David Ha

Cofounder of Sakana AI

Authored Projects (3)

Starred by

Benjamin Bolte

Benjamin Bolte(Cofounder of K-Scale Labs).

slimevolleygym by hardmaru

Gym environment for single/multi-agent RL research

Tests RL algos in a simple volleyball game setting.
Supports state-space and pixel-based observations.
Enables multi-agent, self-play, and imitation learning.
Includes pre-trained PPO models and baseline agents.

Created 5 years ago

Updated 1 year ago

Starred by

Aravind Srinivas

Aravind Srinivas(Cofounder of Perplexity)

Tom Brown

Tom Brown(Cofounder of Anthropic)

Benjamin Bolte

Benjamin Bolte(Cofounder of K-Scale Labs)

estool by hardmaru

Evolution Strategies tool for reinforcement learning research

Implements GA, Population-based REINFORCE, CMA-ES, and OpenAI's ES algorithms.
Includes parallel processing training with MPI.
Features self-contained Cartpole Swingup and Slime Volleyball Gym environments.
Supports PyBullet environments like Bullet Ant and custom Minitaur.

Created 8 years ago

Updated 2 years ago

Starred by

Aravind Srinivas

Aravind Srinivas(Cofounder of Perplexity) and

Tom Brown

Tom Brown(Cofounder of Anthropic).

WorldModelsExperiments by hardmaru

RL research paper reproduction

Trains VAE for environment latent-space encoding.
Uses MDN-RNN for world model dynamics prediction.
Employs evolution strategies for policy optimization.

Created 7 years ago

Updated 3 years ago

Starred Projects (15)

Perplexica by ItzCrazyKns

AI-powered search engine alternative

karpathy:

assafelovic:

taranjeet:

AlexCheema:

Created 1 year ago

Updated 10 hours ago

web-llm by mlc-ai

In-browser LLM inference engine using WebGPU for hardware acceleration

tobi:

didierrlopes:

doriandarko:

osanseviero:

Created 2 years ago

Updated 1 month ago

dalle-mini by borisdayma

Text-to-image model for generating images from text prompts

karpathy:

infwinston:

codekansas:

casper-hansen:

Created 4 years ago

Updated 1 year ago

cleanrl by vwxyzjn

RL algorithms implementation with research-friendly features

sxyu:

john-b-yang:

lysandrejik:

infwinston:

Created 6 years ago

Updated 3 months ago

chainerrl by chainer

Deep RL library for algorithm experimentation

aravindsrinivas:

junxiaosong:

joschu:

jekbradbury:

Created 8 years ago

Updated 4 years ago

c-swm by tkipf

PyTorch code for contrastive structured world model research paper

Created 6 years ago

Updated 5 years ago

numpy-ml by ddbourgin

ML algorithms implemented in NumPy

aravindsrinivas:

thinkall:

parano:

evhub:

Created 6 years ago

Updated 1 year ago

ludwig by ludwig-ai

Low-code framework for custom AI models (LLMs, neural networks)

aravindsrinivas:

winglian:

w4nderlust:

wesm:

Created 6 years ago

Updated 1 day ago

neataptic by wagenaartje

JS library for neural networks, evolution, and backpropagation

bcherny:

Created 8 years ago

Updated 6 years ago

rocket-lander by arex18

Box2D environment for vertical rocket landing simulation

Created 8 years ago

Updated 2 years ago

a3c_continuous by dgriff777

RL training repo for continuous action A3C with LSTM in PyTorch

AntonOsika:

Created 7 years ago

Updated 1 year ago

roboschool by openai

Deprecated robot simulation software integrated with OpenAI Gym

aravindsrinivas:

truell20:

bcherny:

vincentweisser:

Created 8 years ago

Updated 2 years ago

gym by openai

RL toolkit for reinforcement learning algorithm development

aravindsrinivas:

fchollet:

bcherny:

ValentaTomas:

Created 9 years ago

Updated 1 year ago

evolution-strategies-starter by openai

Research paper code for distributed evolution strategies

aravindsrinivas:

junxiaosong:

infwinston:

jekbradbury:

Created 8 years ago

Updated 6 years ago

tensorflow by tensorflow

Open-source ML framework

norvig:

aravindsrinivas:

karpathy:

bcherny:

Created 10 years ago

Updated 5 hours ago

Feedback? Help us improve.