Kelym

FAST

Code for "Tactical Rewind: Self-Correction via Backtracking in Vision-and-Language Navigation"

DeepRL-UCB2017-Homework

My solutions to the UC Berkeley Deep Reinforcement Learning course offered in 2017 Fall, taught by Sergey Levine. Course URL: rll.berkeley.edu/deeprlcourse/

adversarial-reinforcement-learning

Play to mislead RL agents

ACM_Training_Archive

CQL

Conservative Q Learning on top of SAC

CS231n

Have fun with Stanford Vision CS231n

franka_sim

Franka panda mujoco models

FrankaTest

gym

A toolkit for developing and comparing reinforcement learning algorithms.

kelym.github.io

Kay Ke's personal blog (Liyiming Ke)

mjrl

Reinforcement learning algorithms for MuJoCo tasks

One-Solution-is-Not-All-You-Need

One Solution is Not All You Need: Few-Shot Extrapolation via Structured MaxEnt RL

Playground

Store my codes and notes for toy problems in RL / Robot / DL / Vision / NLP / Graphic Model.

sunrise

SUNRISE: A Simple Unified Framework for Ensemble Learning in Deep Reinforcement Learning

TD3

Author's PyTorch implementation of TD3 for OpenAI gym tasks

Tetris

Trying to have fun with Tetris => Now I have PTSD with Tetris