[ICLR 2026] RPG: KL-Regularized Policy Gradient (https://arxiv.org/abs/2505.17508)
☆78Nov 5, 2026Updated last week
Alternatives and similar repositories for RPG
Users that are interested in RPG are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- Official implementation of TBA for async LLM post-training.☆32Nov 5, 2025Updated last year
- The code for paper "EPO: Entropy-regularized Policy Optimization for LLM Agents Reinforcement Learning"☆40Jul 13, 2026Updated 4 months ago
- Optimizing Anytime Reasoning via Budget Relative Policy Optimization☆54Jul 15, 2025Updated last year
- Reinforcing General Reasoning without Verifiers☆103Jun 24, 2025Updated last year
- ☆38Oct 8, 2025Updated last year
- Deploy to Railway using AI coding agents - Free Credits Offer • AdUse Claude Code, Codex, OpenCode, and more. Autonomous software development now has the infrastructure to match with Railway.
- The Entropy Mechanism of Reinforcement Learning for Large Language Model Reasoning.☆456Jul 11, 2025Updated last year
- [COLM 2026] An efficient 3D sampling method for long-CoT LLM.☆16May 25, 2025Updated last year
- Self-Hinting Language Models Enhance Reinforcement Learning☆30Mar 28, 2026Updated 7 months ago
- Code for "Variational Reasoning for Language Models"☆64Sep 29, 2025Updated last year
- A Gym for Agentic LLMs☆518Jan 21, 2026Updated 9 months ago
- [COLM 2025] Code for Paper: Learning Adaptive Parallel Reasoning with Language Models☆146Dec 17, 2025Updated 11 months ago
- Trust Region Preference Approximation: A simple and stable reinforcement learning algorithm for LLM reasoning☆15Jun 28, 2025Updated last year
- Code for "EMA Policy Gradient: Taming Reinforcement Learning for LLMs with EMA Anchor and Top-k KL" (arxiv.org/abs/2602.04417)☆11Feb 5, 2026Updated 9 months ago
- Training and evaluating with OpenReward☆33Apr 28, 2026Updated 6 months ago
- Managed Database hosting by DigitalOcean • AdPostgreSQL, MySQL, MongoDB, Kafka, Valkey, and OpenSearch available. Automatically scale up storage and focus on building your apps.
- [ICLR 2026] GRAPE: Group Representational Position Encoding (https://arxiv.org/abs/2512.07805)☆122Nov 5, 2026Updated last week
- The official implementation of Cross-Task Experience Sharing (COPS)☆29Oct 23, 2024Updated 2 years ago
- ☆20Dec 14, 2024Updated last year
- This repository is the official implementation of Learning Goal-Conditioned Representations for Language Reward Models☆11Dec 14, 2024Updated last year
- [ACL 2025] Outlier-Safe Pre-Training for Robust 4-Bit Quantization of Large Language Models☆40Nov 4, 2025Updated last year
- OpenTinker is an RL-as-a-Service infrastructure for foundation models☆677Mar 21, 2026Updated 7 months ago
- [NeurIPS 2025 Spotlight] TPA: Tensor ProducT ATTenTion Transformer (https://arxiv.org/abs/2501.06425)☆464Nov 5, 2026Updated last week
- ☆11May 18, 2025Updated last year
- [NeurIPS 2025] Implementation for the paper "The Surprising Effectiveness of Negative Reinforcement in LLM Reasoning"☆172Mar 2, 2026Updated 8 months ago
- Deploy on Railway without the complexity - Free Credits Offer • AdConnect your repo and Railway handles the rest with instant previews. Quickly provision container image services, databases, and storage volumes.
- SimPER: A Minimalist Approach to Preference Alignment without Hyperparameters (ICLR 2025)☆17Aug 22, 2025Updated last year
- ☆16Sep 4, 2025Updated last year
- Rethinking the Trust Region in LLM Reinforcement Learning☆76Mar 2, 2026Updated 8 months ago
- [ICLR 2026] Official PyTorch Implementation of RLP: Reinforcement as a Pretraining Objective☆257Jan 26, 2026Updated 9 months ago
- DCPO: Dynamic Adaptive Clipping for RL☆50Apr 1, 2026Updated 7 months ago
- An official implementation of Random Policy Valuation is Enough for LLM Reasoning with Verifiable Rewards☆36Oct 3, 2025Updated last year
- 🚀 Pytorch Distributed native training library for LLMs/VLMs with OOTB Hugging Face support☆26Sep 5, 2026Updated 2 months ago
- ☆370Jul 29, 2025Updated last year
- 🌾 OAT: A research-friendly framework for LLM online alignment, including reinforcement learning, preference learning, etc.☆678Jan 29, 2026Updated 9 months ago
- Bare Metal GPUs on DigitalOcean Gradient AI • AdPurpose-built for serious AI teams training foundational models, running large-scale inference, and pushing the boundaries of what's possible.
- ☆91Aug 16, 2025Updated last year
- GenRM-CoT: Data release for verification rationales☆70Oct 16, 2024Updated 2 years ago
- Self-Questioning Language Models☆55Mar 30, 2026Updated 7 months ago
- A containerized HTTP server that executes code in many languages☆11Jul 19, 2024Updated 2 years ago
- Agentic RL on Any Harness at Scale☆878Updated this week
- Automated management of ad campaigns in Google Display&Video 360.☆15Feb 9, 2026Updated 9 months ago
- [NeurIPS 2025] RL Tango: Reinforcing Generator and Verifier Together for Language Reasoning☆60Oct 23, 2025Updated last year
Are these results useful?