awjuliani / web-rl-playgroundLinks
An interactive web-based demonstration of fundamental tabular Reinforcement Learning (RL) algorithms in a simple grid world environment.
☆67Updated 3 weeks ago
Alternatives and similar repositories for web-rl-playground
Users that are interested in web-rl-playground are comparing it to the libraries listed below
Sorting:
- Fetch arxiv data to LLM-friendly text☆121Updated 4 months ago
- ☆54Updated 7 months ago
- A Deep Research agent from scratch☆189Updated last month
- Train a Language Model with GRPO to create a schedule from a list of events and priorities☆206Updated last month
- Repo housing the open sourced code for the ai2 scholar qa app and also the corresponding library☆184Updated 2 weeks ago
- ☆63Updated last month
- A transformer-based multimodal model for music.☆28Updated 10 months ago
- Chrome / Edge extension to turn arXiv papers into Markdown codes in one click.☆78Updated 3 months ago
- Countdown Game Distill&RL☆47Updated 2 months ago
- ☆48Updated 4 months ago
- Code and data for the paper "Why think step by step? Reasoning emerges from the locality of experience"☆60Updated 2 months ago
- Using APPL to reimplement popular algorithms for Large Language Models (LLMs) and prompts☆45Updated 5 months ago
- A fully functional and simple Machine Learning library made entirely from scratch with Python.☆294Updated 3 weeks ago
- ☆165Updated last year
- Very minimal (and stateless) agent framework☆44Updated 5 months ago
- Learning records for building a large language model from scratch☆55Updated 5 months ago
- An AI agent to control drones☆112Updated this week
- ☆76Updated 2 months ago
- Train your own SOTA deductive reasoning model☆94Updated 3 months ago
- Testing paligemma2 finetuning on reasoning dataset☆18Updated 5 months ago
- Commit0: Library Generation from Scratch☆155Updated last month
- SkillWeaver is a framework to enable web agent self-improvement through environment exploration and skill synthesis.☆84Updated 2 months ago
- LLM-as-SERP☆67Updated 3 months ago
- Awesome Code Action - DeepWebSearch AgentKit App. Build with 🤗 Hugging Face smolagents framework☆72Updated last week
- A framework for pitting LLMs against each other in an evolving library of games ⚔☆31Updated 2 months ago
- Stream live plots to a matplotlib figure☆78Updated 2 months ago
- CodeScientist: An automated scientific discovery system for code-based experiments☆273Updated this week
- ☆11Updated 11 months ago
- This is a survey of research on AI scientists, AI researchers, AI engineers, and a series of AI-driven research studies☆71Updated last month
- ☆156Updated 3 months ago