facebookresearch / motif
Intrinsic Motivation from Artificial Intelligence Feedback
☆127Updated last year
Alternatives and similar repositories for motif:
Users that are interested in motif are comparing it to the libraries listed below
- Efficient World Models with Context-Aware Tokenization. ICML 2024☆92Updated 4 months ago
- Efficient baselines for autocurricula in JAX.☆179Updated 5 months ago
- Official implementation of the DECKARD Agent from the paper "Do Embodied Agents Dream of Pixelated Sheep?"☆91Updated last year
- ☆78Updated 7 months ago
- Simple single-file baselines for Q-Learning in pure-GPU setting☆137Updated 2 months ago
- ☆141Updated 9 months ago
- CleanRL's implementation of DeepMind's Podracer Sebulba Architecture for Distributed DRL☆109Updated 5 months ago
- Benchmarking Agentic LLM and VLM Reasoning On Games☆114Updated this week
- ☆70Updated 5 months ago
- Intelligent Go-Explore: Standing on the Shoulders of Giant Foundation Models☆51Updated 2 weeks ago
- Pytorch Implementation of MuZero Unplugged for gym environment. This algorithm is capable of supporting a wide range of action and observ…☆27Updated 2 years ago
- ☆73Updated 3 months ago
- General multi-task deep RL Agent☆176Updated 8 months ago
- Learn online intrinsic rewards from LLM feedback☆34Updated 2 months ago
- An OpenAI gym environment to evaluate the ability of LLMs (eg. GPT-4, Claude) in long-horizon reasoning and task planning in dynamic mult…☆64Updated last year
- The Controllable Agent project trains RL Agents able to optimize any reward function specified in real time, without any further learning…☆61Updated last year
- SmartPlay is a benchmark for Large Language Models (LLMs). Uses a variety of games to test various important LLM capabilities as agents. …☆131Updated 10 months ago
- STEVE-1: A Generative Model for Text-to-Behavior in Minecraft☆183Updated 8 months ago
- Lamorel is a Python library designed for RL practitioners eager to use Large Language Models (LLMs).☆214Updated 3 months ago
- Public code for "Reinforcement Learning from Passive Data via Latent Intentions"☆87Updated last year
- OMNI: Open-endedness via Models of human Notions of Interestingness☆42Updated 3 weeks ago
- Implementation of "Open-World Multi-Task Control Through Goal-Aware Representation Learning and Adaptive Horizon Prediction"☆45Updated last year
- ☆123Updated last year
- Code for "Learning to Model the World with Language." ICML 2024 Oral.☆378Updated last year
- [NeurIPS '23 Spotlight] Thought Cloning: Learning to Think while Acting by Imitating Human Thinking☆260Updated 7 months ago
- An Open-Ended Agentic Simulator☆39Updated 6 months ago
- Learning to Modulate pre-trained Models in RL (Decision Transformer, LoRA, Fine-tuning)☆53Updated 4 months ago
- Repo to reproduce the First-Explore paper results☆37Updated last month