A presentation explaining how Einsum could be understood and implemented.

Official implementation of Reach-Aware Value Estimation (RAVL) from the paper: "The Edge-of-Reach Problem in Offline Model-Based Reinforcement Learning."

The extended AI-Economist which will be compared with the extended Concordia, a generative agent-based model (GABM)

This repository contains the codebase for the research paper "An Empirical Study of Deep Reinforcement Learning in Continuing Tasks".

This repository contains the implementation of Ground4Act, a two-stage approach for collaborative pushing and grasping in clutter using a visual-language model.

JAX accelerated Quantum Monte Carlo

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

Neuroevolution is a Competitive Alternative to Reinforcement Learning for Skill Discovery

Minimalistic, hackable PyTorch implementation of SimSiam in ~400 lines. Achieves good performance on ImageNet with ResNet50. Features distributed training, real-time KNN eval, and AMP. Perfect for …

Learning grid cells by predictive coding

Goal-Conditioned Reinforcement Learning with JAX

Implementation of Diffusion Transformer (DiT) in JAX

Differentiable convex optimization layers

Pytorch-like dataloaders in JAX.

Advanced evolutionary computation library built directly on top of PyTorch, created at NNAISENSE.

An Open Large Reasoning Model for Real-World Solutions

Multi-agent simulator in Jax for research and teaching in AI & ALife

Benchmarking Agentic LLM and VLM Reasoning On Games

A curated list for awesome discrete diffusion models resources.

The Fastest Deep Reinforcement Learning Library

Source code and data for algorithms designed for decentralized anonymous/unlabeled multi-agent pathfinding (AMAPF)

Implementation of DreamerV3 in Pytorch

A reinforcement learning package for Julia

JAX reimplementation of the DeepMind paper "Genie: Generative Interactive Environments"

Paper collections of the continuous effort start from World Models.

Latent Program Network (from the "Searching Latent Program Spaces" paper)

Action Value Gradient Algorithm