complex-reasoning / RPGLinks
Official implementation of Regularized Policy Gradient (RPG) (https://arxiv.org/abs/2505.17508)
☆60Updated 2 months ago
Alternatives and similar repositories for RPG
Users that are interested in RPG are comparing it to the libraries listed below
Sorting:
- Reinforcing General Reasoning without Verifiers☆92Updated 6 months ago
- ☆20Updated 4 months ago
- ☆33Updated 11 months ago
- [Preprint] RLVE: Scaling Up Reinforcement Learning for Language Models with Adaptive Verifiable Environments☆162Updated last month
- [NeurIPS 2025 Spotlight] Co-Evolving LLM Coder and Unit Tester via Reinforcement Learning☆144Updated 3 months ago
- The official repository for SkyLadder: Better and Faster Pretraining via Context Window Scheduling☆40Updated 2 months ago
- An official implementation of Random Policy Valuation is Enough for LLM Reasoning with Verifiable Rewards☆31Updated 2 months ago
- Defeating the Training-Inference Mismatch via FP16☆165Updated last month
- Resa: Transparent Reasoning Models via SAEs☆46Updated 3 months ago
- The official implementation of Self-Exploring Language Models (SELM)☆63Updated last year
- Esoteric Language Models☆108Updated last month
- Verlog: A Multi-turn RL framework for LLM agents☆67Updated last month
- Official Repo for InSTA: Towards Internet-Scale Training For Agents☆55Updated 5 months ago
- SPIRAL: Self-Play on Zero-Sum Games Incentivizes Reasoning via Multi-Agent Multi-Turn Reinforcement Learning☆171Updated 3 months ago
- ☆108Updated 3 months ago
- ☆76Updated last month
- [COLM 2025] Code for Paper: Learning Adaptive Parallel Reasoning with Language Models☆136Updated last week
- Code for "Reasoning to Learn from Latent Thoughts"☆123Updated 8 months ago
- Official repo of paper LM2☆46Updated 10 months ago
- ☆125Updated 10 months ago
- ☆105Updated 2 weeks ago
- Official PyTorch implementation and models for paper "Diffusion Beats Autoregressive in Data-Constrained Settings". We find diffusion mod…☆117Updated last month
- [ACL 2025] Agentic Reward Modeling: Integrating Human Preferences with Verifiable Correctness Signals for Reliable Reward Systems☆115Updated 6 months ago
- ☆111Updated last year
- ☆44Updated 6 months ago
- ☆51Updated 10 months ago
- Natural Language Reinforcement Learning☆101Updated 4 months ago
- SSRL: Self-Search Reinforcement Learning☆195Updated 4 months ago
- ☆65Updated 9 months ago
- ☆86Updated last month