method · first seen 7 Oct 2026
policy gradient
Also: REINFORCE, log-derivative trick, score function estimator
Optimizing a policy by ascending the expected gradient of return with respect to policy parameters.
Mentions per week
PapersCodeDiscussion
Earliest sources
- Marrying Pricing and Advertising with LLMsPapers · 7 Oct 2026 · Alessandro Barro, Francesco Bacchiocchi, Francesco Emanuele Stradi, Alberto Marc…
- Randomized Transport Maps for Model-Free Policy-Gradient Mean-Field ControlPapers · 8 Oct 2026 · Adonis Jamal, Samy Mekkaoui, Yadh Hafsi, Huyên Pham
- Ascent Conditions for Length-Normalized Single-Rollout Policy UpdatesPapers · 10 Oct 2026 · Levin David Schwab
- Learning based Scalable Multi-Objective Scheduling of Workflows across UD-IaaS-FaaS SystemsPapers · 11 Oct 2026 · G Vasantha Reddy, Ram Bansal, Krashna, Suvarthi Sarkar, Aryabartta Sahu
- CASI: Credit Assignment via Set Intervention for Agentic RetrievalPapers · 14 Oct 2026 · Xinyi Cheng, Tianfu Zhang, Jiwen Li, Xuesen Zhang, Shihao Yu, Pengfei Zhu, Renhu…
- Aligning Language Models Towards Counterfactual InvariancePapers · 16 Oct 2026 · Basar Demir, Emily Shen, Ksheeraj Sai Vepuri, Sourabh Kulkarni, Harihar Subraman…
Latest sources
- See Every Block Once: Variance-Reduced Post-Training for Masked Diffusion Language ModelsPapers · 13 Nov 2026 · Yunzhen He, Hiroaki Yamagiwa, Hidetoshi Shimodaira
- Learning a calibrated decision head from logged bandit feedbackPapers · 11 Nov 2026 · Ye Yuan
- A New Framework for Quantum Reinforcement LearningPapers · 10 Nov 2026 · Alireza Tavakoli, Mohsen Heidari
- A Theory of Policy Optimization in Post-Training: Coverage Collapse and Reference ResetsPapers · 10 Nov 2026 · Audrey Huang, Nan Jiang, Sham M. Kakade, Sadhika Malladi, Akshay Krishnamurthy,…
- RLiD: Reinforcement Learning in the Decision Plane for Language Agents and LLMsPapers · 2 Nov 2026 · Ziyi Chen, Yan Zhang, Jianhui Wei, Jianing Yin, Daoan Zhang
- Log-Derivative Trick for Parametric Markov ChainsPapers · 27 Oct 2026 · Arthur Gall, Ichiro Hasuo, Thomas Seiller
- ProtAgent: Post-Training Compact Protein Tool Agents with Interaction-Level Credit AssignmentPapers · 24 Oct 2026 · Yuxiang Wang, Baojian Zhou, Qifang Zhao, Keyue Jiang, Yanghua Xiao, Xiaoxiao Xu
- Effectiveness of Curriculum Learning Depends on Reward Sparsity and Competing OptimaPapers · 22 Oct 2026 · John J. Vastola, Ann Huang, Satpreet H. Singh, Samuel J. Gershman, Kanaka Rajan
- Continuous-Time Policy Gradient from Discrete Data: Convergence Analysis and Model-Free AlgorithmsPapers · 20 Oct 2026 · Martin Hernandez, Xinyan Qing, Mo Zhou, Yuhua Zhu
- On Reparameterizing the Score FunctionPapers · 16 Oct 2026 · Mohammad Hossein Amani, Leonardo Bocchieri, Maxime Peyrard, Clément Hongler, Ro…
- Aligning Language Models Towards Counterfactual InvariancePapers · 16 Oct 2026 · Basar Demir, Emily Shen, Ksheeraj Sai Vepuri, Sourabh Kulkarni, Harihar Subraman…
- CASI: Credit Assignment via Set Intervention for Agentic RetrievalPapers · 14 Oct 2026 · Xinyi Cheng, Tianfu Zhang, Jiwen Li, Xuesen Zhang, Shihao Yu, Pengfei Zhu, Renhu…