Stars
PWM: Policy Learning with Large World Models
DAR introduces the diagonal scanning order for next-token prediction and proposes a direction-aware autoregressive transformer framework.
a continual learning optimizer mitigating catastrophic forgetting and loss of plasticity
Unified Implementations of Offline Reinforcement Learning Algorithms
An implementation of CAREL framework on Babyai and Semantic HELM.
A Multi-Task Dataset for Simulated Humanoid Control
[ECCV 2024] Official PyTorch implementation of RoPE-ViT "Rotary Position Embedding for Vision Transformer"
Implementation of Vision Transformer, a simple way to achieve SOTA in vision classification with only a single transformer encoder, in Pytorch
Poses-Openpose-GAN-project RNN LSTM
This repo contains the code for 1D tokenizer and generator
DeepSeek Coder: Let the Code Write Itself
NVIDIA Isaac GR00T N1 is the world's first open foundation model for generalized humanoid robot reasoning and skills.
Exploring techniques to generate diverse conventions in multi-agent settings
Repository for "Generative Flow Networks as Entropy-Regularized RL" (AISTATS-2024, Oral)
Distributed Reinforcement Learning accelerated by Lightning Fabric
One repository is all that is necessary for Multi-agent Reinforcement Learning (MARL)
This repository contains examples for RxInfer.jl
An offline deep reinforcement learning library
LeanRL is a fork of CleanRL, where selected PyTorch scripts optimized for performance using compile and cudagraphs.
1 million FPS multi-agent driving simulator
Zonos-v0.1 is a leading open-weight text-to-speech model trained on more than 200k hours of varied multilingual speech, delivering expressiveness and quality on par with—or even surpassing—top TTS …
The official implementation of flow Q-learning (FQL)
Implementation the paper: Discovering Object-Centric Generalized Value Functions From Pixels