Grow your team on GitHub
GitHub is home to over 50 million developers working together. Join them to grow your own development teams, manage permissions, and collaborate on projects.
Sign up
Pinned repositories
Repositories
-
-
phasic-policy-gradient
Code for the paper "Phasic Policy Gradient"
-
scheduler-plugins
Forked from kubernetes-sigs/scheduler-pluginsRepository for out-of-tree scheduler plugins based on scheduler framework.
-
retro
Retro Games in Gym
-
-
blocksparse
Efficient GPU kernels for block-sparse matrix multiplication and convolution
-
gym
A toolkit for developing and comparing reinforcement learning algorithms.
-
summarize-from-feedback
Code for "Learning to summarize from human feedback"
-
pixel
Code for the single pixel debate game from the paper "AI safety via debate" (https://arxiv.org/abs/1805.00899)
-
baselines
OpenAI Baselines: high-quality implementations of reinforcement learning algorithms
-
lustre
Forked from Cray/lustre -
-
spinningup
An educational resource to help anyone learn deep reinforcement learning.
-
mujoco-py
MuJoCo is a physics engine for detailed, efficient rigid body simulations with contacts. mujoco-py allows using MuJoCo from Python 3.
-
multiagent-particle-envs
Code for a multi-agent particle environment used in the paper "Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environments"
-
sparse_attention
Examples of using sparse attention, as in "Generating Long Sequences with Sparse Transformers"
-
gpt-2-output-dataset
Dataset of GPT-2 outputs for research in detection, biases, and more
-
distribution_augmentation
Code for the paper, "Distribution Augmentation for Generative Modeling", ICML 2020.
-
assign-one-project-github-action
Forked from srggrs/assign-one-project-github-actionAutomatically add an issue or pull request to specific GitHub Project when you create them.
-
procgen
Procgen Benchmark: Procedurally-Generated Game-Like Gym-Environments
-
gym3
Vectorized interface for reinforcement learning environments
-
jukebox
Code for the paper "Jukebox: A Generative Model for Music"
-
bchess-personal
temporarily public for a bug report
-
-
-
consul-helm
Forked from hashicorp/consul-helmHelm chart to install Consul and other associated components.
-
train-procgen
Code for the paper "Leveraging Procedural Generation to Benchmark Reinforcement Learning"