PufferAI ORG

Puffing up reinforcement learning

CUDA Docker for PufferLib

Gymnasium environment for Pokemon Red

Cost aware hyperparameter tuning algorithm

SpaceX Falcon 9 Box2D continuous-action simulation with traditional and AI controllers.

Our website

Documentation for PufferLib

Procgen Benchmark: Procedurally-Generated Game-Like Gym-Environments

Base images for PufferTank, PufferLib, and supported projects

No description.

Hosting web demos for PufferLib's first-party environments

A reinforcement learning codebase focusing on the emergence of cooperation and alignment in multi-agent AI systems.

No description.

CoGames is a collection of multi-agent cooperative and competitive environments designed for reinforcement learning research.

Box2D is a 2D physics engine for games

Vectorized interface for reinforcement learning environments

SAPIEN Manipulation Skill Framework, an open source GPU parallelized robotics simulator and benchmark, led by Hillbot, Inc.

Tensors and Dynamic neural networks in Python with strong GPU acceleration

puffer_drive dev

Implementation of Dreamer v3 in pytorch.

A fast grid-based open-ended MARL environment

No description.

IntersectionZoo: Eco-driving for Benchmarking Multi-Agent Contextual Reinforcement Learning

No description.

Fork for updating deps and bug fixes

GPU-acceleration of Nocturne via Madrona

Development build of PufferLib docs

An experiment with different Python extensions for flattening and unflattening data