English
Related papers

Related papers: Exploring TD error as a heuristic for $\sigma$ sel…

200 papers

Modern deep reinforcement learning methods have departed from the incremental learning required for eligibility traces, rendering the implementation of the $\lambda$-return difficult in this context. In particular, off-policy methods that…

Machine Learning · Computer Science 2020-01-15 Brett Daley , Christopher Amato

Off-policy reinforcement learning with eligibility traces is challenging because of the discrepancy between target policy and behavior policy. One common approach is to measure the difference between two policies in a probabilistic way,…

Machine Learning · Computer Science 2019-05-20 Longxiang Shi , Shijian Li , Longbing Cao , Long Yang , Gang Pan

In offline reinforcement learning (RL), single-step temporal-difference (TD) learning can suffer from bootstrapping error accumulation over long horizons. Action-chunked TD methods mitigate this by backing up over multiple steps, but can…

Machine Learning · Computer Science 2026-03-17 Gwanwoo Song , Kwanyoung Park , Youngwoon Lee

We present a distributional approach to theoretical analyses of reinforcement learning algorithms for constant step-sizes. We demonstrate its effectiveness by presenting simple and unified proofs of convergence for a variety of…

Machine Learning · Computer Science 2020-03-30 Philip Amortila , Doina Precup , Prakash Panangaden , Marc G. Bellemare

To estimate the value functions of policies from exploratory data, most model-free off-policy algorithms rely on importance sampling, where the use of importance sampling ratios often leads to estimates with severe variance. It is thus…

Machine Learning · Computer Science 2017-02-13 Ashique Rupam Mahmood , Huizhen Yu , Richard S. Sutton

Temporal difference (TD) learning is one of the main foundations of modern reinforcement learning. This paper studies the use of TD(0), a canonical TD algorithm, to estimate the value function of a given policy from a batch of data. In this…

Machine Learning · Computer Science 2020-08-18 Brahma Pavse , Ishan Durugkar , Josiah Hanna , Peter Stone

We consider optimal control of an unknown multi-agent linear quadratic (LQ) system where the dynamics and the cost are coupled across the agents through the mean-field (i.e., empirical mean) of the states and controls. Directly using…

Systems and Control · Electrical Eng. & Systems 2020-11-11 Mukul Gagrani , Sagar Sudhakara , Aditya Mahajan , Ashutosh Nayyar , Yi Ouyang

State-of-the-art deep Q-learning methods update Q-values using state transition tuples sampled from the experience replay buffer. This strategy often uniformly and randomly samples or prioritizes data sampling based on measures such as the…

Machine Learning · Computer Science 2023-06-28 Zhang-Wei Hong , Tao Chen , Yen-Chen Lin , Joni Pajarinen , Pulkit Agrawal

Q-learning is a reliable but inefficient off-policy temporal-difference method, backing up reward only one step at a time. Replacing traces, using a recency heuristic, are more efficient but less reliable. In this work, we introduce…

Machine Learning · Computer Science 2015-03-19 Mitchell Keith Bloch

We study the problem of online multi-task learning where the tasks are performed within similar but not necessarily identical multi-armed bandit environments. In particular, we study how a learner can improve its overall performance across…

Machine Learning · Computer Science 2022-06-20 Zhi Wang , Chicheng Zhang , Kamalika Chaudhuri

We propose and analyze an alternate approach to off-policy multi-step temporal difference learning, in which off-policy returns are corrected with the current Q-function in terms of rewards, rather than with the target policy in terms of…

Artificial Intelligence · Computer Science 2016-08-12 Anna Harutyunyan , Marc G. Bellemare , Tom Stepleton , Remi Munos

Recent experimental breakthroughs have signalled the imminent arrival of the early fault-tolerant era. However, for a considerable period in the foreseeable future, relying solely on quantum error correction for full error suppression will…

Quantum Physics · Physics 2025-02-18 Kecheng Liu , Zhenyu Cai

Gradient temporal difference (Gradient TD) algorithms are a popular class of stochastic approximation (SA) algorithms used for policy evaluation in reinforcement learning. Here, we consider Gradient TD algorithms with an additional heavy…

Machine Learning · Computer Science 2021-11-23 Rohan Deb , Shalabh Bhatnagar

Temporal difference learning (TD) is a foundational concept in reinforcement learning (RL), aimed at efficiently assessing a policy's value function. TD($\lambda$), a potent variant, incorporates a memory trace to distribute the prediction…

Machine Learning · Computer Science 2024-02-13 Jianfei Ma

A key claim in recent work on Selective State Space Models is that selectivity, the ability to focus on relevant information while filtering irrelevant inputs, requires breaking the Linear Time-Invariant (LTI) property through time-varying…

Systems and Control · Electrical Eng. & Systems 2026-03-13 Umberto Casti , Giacomo Baggio , Sandro Zampieri , Fabio Pasqualetti

Thompson sampling (TS) is a Bayesian randomized exploration strategy that samples options (e.g., system parameters or control laws) from the current posterior and then applies the selected option that is optimal for a task, thereby…

Machine Learning · Computer Science 2026-02-06 Kaikai Zheng , Dawei Shi , Yang Shi , Long Wang

Temporal difference learning (TD) is a simple iterative algorithm used to estimate the value function corresponding to a given policy in a Markov decision process. Although TD is one of the most widely used algorithms in reinforcement…

Machine Learning · Computer Science 2018-11-07 Jalaj Bhandari , Daniel Russo , Raghav Singal

Temporal-Difference (TD) learning is a standard and very successful reinforcement learning approach, at the core of both algorithms that learn the value of a given policy, as well as algorithms which learn how to improve policies.…

Machine Learning · Computer Science 2020-06-17 Mingde Zhao

Q-learning is a stochastic approximation version of the classic value iteration. The literature has established that Q-learning suffers from both maximization bias and slower convergence. Recently, multi-step algorithms have shown practical…

Machine Learning · Computer Science 2024-07-03 Antony Vijesh , Shreyas S R

Thompson sampling has emerged as an effective heuristic for a broad range of online decision problems. In its basic form, the algorithm requires computing and sampling from a posterior distribution over models, which is tractable only for…

Machine Learning · Statistics 2023-04-26 Xiuyuan Lu , Benjamin Van Roy