Reward-rate Policy Gradient for Efficient Machine Learning Engineering Agents
cs.LG, cs.AI
Submitted: 2026-09-28
Updated: 2026-09-28
Code: https://github.com/MuhangTian/Reward-rate-Policy-Gradient
Project page: https://muhang-tian.com/reward-rate
Sources
- Bandits with Knapsacks
- Exploring LLM Agents for Cleaning Tabular Machine Learning Datasets
- Teaching Large Language Models to Self-Debug
- Deep reinforcement learning from human preferences
- DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning
- Kolb-Based Experiential Learning for Generalist Agents with Human-Level Kaggle Data Science Performance
- Dynamic Speculative Agent Planning
- A Practical Guide to Multi-Objective Reinforcement Learning and Planning
- AIDE: AI-Driven Exploration in the Space of Code
- Adam: A Method for Stochastic Optimization
- AutoKaggle: A Multi-Agent Framework for Autonomous Data Science Competitions
- Large Language Model Agent for Hyper-Parameter Optimization
- Self-Refine: Iterative Refinement with Self-Feedback
- The FineWeb Datasets: Decanting the Web for the Finest Text Data at Scale
- A Survey of Multi-Objective Sequential Decision-Making
- Proximal Policy Optimization Algorithms
- Reflexion: Language Agents with Verbal Reinforcement Learning
- ML-Bench: Evaluating Large Language Models and Agents for Machine Learning Tasks on Repository-Level Code
- Reinforcement Learning for Machine Learning Engineering Agents
- Learning to Discover at Test Time
Related papers
- Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
- AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
- Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
- Convergence issues in Relational Concept Analysis based on AOC-posets
- Beliefs Beyond Posteriors: The Predictive Cost of ELBO Binding
- Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks