simonsays1980

the-algorithm

Source code for Twitter's Recommendation Algorithm

audiocraft

Audiocraft is a library for audio processing and generation with deep learning. It features the state-of-the-art EnCodec audio compressor / tokenizer, along with MusicGen, a simple and controllable music generation LM with textual and melodic conditioning.

sd

Intuitive find & replace CLI (sed alternative)

speedscope

🔬 A fast, interactive web-based viewer for performance profiles.

snakeviz

An in-browser Python profile viewer

brax

Massively parallel rigidbody physics simulation on accelerator hardware.

tuna

:fish: Python profile viewer

d3rlpy

An offline deep reinforcement learning library

CLR

envpool

C++-based high-performance parallel environment execution engine (vectorized env) for general RL environments.

CORL

High-quality single-file implementations of SOTA Offline and Offline-to-Online RL algorithms: AWAC, BC, CQL, DT, EDAC, IQL, SAC-N, TD3+BC, LB-SAC, SPOT, Cal-QL, ReBRAC

pytorch_memlab

Profiling and inspecting memory in pytorch

rliable

[NeurIPS'21 Outstanding Paper] Library for reliable evaluation on RL and ML benchmarks, even with only a handful of seeds.

OCTIS

OCTIS: Comparing Topic Models is Simple! A python package to optimize and evaluate topic models (accepted at EACL2021 demo track)

aviary

Ray Aviary - evaluate multiple LLMs easily

aquarel

Styling matplotlib made easy

AgileRL

Streamlining reinforcement learning with RLOps. State-of-the-art RL algorithms and tools.

askmybook

muzero-pytorch

Pytorch Implementation of MuZero

diffusion_policy

[RSS 2023] Diffusion Policy Visuomotor Policy Learning via Action Diffusion

DeepReinforcementLearningThatMatters

Accompanying code for "Deep Reinforcement Learning that Matters"

FlexDict

Easily work with deeply nested dictionaries and write clean code using FlexDict; a small subclass of dict. FlexDict provides automatic and arbitrary levels of nesting along with additional utility functions.

flacco

Feature-Based Landscape Analysis of Continuous and Constrained Optimization Problems

pysparklines

Python clone of @holman's spark

fromp

Contains code for the NeurIPS 2020 paper by Pan et al., "Continual Deep Learning by FunctionalRegularisation of Memorable Past"

bcf

[NeurIPS 2021 DDM Workshop] A hybrid control strategy for combining deep RL and classical robotic controllers

DRL-for-Pick-and-Place-Task-subtasks

A multi-subtask reinforcement learning method where complex tasks can be decomposed into low-level subtasks.

pflacco

Feature-Based Landscape Analysis of Continuous and Constrained Optimization Problems

CFN

Accompanying Code for "Flipping Coins to Estimate Pseudocounts for Exploration in Reinforcement Learning", ICML 2023

Match-Plan-Generation-in-Web-Search

Codes for WWW 2021 Paper-Match Plan Generation in Web Search with Parameterized Action Reinforcement Learning