English
Related papers

Related papers: A First Empirical Study of Emphatic Temporal Diffe…

200 papers

On-policy distillation (OPD) is increasingly used in LLM post-training because it can leverage a teacher model to provide dense supervision on student rollouts. The standard implementation, however, usually reduces distribution matching to…

Machine Learning · Computer Science 2026-04-28 Yuqian Fu , Haohuan Huang , Kaiwen Jiang , Jiacai Liu , Zhuo Jiang , Yuanheng Zhu , Dongbin Zhao

Large scale reinforcement learning has become a central tool for improving reasoning in large language models. At this scale, generation is often lagged or asynchronous, so updates are performed on data collected by older policies. This…

Machine Learning · Computer Science 2026-05-28 Otmane Sakhi , Aleksei Arzhantsev , Imad Aouali , Flavian Vasile

Value function approximation is a crucial module for policy evaluation in reinforcement learning when the state space is large or continuous. The present paper takes a generative perspective on policy evaluation via temporal-difference (TD)…

Machine Learning · Statistics 2021-12-03 Qin Lu , Georgios B. Giannakis

On-policy distillation (OPD) trains a student on its own trajectories with token-level teacher feedback and often outperforms off-policy distillation and standard reinforcement learning. However, we find that its standard advantage weighted…

Machine Learning · Computer Science 2026-05-14 Nan Jia , Haojin Yang , Xing Ma , Jiesong Lian , Shuailiang Zhang , Weipeng Zhang , Ke Zeng , Xunliang Cai , Zequn Sun

Stemming on the idea that a key objective in reinforcement learning is to invert a target distribution of effects, end-effect drives are proposed as an effective way to implement goal-directed motor learning, in the absence of an explicit…

Artificial Intelligence · Computer Science 2020-10-06 Emmanuel Daucé

Integral to recent successes in deep reinforcement learning has been a class of temporal difference methods that use infrequently updated target values for policy evaluation in a Markov Decision Process. Yet a complete theoretical…

Machine Learning · Computer Science 2023-08-15 Mattie Fellows , Matthew J. A. Smith , Shimon Whiteson

In large-scale distributed machine learning, recent works have studied the effects of compressing gradients in stochastic optimization to alleviate the communication bottleneck. These works have collectively revealed that stochastic…

Machine Learning · Computer Science 2024-06-05 Aritra Mitra , George J. Pappas , Hamed Hassani

Matrix evolution equations occur in many applications, such as dynamical Lyapunov/Sylvester systems or Riccati equations in optimization and stochastic control, machine learning or data assimilation. In many such problems, the dominant…

Numerical Analysis · Mathematics 2026-02-12 Nayef Shkeir , Tobias Grafke

Value-based deep Reinforcement Learning (RL) algorithms suffer from the estimation bias primarily caused by function approximation and temporal difference (TD) learning. This problem induces faulty state-action value estimates and therefore…

Machine Learning · Computer Science 2021-11-15 Dogan C. Cicek , Enes Duran , Baturay Saglam , Kagan Kaya , Furkan B. Mutlu , Suleyman S. Kozat

Recent research endeavours have theoretically shown the beneficial effect of cooperation in multi-agent reinforcement learning (MARL). In a setting involving $N$ agents, this beneficial effect usually comes in the form of an $N$-fold linear…

Multiagent Systems · Computer Science 2024-07-31 Nicolò Dal Fabbro , Arman Adibi , Aritra Mitra , George J. Pappas

Unlike popular modularized framework, end-to-end autonomous driving seeks to solve the perception, decision and control problems in an integrated way, which can be more adapting to new scenarios and easier to generalize at scale. However,…

Robotics · Computer Science 2020-07-08 Jianyu Chen , Shengbo Eben Li , Masayoshi Tomizuka

We present a novel $l_1$ regularized off-policy convergent TD-learning method (termed RO-TD), which is able to learn sparse representations of value functions with low computational complexity. The algorithmic framework underlying RO-TD…

Machine Learning · Computer Science 2020-06-11 Bo Liu , Sridhar Mahadevan , Ji Liu

We propose a novel adaptive reinforcement learning control approach for fault tolerant control of degrading systems that is not preceded by a fault detection and diagnosis step. Therefore, \textit{a priori} knowledge of faults that may…

Systems and Control · Electrical Eng. & Systems 2020-08-12 Ibrahim Ahmed , Marcos Quiñones-Grueiro , Gautam Biswas

Reinforcement learning algorithms typically rely on the assumption that the environment dynamics and value function can be expressed in terms of a Markovian state representation. However, when state information is only partially observable,…

One of the most basic problems in reinforcement learning (RL) is policy evaluation: estimating the long-term return, i.e., value function, corresponding to a given fixed policy. The celebrated Temporal Difference (TD) learning algorithm…

Machine Learning · Computer Science 2025-02-10 Sreejeet Maity , Aritra Mitra

Distributional reinforcement learning (DRL) has achieved empirical success in various domains. One core task in DRL is distributional policy evaluation, which involves estimating the return distribution $\eta^\pi$ for a given policy $\pi$.…

Machine Learning · Statistics 2025-01-17 Yang Peng , Liangyu Zhang , Zhihua Zhang

On-policy distillation (OPD) has shown strong potential for transferring reasoning ability from frontier or domain-specific models to smaller students. While effective on static single-turn tasks, its behavior in multi-turn agent settings…

Machine Learning · Computer Science 2026-04-30 Jiaqi Wang , Wenhao Zhang , Weijie Shi , Yaliang Li , James Cheng

In this paper, we introduce a method for adapting the step-sizes of temporal difference (TD) learning. The performance of TD methods often depends on well chosen step-sizes, yet few algorithms have been developed for setting the step-size…

Machine Learning · Computer Science 2018-04-11 Alex Kearney , Vivek Veeriah , Jaden B. Travnik , Richard S. Sutton , Patrick M. Pilarski

This paper presents a novel framework for automatic learning of complex strategies in human decision making. The task that we are interested in is to better facilitate long term planning for complex, multi-step events. We observe temporal…

Computer Vision and Pattern Recognition · Computer Science 2018-05-15 Tharindu Fernando , Simon Denman , Sridha Sridharan , Clinton Fookes

In a sequential decision-making problem, off-policy evaluation estimates the expected cumulative reward of a target policy using logged trajectory data generated from a different behavior policy, without execution of the target policy.…

Machine Learning · Computer Science 2022-11-04 Jie Wang , Rui Gao , Hongyuan Zha