balrog-ai / BALROG
Benchmarking Agentic LLM and VLM Reasoning On Games
☆126Updated last week
Alternatives and similar repositories for BALROG:
Users that are interested in BALROG are comparing it to the libraries listed below
- ☆85Updated 9 months ago
- Code for the paper "VinePPO: Unlocking RL Potential For LLM Reasoning Through Refined Credit Assignment"☆148Updated 4 months ago
- Repository for the paper Stream of Search: Learning to Search in Language☆142Updated 2 months ago
- ☆111Updated last month
- SmartPlay is a benchmark for Large Language Models (LLMs). Uses a variety of games to test various important LLM capabilities as agents. …☆135Updated 11 months ago
- ScienceWorld is a text-based virtual environment centered around accomplishing tasks from the standardized elementary science curriculum.☆248Updated 5 months ago
- ☆96Updated 9 months ago
- Bootstrapping ARC☆106Updated 4 months ago
- ☆104Updated 2 months ago
- Lamorel is a Python library designed for RL practitioners eager to use Large Language Models (LLMs).☆225Updated 5 months ago
- Intrinsic Motivation from Artificial Intelligence Feedback☆128Updated last year
- ☆141Updated 11 months ago
- Official implementation of the DECKARD Agent from the paper "Do Embodied Agents Dream of Pixelated Sheep?"☆91Updated last year
- Research Code for "ArCHer: Training Language Model Agents via Hierarchical Multi-Turn RL"☆156Updated last year
- Code release for "Debating with More Persuasive LLMs Leads to More Truthful Answers"☆103Updated last year
- ☆173Updated last year
- Implementation of the Quiet-STAR paper (https://arxiv.org/pdf/2403.09629.pdf)☆53Updated 7 months ago
- Flow of Reasoning: Training LLMs for Divergent Problem Solving with Minimal Examples☆84Updated last week
- Intelligent Go-Explore: Standing on the Shoulders of Giant Foundation Models☆54Updated last month
- OpenCoconut implements a latent reasoning paradigm where we generate thoughts before decoding.☆169Updated 2 months ago
- A benchmark for evaluating learning agents based on just language feedback☆70Updated last week
- ☆163Updated 3 weeks ago
- Efficient World Models with Context-Aware Tokenization. ICML 2024☆94Updated 6 months ago
- Archon provides a modular framework for combining different inference-time techniques and LMs with just a JSON config file.☆166Updated 3 weeks ago
- This is code for most of the experiments in the paper Understanding the Effects of RLHF on LLM Generalisation and Diversity☆41Updated last year
- A Large-Scale, High-Quality Math Dataset for Reinforcement Learning in Language Models☆46Updated last month
- nanoGRPO is a lightweight implementation of Group Relative Policy Optimization (GRPO)☆95Updated last week
- a simple and scalable agent for training adaptive policies with sequence-based RL☆117Updated last month
- Code for Paper: Autonomous Evaluation and Refinement of Digital Agents [COLM 2024]☆131Updated 4 months ago
- Official code from the paper "Offline RL for Natural Language Generation with Implicit Language Q Learning"☆205Updated last year