English
Related papers

Related papers: Scaling laws for single-agent reinforcement learni…

200 papers

Many model-based reinforcement learning (RL) methods follow a similar template: fit a model to previously observed data, and then use data from that model for RL or planning. However, models that achieve better training performance (e.g.,…

Machine Learning · Computer Science 2023-02-21 Benjamin Eysenbach , Alexander Khazatsky , Sergey Levine , Ruslan Salakhutdinov

Neural scaling laws have driven the field's ever-expanding exponential growth in parameters, data and compute. While scaling behaviors for pretraining losses and discriminative benchmarks are well established, generative benchmarks such as…

Machine Learning · Computer Science 2026-02-03 Rylan Schaeffer , Noam Levi , Brando Miranda , Sanmi Koyejo

One of the main challenges in real-world reinforcement learning is to learn successfully from limited training samples. We show that in certain settings, the available data can be dramatically increased through a form of multi-task…

Machine Learning · Computer Science 2021-02-19 Desmond Cai , Shiau Hong Lim , Laura Wynter

We consider the problem of reinforcement learning (RL) with unbounded state space motivated by the classical problem of scheduling in a queueing network. Traditional policies as well as error metric that are designed for finite, bounded or…

Machine Learning · Computer Science 2020-06-09 Devavrat Shah , Qiaomin Xie , Zhi Xu

Finding parameters that minimise a loss function is at the core of many machine learning methods. The Stochastic Gradient Descent algorithm is widely used and delivers state of the art results for many problems. Nonetheless, Stochastic…

Machine Learning · Computer Science 2018-09-26 Yao Zhang , Andrew M. Saxe , Madhu S. Advani , Alpha A. Lee

In Multi-Goal Reinforcement Learning, an agent learns to achieve multiple goals with a goal-conditioned policy. During learning, the agent first collects the trajectories into a replay buffer, and later these trajectories are selected…

Machine Learning · Computer Science 2020-05-26 Rui Zhao , Xudong Sun , Volker Tresp

The quality of Large Language Model (LLM) pretraining depends on multiple factors, including the compute budget and the choice of optimization algorithm. Empirical scaling laws are widely used to predict loss as model size and training data…

Machine Learning · Computer Science 2026-02-25 Alexandra Volkova , Mher Safaryan , Christoph H. Lampert , Dan Alistarh

Robustness and Effectiveness are critical aspects of developing dense retrieval models for real-world applications. It is known that there is a trade-off between the two. Recent work has addressed scaling laws of effectiveness in dense…

Information Retrieval · Computer Science 2025-06-02 Yu-An Liu , Ruqing Zhang , Jiafeng Guo , Maarten de Rijke , Yixing Fan , Xueqi Cheng

We consider the reinforcement learning (RL) problem with general utilities which consists in maximizing a function of the state-action occupancy measure. Beyond the standard cumulative reward RL setting, this problem includes as particular…

Machine Learning · Computer Science 2023-06-06 Anas Barakat , Ilyas Fatkhullin , Niao He

Scaling laws describe how model performance grows with data, parameters and compute. While large datasets can usually be collected at relatively low cost in domains such as language or vision, scientific machine learning is often limited by…

Machine Learning · Computer Science 2025-11-04 Paul Setinek , Gianluca Galletti , Johannes Brandstetter

Large genomic and imaging datasets can be used to train models that learn meaningful representations of cellular systems. Across domains, model performance improves predictably with dataset size and compute budget, providing a basis for…

Quantitative Methods · Quantitative Biology 2026-02-23 Gokul Gowri , Igor Sadalski , Dan Raviv , Peng Yin , Jonathan Rosenfeld , Allon M. Klein

Tool-using agents based on Large Language Models (LLMs) excel in tasks such as mathematical reasoning and multi-hop question answering. However, in long trajectories, agents often trigger excessive and low-quality tool calls, increasing…

Artificial Intelligence · Computer Science 2026-03-25 Zeping Li , Hongru Wang , Yiwen Zhao , Guanhua Chen , Yixia Li , Keyang Chen , Yixin Cao , Guangnan Ye , Hongfeng Chai , Zhenfei Yin

The aim of multi-task reinforcement learning is two-fold: (1) efficiently learn by training against multiple tasks and (2) quickly adapt, using limited samples, to a variety of new tasks. In this work, the tasks correspond to reward…

Machine Learning · Computer Science 2019-11-05 Nicholas C. Landolfi , Garrett Thomas , Tengyu Ma

Reinforcement learning (RL) has enabled machine learning models to achieve significant advances in many fields. Most recently, RL has empowered frontier language models to solve challenging math, science, and coding problems. However,…

Machine Learning · Computer Science 2025-06-30 Mihir Prabhudesai , Lili Chen , Alex Ippoliti , Katerina Fragkiadaki , Hao Liu , Deepak Pathak

This paper studies the continuous-time reinforcement learning (RL) for optimal switching problems across multiple regimes. We consider a type of exploratory formulation under entropy regularization where the agent randomizes both the timing…

Optimization and Control · Mathematics 2025-12-23 Yijie Huang , Mengge Li , Xiang Yu , Zhou Zhou

Learning from Demonstration is increasingly used for transferring operator manipulation skills to robots. In practice, it is important to cater for limited data and imperfect human demonstrations, as well as underlying safety constraints.…

Robotics · Computer Science 2020-04-03 Ya-Yen Tsai , Bo Xiao , Edward Johns , Guang-Zhong Yang

Recent progress in large language models (LLMs) highlights the power of scaling test-time compute to achieve strong performance on complex tasks, such as mathematical reasoning and code generation. This raises a critical question: how…

Machine Learning · Computer Science 2025-11-26 Feng Chen , Allan Raventos , Nan Cheng , Surya Ganguli , Shaul Druckmann

Recently, Large Language Models (LLMs) have achieved remarkable success. A key factor behind this success is the scaling law observed by OpenAI. Specifically, for models with Transformer architecture, the test loss exhibits a power-law…

Machine Learning · Computer Science 2025-03-04 Yifang Chen , Xuyang Guo , Xiaoyu Li , Yingyu Liang , Zhenmei Shi , Zhao Song

We consider the challenge of finding a deterministic policy for a Markov decision process that uniformly (in all states) maximizes one reward subject to a probabilistic constraint over a different reward. Existing solutions do not fully…

Machine Learning · Computer Science 2022-01-21 Jaeyoung Lee , Sean Sedwards , Krzysztof Czarnecki

Learning arguably involves the discovery and memorization of abstract rules. The aim of this paper is to study associative memory mechanisms. Our model is based on high-dimensional matrices consisting of outer products of embeddings, which…

Machine Learning · Statistics 2024-02-22 Vivien Cabannes , Elvis Dohmatob , Alberto Bietti