justinjfu Goto Github PK

.env

2021

Website for the Offline RL Workshop at NeurIPS 2020.

awr

Implementation of advantage-weighted regression.

chaos_theory

Deep reinforcement learning library

d4rl

A benchmark for offline reinforcement learning.

diagnosing_qlearning

Code for Diagnosing Bottlenecks in Deep Q-learning. Contains implementations of tabular environments plus solvers.

doodad

A job launching library for docker, EC2, GCP, etc.

dynamic_mjc

A library for programatically building MuJoCo XML files

exemplar_models

Exemplar models for approximate density estimation

hand_dapg

Repository to accompany RSS 2018 paper on dexterous hand manipulation

icnn

Input Convex Neural Networks

inverse_rl

jax

Composable transformations of Python+NumPy programs: differentiate, vectorize, JIT to GPU/TPU, and more

justinjfu.github.io

github.io website

pytop

Parses output of the unix top command

relay-policy-learning

renoir

resources

rlkit

Collection of reinforcement learning algorithms

rllab

rllab is a framework for developing and evaluating reinforcement learning algorithms, fully compatible with OpenAI Gym.

rlutil

sandbox

Random experiments & implementations

toy_vm

Toy Stack-based VM

vs265_lstm

LSTM Implementation

waymax

A JAX-based simulator for autonomous driving research.