ManifoldRG / NEKOLinks
Implementation of GATO style Generalist Multimodal model capable of image, text, RL and Robotics tasks
☆45Updated last year
Alternatives and similar repositories for NEKO
Users that are interested in NEKO are comparing it to the libraries listed below
Sorting:
- Efficient World Models with Context-Aware Tokenization. ICML 2024☆116Updated last year
- Official implementation of the DECKARD Agent from the paper "Do Embodied Agents Dream of Pixelated Sheep?"☆94Updated 2 years ago
- Intelligent Go-Explore: Standing on the Shoulders of Giant Foundation Models☆66Updated 11 months ago
- Pytorch implementation of the Gato paper from Deepmind☆12Updated 3 years ago
- This code accompanies the paper "Leveraging Skills from Unlabeled Prior Data for Efficient Online Exploration."☆36Updated 6 months ago
- OMNI: Open-endedness via Models of human Notions of Interestingness☆58Updated last year
- A Generalist Benchmark for Multimodal Action models.☆36Updated last week
- ☆24Updated last year
- Multi-Modal Multi-Embodied Hivemind-like Iteration of RTX-2☆15Updated 7 months ago
- Using advances in generative modeling to learn reward functions from unlabeled videos.☆140Updated last year
- OMNI-EPIC: Open-endedness via Models of human Notions of Interestingness with Environments Programmed in Code (ICLR 2025).☆73Updated last year
- Selected list of papers on World Models that I found interesting and/or useful.☆34Updated last year
- Intrinsic Motivation from Artificial Intelligence Feedback☆134Updated 2 years ago
- Implementations of Curious Replay for model-based adaptation.☆43Updated 2 years ago
- [NeurIPS 2024] GenRL: Multimodal-foundation world models enable grounding language and video prompts into embodied domains, by turning th…☆86Updated 10 months ago
- Generative cellular automaton-like learning environments for RL.☆20Updated last year
- A Large Recurrent Action Model: xLSTM enables Fast Inference for Robotics Tasks☆36Updated last year
- Galactic Scaling End-to-End Reinforcement Learning for Rearrangement at 100k Steps-Per-Second☆86Updated 2 years ago
- General multi-task deep RL Agent☆185Updated last year
- Implementations of Temporal Difference InfoNCE (TD InfoNCE)☆33Updated 2 years ago
- Minimal code for A Generalist Agent☆44Updated 3 years ago
- GROOT: Learning to Follow Instructions by Watching Gameplay Videos (ICLR'24, Spotlight)☆67Updated 2 years ago
- Recall to Imagine, a model-based RL algorithm with superhuman memory. Oral (1.2%) @ ICLR 2024☆78Updated last year
- Codebase for PRISE: Learning Temporal Action Abstractions as a Sequence Compression Problem☆24Updated last year
- Code for the paper "Learning Temporal Distances: Contrastive Successor Features Can Provide a Metric Structure for Decision-Making"☆28Updated last year
- DynaMo: In-Domain Dynamics Pretraining for Visuo-Motor Control☆118Updated last year
- A web-based tool to collect human data from simulated environments.☆35Updated 4 years ago
- Synchronized Curriculum Learning for RL Agents☆121Updated last week
- ☆89Updated 3 months ago
- Implementation of Deepmind's RoboCat: "Self-Improving Foundation Agent for Robotic Manipulation" An next generation robot LLM☆87Updated 2 years ago