ManifoldRG / NEKO
In Progress Implementation of GATO style Generalist Multimodal model capable of image, text, RL and Robotics tasks
☆48Updated 9 months ago
Alternatives and similar repositories for NEKO:
Users that are interested in NEKO are comparing it to the libraries listed below
- ☆24Updated this week
- Pytorch implementation of the Gato paper from Deepmind☆13Updated 2 years ago
- Official implementation of the DECKARD Agent from the paper "Do Embodied Agents Dream of Pixelated Sheep?"☆91Updated last year
- Intelligent Go-Explore: Standing on the Shoulders of Giant Foundation Models☆54Updated 3 weeks ago
- Efficient World Models with Context-Aware Tokenization. ICML 2024☆93Updated 6 months ago
- Official implementation of Zero-Hero paper☆22Updated last month
- a simple and scalable agent for training adaptive policies with sequence-based RL☆114Updated last month
- Galactic Scaling End-to-End Reinforcement Learning for Rearrangement at 100k Steps-Per-Second☆83Updated last year
- AgentHive provides the primitives and helpers for a seamless usage of robohive within TorchRL.☆33Updated last year
- Using advances in generative modeling to learn reward functions from unlabeled videos.☆124Updated last year
- ☆82Updated 8 months ago
- Public code for "Reinforcement Learning from Passive Data via Latent Intentions"☆87Updated last year
- A web-based tool to collect human data from simulated environments.☆32Updated 3 years ago
- Multi-Modal Multi-Embodied Hivemind-like Iteration of RTX-2☆16Updated 4 months ago
- DynaMo: In-Domain Dynamics Pretraining for Visuo-Motor Control☆99Updated 4 months ago
- General multi-task deep RL Agent☆178Updated 9 months ago
- Minimal code for A Generalist Agent☆39Updated 2 years ago
- This code accompanies the paper "Leveraging Skills from Unlabeled Prior Data for Efficient Online Exploration."☆27Updated 4 months ago
- Efficient baselines for autocurricula in JAX.☆186Updated 6 months ago
- Generative cellular automaton-like learning environments for RL.☆19Updated last month
- Implementation of Deepmind's RoboCat: "Self-Improving Foundation Agent for Robotic Manipulation" An next generation robot LLM☆81Updated last year
- Recall to Imagine, a model-based RL algorithm with superhuman memory. Oral (1.2%) @ ICLR 2024☆63Updated 9 months ago
- Code for "Hierarchical World Models as Visual Whole-Body Humanoid Controllers"☆167Updated 8 months ago
- [NeurIPS 2024] GenRL: Multimodal-foundation world models enable grounding language and video prompts into embodied domains, by turning th…☆70Updated 2 months ago
- Spot Sim2Real Infrastructure☆91Updated 2 weeks ago
- Code for "Unsupervised Zero-Shot RL via Functional Reward Representations"☆53Updated 11 months ago
- MTM Masked Trajectory Models for Prediction, Representation, and Control.☆150Updated last year
- Code for "Interactive Task Planning with Language Models"☆27Updated last year
- Simple single-file baselines for Q-Learning in pure-GPU setting☆142Updated last week