Proximal Meta-Policy Search
zhanpenghe/6dof-annotation
zhanpenghe/Drone-Vision
zhanpenghe/embed2learn
Embedding to Learn
zhanpenghe/file_sys
zhanpenghe/fyi_hook
Simple hook server to update static website with github.io
zhanpenghe/gym
A toolkit for developing and comparing reinforcement learning algorithms.
zhanpenghe/mj_envs
A collection of MuJoCo based environments.
zhanpenghe/playground
A place to hold my guilty pleasure.
zhanpenghe/pytorch-maml-rl
Reinforcement Learning with Model-Agnostic Meta-Learning in Pytorch
zhanpenghe/rllab
rllab is a framework for developing and evaluating reinforcement learning algorithms, fully compatible with OpenAI Gym.
zhanpenghe/rltoolkits
zhanpenghe/se3posenets-pytorch
Code for SE3-Pose-Nets paper from ICRA 2018.
zhanpenghe/torch-ngp
A pytorch CUDA extension implementation of instant-ngp (sdf and nerf), with a GUI.
zhanpenghe/Tracking-Core
[IoT Eye Project] The server for location caculation.