Denis Yarats (denisyarats)

denisyarats

Geek Repo

Company:NYU

Location:New York

Home Page:https://cs.nyu.edu/~dy1042

Twitter:@denisyarats

Github PK Tool:Github PK Tool

Denis Yarats's repositories

pytorch_sac

PyTorch implementation of Soft Actor-Critic (SAC)

Language:Jupyter NotebookLicense:MITStargazers:515Issues:6Issues:7

drq

DrQ: Data regularized Q

Language:Jupyter NotebookLicense:MITStargazers:407Issues:13Issues:26

pytorch_sac_ae

PyTorch implementation of Soft Actor-Critic + Autoencoder(SAC+AE)

Language:PythonLicense:MITStargazers:226Issues:6Issues:5

dmc2gym

OpenAI Gym wrapper for the DeepMind Control Suite

Language:PythonLicense:MITStargazers:205Issues:5Issues:12

exorl

ExORL: Exploratory Data for Offline Reinforcement Learning

Language:PythonLicense:MITStargazers:105Issues:3Issues:4

proto

Proto-RL: Reinforcement Learning with Prototypical Representations

Language:PythonLicense:MITStargazers:82Issues:4Issues:5

densenet_cifar10

Meta-learning learning rates with higher

Language:PythonStargazers:12Issues:4Issues:0

dm_control2gym

OpenAI Gym Wrapper for DeepMind Control Suite

Language:PythonStargazers:4Issues:2Issues:0
Language:Jupyter NotebookStargazers:2Issues:5Issues:0

decision-transformer

Official codebase for Decision Transformer: Reinforcement Learning via Sequence Modeling.

Language:PythonLicense:MITStargazers:1Issues:1Issues:0
Language:PythonStargazers:1Issues:4Issues:0

pytorch-flows

PyTorch implementations of algorithms for density estimation

Language:PythonLicense:MITStargazers:1Issues:3Issues:0

rlenv

Docker Image for RL

TD3

PyTorch implementation of TD3 and DDPG for OpenAI gym tasks

Language:PythonStargazers:1Issues:3Issues:0
Language:HTMLStargazers:0Issues:2Issues:0
Stargazers:0Issues:2Issues:0
Stargazers:0Issues:2Issues:0
Language:Jupyter NotebookStargazers:0Issues:3Issues:0

dm_control

The DeepMind Control Suite and Package

Language:PythonLicense:Apache-2.0Stargazers:0Issues:2Issues:0

dreamerv2

Mastering Atari with Discrete World Models

Language:PythonLicense:MITStargazers:0Issues:1Issues:0

higher

higher is a pytorch library allowing users to obtain higher order gradients over losses spanning training loops rather than individual training steps.

Language:PythonLicense:Apache-2.0Stargazers:0Issues:1Issues:0
Language:Jupyter NotebookStargazers:0Issues:2Issues:0

mbrl-lib

Library for Model Based RL

Language:PythonLicense:MITStargazers:0Issues:1Issues:0

qhoptim

Implementations of quasi-hyperbolic optimization algorithms.

Language:PythonLicense:MITStargazers:0Issues:3Issues:0

rad

RAD: Reinforcement Learning with Augmented Data

Language:Jupyter NotebookStargazers:0Issues:2Issues:0
Stargazers:0Issues:2Issues:0

torchbeast

A PyTorch Platform for Distributed RL

Language:PythonLicense:Apache-2.0Stargazers:0Issues:2Issues:0

tutorials_week2

tutorials for MLSS 2019 Skoltech

Language:Jupyter NotebookStargazers:0Issues:0Issues:0
Language:JavaScriptStargazers:0Issues:2Issues:0

xt

torch TH/THC c++11 wrapper

Language:CStargazers:0Issues:2Issues:0