eugenevinitsky

ai-deadlines

:alarm_clock: AI conference deadline countdowns

ai_on_threads

anki_gpt

Tools for using GPT to build anki cards

bayesian_reasoning_traffic

bayesian_traffic_highway

decentralized_bottlenecks

Code and figures for bottlenecks paper

ray

A high-performance distributed execution engine

robust_RL_multi_adversary

We investigate the effect of populations on finding good solutions to the robust MDP

sequential_social_dilemma_games

Repo for reproduction of sequential social dilemmas

stable-baselines

A fork of OpenAI Baselines, implementations of reinforcement learning algorithms

eugenevinitsky/sequential_social_dilemma_games

Repo for reproduction of sequential social dilemmas

eugenevinitsky/robust_RL_multi_adversary

We investigate the effect of populations on finding good solutions to the robust MDP

eugenevinitsky/decentralized_bottlenecks

Code and figures for bottlenecks paper

eugenevinitsky/bayesian_reasoning_traffic

eugenevinitsky/stable-baselines

A fork of OpenAI Baselines, implementations of reinforcement learning algorithms

eugenevinitsky/anki_gpt

Tools for using GPT to build anki cards

eugenevinitsky/bayesian_traffic_highway

eugenevinitsky/ray

A high-performance distributed execution engine

eugenevinitsky/ai-deadlines

:alarm_clock: AI conference deadline countdowns

eugenevinitsky/ai_on_threads

eugenevinitsky/on-policy

This is the official implementation of Multi-Agent PPO (MAPPO).

eugenevinitsky/active-domainrand

Code repository for Active Domain Randomization (https://arxiv.org/abs/1904.04762)

eugenevinitsky/antialiased-cnns

pip install antialiased-cnns to improve stability and accuracy

eugenevinitsky/CrowdNav

[ICRA19] Crowd-aware Robot Navigation with Attention-based Deep Reinforcement Learning

eugenevinitsky/drqv2

DrQ-v2: Improved Data-Augmented Reinforcement Learning

eugenevinitsky/git

Git Source Code Mirror - This is a publish-only repository and all pull requests are ignored. Please follow Documentation/SubmittingPatches procedure for any of your improvements.

eugenevinitsky/imaginaire

NVIDIA's Deep Imagination Team's PyTorch Library

eugenevinitsky/mpc.pytorch

A fast and differentiable model predictive control (MPC) solver for PyTorch.

eugenevinitsky/nocturne-1

A data-driven, fast driving simulator for multi-agent coordination under partial observability.

eugenevinitsky/open_spiel

OpenSpiel is a collection of environments and algorithms for research in general reinforcement learning and search/planning in games.

eugenevinitsky/planet

Learning Latent Dynamics for Planning from Pixels

eugenevinitsky/pycolab

A highly-customisable gridworld game engine with some batteries included. Make your own gridworld games to test reinforcement learning agents!

eugenevinitsky/rayutils

RayUtils

eugenevinitsky/reward-learning-rl

[RSS 2019] End-to-End Robotic Reinforcement Learning without Reward Engineering

eugenevinitsky/robogym

Robotics Gym Environments

eugenevinitsky/screamtime

Screams if you're on a website you shouldn't be

eugenevinitsky/streamlit-example

Example Streamlit app that you can fork to test out share.streamlit.io

eugenevinitsky/sumo-web3d

Web-based 3D visualization of SUMO microsimulations using TraCI and three.js.

eugenevinitsky/visual_mpc

Visual MPC implementation running on Rethink Sawyer Robot

eugenevinitsky/waymo-open-dataset

Waymo Open Dataset