English
Related papers

Related papers: Spend Wisely: Maximizing Post-Training Gains in It…

200 papers

In real-world decision making tasks, it is critical for data-driven reinforcement learning methods to be both stable and sample efficient. On-policy methods typically generate reliable policy improvement throughout training, while…

Machine Learning · Computer Science 2021-11-02 James Queeney , Ioannis Ch. Paschalidis , Christos G. Cassandras

Deep learning's success has been attributed to the training of large, overparameterized models on massive amounts of data. As this trend continues, model training has become prohibitively costly, requiring access to powerful computing…

Machine Learning · Computer Science 2021-11-25 Ravi S Raju , Kyle Daruwalla , Mikko Lipasti

Synthetic data has gained attention for training large language models, but poor-quality data can harm performance (see, e.g., Shumailov et al. (2023); Seddik et al. (2024)). A potential solution is data pruning, which retains only…

Machine Learning · Computer Science 2024-10-14 Aymane El Firdoussi , Mohamed El Amine Seddik , Soufiane Hayou , Reda Alami , Ahmed Alzubaidi , Hakim Hacid

How can we train models whose post-trained capabilities survive subsequent fine-tuning? Rather than focusing on downstream interventions to mitigate forgetting of upstream capabilities, we study how upstream training choices - that is, the…

Machine Learning · Computer Science 2026-05-14 Lawrence Feng , Gaurav R. Ghosal , Jacob Mitchell Springer , Ziqian Zhong , Aditi Raghunathan

Modern generative models exhibit unprecedented capabilities to generate extremely realistic data. However, given the inherent compositionality of the real world, reliable use of these models in practical applications requires that they…

Machine Learning · Computer Science 2025-07-29 Maya Okawa , Ekdeep Singh Lubana , Robert P. Dick , Hidenori Tanaka

Learning in a lifelong setting, where the dynamics continually evolve, is a hard challenge for current reinforcement learning algorithms. Yet this would be a much needed feature for practical applications. In this paper, we propose an…

Machine Learning · Computer Science 2021-12-14 Pierre Liotet , Francesco Vidaich , Alberto Maria Metelli , Marcello Restelli

Policy evaluation estimates the performance of a policy by (1) collecting data from the environment and (2) processing raw data into a meaningful estimate. Due to the sequential nature of reinforcement learning, any improper data-collecting…

Machine Learning · Computer Science 2025-03-21 Shuze Daniel Liu , Claire Chen , Shangtong Zhang

As large language models (LLMs) are applied to more use cases, creating high quality, task-specific datasets for fine-tuning becomes a bottleneck for model improvement. Using high quality human data has been the most common approach to…

Computation and Language · Computer Science 2024-10-31 Yung-Chieh Chan , George Pu , Apaar Shanker , Parth Suresh , Penn Jenks , John Heyer , Sam Denton

In reinforcement learning, it is typical to use the empirically observed transitions and rewards to estimate the value of a policy via either model-based or Q-fitting approaches. Although straightforward, these techniques in general yield…

Machine Learning · Computer Science 2020-07-28 Ilya Kostrikov , Ofir Nachum

Humans have developed considerable machinery used at scale to create policies and to distribute incentives, yet we are forever seeking ways in which to improve upon these, our institutions. Especially when funding is limited, it is…

Multiagent Systems · Computer Science 2023-01-18 Theodor Cimpeanu , Francisco C Santos , The Anh Han

A common and effective means for improving language model capabilities involves finetuning a ``student'' language model's parameters on generations from a more proficient ``teacher'' model. Termed ``synthetic data'', these generations are…

Adapting language models to new tasks through continued pretraining faces a fundamental trade-off: models must learn new capabilities while avoiding catastrophic forgetting of existing knowledge. While prior work has studied synthetic data…

Machine Learning · Computer Science 2025-10-15 Urs Spiegelhalter , Jörg K. H. Franke , Frank Hutter

Composing previously mastered skills to solve novel tasks promises dramatic improvements in the data efficiency of reinforcement learning. Here, we analyze two recent works composing behaviors represented in the form of action-value…

Machine Learning · Computer Science 2019-07-08 Jonathan J Hunt , Andre Barreto , Timothy P Lillicrap , Nicolas Heess

Simulation methods have always been instrumental in finance, and data-driven methods with minimal model specification, commonly referred to as generative models, have attracted increasing attention, especially after the success of deep…

Portfolio Management · Quantitative Finance 2025-04-24 Adil Rengim Cetingoz , Charles-Albert Lehalle

Inspired by the principle of deliberate practice in human learning, we propose Deliberate Practice for Synthetic Data Generation (DP), a novel framework that improves sample efficiency through dynamic synthetic data generation. Prior work…

With promising empirical performance across a wide range of applications, synthetic data augmentation appears a viable solution to data scarcity and the demands of increasingly data-intensive models. Its effectiveness lies in expanding the…

Machine Learning · Computer Science 2026-02-02 Zixuan Wu , So Won Jeong , Yating Liu , Yeo Jin Jung , Claire Donnat

Linear dynamical systems that obey stochastic differential equations are canonical models. While optimal control of known systems has a rich literature, the problem is technically hard under model uncertainty and there are hardly any…

Systems and Control · Electrical Eng. & Systems 2023-06-09 Mohamad Kazem Shirani Faradonbeh , Mohamad Sadegh Shirani Faradonbeh

We consider the problem of reinforcement learning when provided with (1) a baseline control policy and (2) a set of constraints that the learner must satisfy. The baseline policy can arise from demonstration data or a teacher agent and may…

Machine Learning · Computer Science 2021-07-13 Tsung-Yen Yang , Justinian Rosca , Karthik Narasimhan , Peter J. Ramadge

Reinforcement learning for large language models faces a fundamental trade-off between sample efficiency and asymptotic performance: strictly on-policy methods discard trajectories after a single update, while off-policy reuse introduces…

Machine Learning · Computer Science 2026-05-26 Changyu Chen , Xiting Wang , Rui Yan

Diffusion-based large language models offer a non-autoregressive alternative for text generation, but enabling them to perform complex reasoning remains challenging. Reinforcement learning has recently emerged as an effective post-training…

Artificial Intelligence · Computer Science 2026-04-14 Shaoan Xie , Lingjing Kong , Xiangchen Song , Xinshuai Dong , Guangyi Chen , Eric P. Xing , Kun Zhang