google-deepmind / alphadevLinks
☆714Updated 2 years ago
Alternatives and similar repositories for alphadev
Users that are interested in alphadev are comparing it to the libraries listed below
Sorting:
- Monte Carlo tree search in JAX☆2,507Updated 3 months ago
- Transformers are Sample-Efficient World Models. ICLR 2023, notable top 5%.☆839Updated 9 months ago
- ☆2,764Updated last year
- Evolution Through Large Models☆726Updated last year
- Open-source codebase for EfficientZero, from "Mastering Atari Games with Limited Data" at NeurIPS 2021.☆903Updated last year
- ☆539Updated last year
- ☆899Updated last year
- ☆486Updated 2 years ago
- Convolutions for Sequence Modeling☆891Updated last year
- Tool for data extraction and interacting with Lean programmatically.☆676Updated last month
- Implementation of Q-Transformer, Scalable Offline Reinforcement Learning via Autoregressive Q-Functions, out of Google Deepmind☆389Updated 3 weeks ago
- Data and code for the paper "A Neural Network Solves, Explains, and Generates University Math Problems by Program Synthesis and Few-Shot …☆184Updated 2 years ago
- ☆400Updated last week
- Unofficial Gato: A Generalist Agent☆214Updated last year
- Implementation of the specific Transformer architecture from PaLM - Scaling Language Modeling with Pathways☆823Updated 2 years ago
- Extremely Fast End-to-End Deep Multi-Agent Reinforcement Learning Framework on a GPU (JMLR 2022)☆487Updated 2 months ago
- ♟️ Vectorized RL game environments in JAX☆498Updated 4 months ago
- Language Modeling with the H3 State Space Model☆520Updated last year
- Code for Parsel 🐍 - generate complex programs with language models☆431Updated last year
- Code for Cicero, an AI agent that plays the game of Diplomacy with open-domain natural language negotiation.☆1,368Updated 3 months ago
- Really Fast End-to-End Jax RL Implementations☆908Updated 10 months ago
- [NeurIPS 22] [AAAI 24] Recurrent Transformer-based long-context architecture.☆765Updated 8 months ago
- AlphaZero in JAX☆78Updated last year
- Video PreTraining (VPT): Learning to Act by Watching Unlabeled Online Videos☆1,474Updated last year
- LeanRL is a fork of CleanRL, where selected PyTorch scripts optimized for performance using compile and cudagraphs.☆603Updated 8 months ago
- Train to 94% on CIFAR-10 in <6.3 seconds on a single A100. Or ~95.79% in ~110 seconds (or less!)☆1,271Updated 7 months ago
- a small code base for training large models☆305Updated 2 months ago
- Large language models (LLMs) made easy, EasyLM is a one stop solution for pre-training, finetuning, evaluating and serving LLMs in JAX/Fl…☆2,482Updated 11 months ago
- fast + parallel AlphaZero in JAX☆97Updated 6 months ago
- Reinforcement learning environments for compiler and program optimization tasks☆957Updated 9 months ago