codingfisch / flashrl
Fast reinforcement learning 💨
☆24Updated last month
Alternatives and similar repositories for flashrl:
Users that are interested in flashrl are comparing it to the libraries listed below
- Intelligent Go-Explore: Standing on the Shoulders of Giant Foundation Models☆54Updated last month
- ☆19Updated 6 months ago
- Generative cellular automaton-like learning environments for RL.☆19Updated 2 months ago
- ☆20Updated 9 months ago
- ☆76Updated 3 weeks ago
- Code for Discovered Policy Optimisation (NeurIPS 2022)☆9Updated last year
- Learn online intrinsic rewards from LLM feedback☆35Updated 4 months ago
- NanoGPT (124M) quality in 2.67B tokens☆28Updated last week
- [ICML 2024] Official code release accompanying the paper "diff History for Neural Language Agents" (Piterbarg, Pinto, Fergus)☆20Updated 7 months ago
- Clean RL implementation using MLX☆30Updated last year
- Fast dataset format and loader☆22Updated 3 months ago
- Efficient baselines for autocurricula in JAX.☆186Updated 7 months ago
- This code accompanies the paper "Leveraging Skills from Unlabeled Prior Data for Efficient Online Exploration."☆27Updated 5 months ago
- GPT implementation in Flax☆18Updated 3 years ago
- Transformer with Mu-Parameterization, implemented in Jax/Flax. Supports FSDP on TPU pods.☆30Updated 4 months ago
- Official Implementation of NeurIPS'23 Paper "Cross-Episodic Curriculum for Transformer Agents"☆31Updated last year
- Reinforcement Learning inside a 3D soccer simulation☆25Updated 7 months ago
- Implementation of Soft Actor Critic and some of its improvements in Pytorch☆55Updated 2 months ago
- Simple single-file baselines for Q-Learning in pure-GPU setting☆153Updated 3 weeks ago
- Efficient World Models with Context-Aware Tokenization. ICML 2024☆97Updated 6 months ago
- Corax: Core RL in JAX☆37Updated last year
- Accelerated replay buffers in JAX☆41Updated 2 years ago
- Repo to reproduce the First-Explore paper results☆37Updated 3 months ago
- NeurIPS 2024 tutorial on LLM Inference☆41Updated 4 months ago
- ☆34Updated last month
- ☆74Updated 5 months ago
- OMNI-EPIC: Open-endedness via Models of human Notions of Interestingness with Environments Programmed in Code (ICLR 2025).☆46Updated 3 months ago
- ☆31Updated last year
- Highly scalable 2D JAX physics engine.☆54Updated last month
- Contains JAX implementation of algorithms for inverse reinforcement learning☆72Updated 7 months ago