Algorithm powering the For You feed on X

Textbook on reinforcement learning from human feedback

A modular, primitive-first, python-first PyTorch library for Reinforcement Learning.

Code from the Deep Reinforcement Learning in Action book from Manning, Inc

Waymo Open Dataset

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

TensorZero is an open-source LLMOps platform that unifies an LLM gateway, observability, evaluation, optimization, and experimentation.

Deep Q-learning for playing tetris game

Deep reinforcement learning without experience replay, target networks, or batch updates.

Dopamine is a research framework for fast prototyping of reinforcement learning algorithms.

A technical report on convolution arithmetic in the context of deep learning

Composable transformations of Python+NumPy programs: differentiate, vectorize, JIT to GPU/TPU, and more

ONNX Runtime: cross-platform, high performance ML inferencing and training accelerator

AG2 (formerly AutoGen): The Open-Source AgentOS.Join us at: https://discord.gg/sNGSwQME3x

A programming framework for agentic AI

You like pytorch? You like micrograd? You love tinygrad! ❤️

MCTS project for Tetris

A deep reinforcement learning bot that plays tetris

🦁 A research-friendly codebase for fast experimentation of multi-agent reinforcement learning in JAX

Deep Reinforcement Learning for mobile robot navigation in ROS Gazebo simulator. Using Twin Delayed Deep Deterministic Policy Gradient (TD3) neural network, a robot learns to navigate to a random g…

A standard API for single-agent reinforcement learning environments, with popular reference environments and related utilities (formerly Gym)

A standard API for multi-agent reinforcement learning environments, with popular reference environments and related utilities

1 million FPS multi-agent driving simulator

Explorer is a PyTorch reinforcement learning framework for exploring new ideas.

Pytorch implementation of convolutional neural network visualization techniques

Deep Q Networks

A fully configurable Gymnasium compatible Tetris environment

Minimal and Clean Reinforcement Learning Examples