shehper / AC-Solver
A long-horizon, sparse-reward math environment for reinforcement learning. Official code repo for "What makes Math problems hard for reinforcement learning: A case study".
☆28Updated 3 months ago
Alternatives and similar repositories for AC-Solver:
Users that are interested in AC-Solver are comparing it to the libraries listed below
- Code that searches for ribbon bands☆15Updated 2 months ago
- symbolic regression☆39Updated 2 years ago
- Harmonic Datasets☆38Updated 9 months ago
- Neural theorem proving tutorial, version II☆36Updated 11 months ago
- ☆28Updated 3 weeks ago
- Benchmark for undergraduate-level formal mathematics☆105Updated 6 months ago
- Formalizing stochastic doubly-efficient debate☆102Updated 6 months ago
- Proof artifact co-training for Lean☆44Updated 2 years ago
- LLMs + Lean, on your laptop or in the cloud☆142Updated 2 weeks ago
- ☆12Updated 2 years ago
- The Lean Theorem Proving Environment☆13Updated last year
- ProofNet dataset ported into Lean 4☆20Updated 3 weeks ago
- Transformers for Mathematics Tutorial | Simons/SLMath Workshop on AI for Mathematics 2025☆32Updated 2 weeks ago
- A package for defining deep learning models using categorical algebraic expressions.☆60Updated 8 months ago
- ☆63Updated 3 years ago
- [ICLR 2024 Spotlight] This is the official code for the paper "SNIP: Bridging Mathematical Symbolic and Numeric Realms with Unified Pre-t…☆52Updated 6 months ago
- Adaptive Subgoal Search☆19Updated 2 years ago
- Python wrapper for lean-gym☆11Updated 2 years ago
- ☆71Updated 7 months ago
- An evaluation benchmark for undergraduate competition math in Lean4, Isabelle, Coq, and natural language.☆108Updated this week
- Learning Formal Mathematics from Intrinsic Motivation☆26Updated last month
- Code for the paper LeanReasoner: Boosting Complex Logical Reasoning with Lean: https://arxiv.org/pdf/2403.13312.pdf☆22Updated 10 months ago
- Python talking to the Lean theorem prover☆43Updated 3 years ago
- LeanEuclid is a benchmark for autoformalization in the domain of Euclidean geometry, targeting the proof assistant Lean.☆98Updated 10 months ago
- llmstep: [L]LM proofstep suggestions in Lean 4.☆130Updated last year
- Latent Program Network (from the "Searching Latent Program Spaces" paper)☆81Updated last month
- ☆24Updated last month
- COPRA: An in-COntext PRoof Agent which uses LLMs like GPTs to prove theorems in formal languages.☆58Updated last week
- blueprint for prime number theorem and more☆158Updated last week
- Official code for paper: INT: An Inequality Benchmark for Evaluating Generalization in Theorem Proving☆39Updated 2 years ago