English
Related papers

Related papers: Generalized Speedy Q-learning

200 papers

We propose a novel algorithmic framework for distributional reinforcement learning, based on learning finite-dimensional mean embeddings of return distributions. We derive several new algorithms for dynamic programming and…

We study offline reinforcement learning under $Q^\star$-approximation and partial coverage, a setting that motivates practical algorithms such as Conservative $Q$-Learning (CQL; Kumar et al., 2020) but has received limited theoretical…

Machine Learning · Computer Science 2026-02-13 Haolin Liu , Braham Snyder , Chen-Yu Wei

Unlike their conventional use as estimators of probability density functions in reinforcement learning (RL), this paper introduces a novel function-approximation role for Gaussian mixture models (GMMs) as direct surrogates for Q-function…

Machine Learning · Computer Science 2025-12-23 Minh Vu , Konstantinos Slavakis

Risk-aversion and bounded rationality are two key characteristics of human decision-making. Risk-averse quantal-response equilibrium (RQE) is a solution concept that incorporates these features, providing a more realistic depiction of human…

Computer Science and Game Theory · Computer Science 2025-08-13 Yizhou Zhang , Eric Mazumdar

Model compression has emerged as a mainstream solution to reduce memory usage and computational overhead. This paper presents Group Quantization and Sparse Acceleration (GQSA), a novel compression technique tailored for LLMs. Traditional…

Machine Learning · Computer Science 2025-07-29 Chao Zeng , Songwei Liu , Shu Yang , Fangmin Chen , Lean Fu , Xing Mei

This paper studies accelerated algorithms for Q-learning. We propose an acceleration scheme by incorporating the historical iterates of the Q-function. The idea is conceptually inspired by the momentum-based acceleration methods in the…

Systems and Control · Electrical Eng. & Systems 2019-10-28 Bowen Weng , Lin Zhao , Huaqing Xiong , Wei Zhang

Q-learning is a popular Reinforcement Learning (RL) algorithm which is widely used in practice with function approximation (Mnih et al., 2015). In contrast, existing theoretical results are pessimistic about Q-learning. For example, (Baird,…

Machine Learning · Computer Science 2021-10-20 Naman Agarwal , Syomantak Chaudhuri , Prateek Jain , Dheeraj Nagaraj , Praneeth Netrapalli

Many reinforcement learning algorithms rely on value estimation, however, the most widely used algorithms -- namely temporal difference algorithms -- can diverge under both off-policy sampling and nonlinear function approximation. Many…

Machine Learning · Computer Science 2024-08-02 Andrew Patterson , Adam White , Martha White

Recent methods for imitation learning directly learn a $Q$-function using an implicit reward formulation rather than an explicit reward function. However, these methods generally require implicit reward regularization to improve stability…

Machine Learning · Computer Science 2023-03-02 Firas Al-Hafez , Davide Tateo , Oleg Arenz , Guoping Zhao , Jan Peters

Distributional reinforcement learning (distributional RL) has seen empirical success in complex Markov Decision Processes (MDPs) in the setting of nonlinear function approximation. However, there are many different ways in which one can…

Machine Learning · Statistics 2018-07-24 Thang Doan , Bogdan Mazoure , Clare Lyle

We study the Whittle index learning algorithm for restless multi-armed bandits. We consider index learning algorithm with Q-learning. We first present Q-learning algorithm with exploration policies -- epsilon-greedy, softmax,…

Machine Learning · Computer Science 2024-09-10 Vishesh Mittal , Rahul Meshram , Surya Prakash

Deep reinforcement learning (RL) has achieved many recent successes, yet experiment turn-around time remains a key bottleneck in research and in practice. We investigate how to optimize existing deep RL algorithms for modern computers,…

Machine Learning · Computer Science 2019-01-14 Adam Stooke , Pieter Abbeel

We describe a general technique that yields the first {\em Statistical Query lower bounds} for a range of fundamental high-dimensional learning problems involving Gaussian distributions. Our main results are for the problems of (1) learning…

Machine Learning · Computer Science 2017-05-18 Ilias Diakonikolas , Daniel M. Kane , Alistair Stewart

Robust Reinforcement Learning (RRL) is a promising Reinforcement Learning (RL) paradigm aimed at training robust to uncertainty or disturbances models, making them more efficient for real-world applications. Following this paradigm,…

Machine Learning · Computer Science 2024-05-06 Anton Plaksin , Vitaly Kalev

This paper introduces Meta-Q-Learning (MQL), a new off-policy algorithm for meta-Reinforcement Learning (meta-RL). MQL builds upon three simple ideas. First, we show that Q-learning is competitive with state-of-the-art meta-RL algorithms if…

Machine Learning · Computer Science 2020-04-07 Rasool Fakoor , Pratik Chaudhari , Stefano Soatto , Alexander J. Smola

We propose and analyze a kernelized version of Q-learning. Although a kernel space is typically infinite-dimensional, extensive study has shown that generalization is only affected by the effective dimension of the data. We incorporate such…

Machine Learning · Computer Science 2022-04-25 Shuang Liu , Hao Su

Reinforcement learning (RL) algorithms typically optimize the expected cumulative reward, i.e., the expected value of the sum of scalar rewards an agent receives over the course of a trajectory. The expected value averages the performance…

Machine Learning · Computer Science 2025-09-01 Xinyi Sheng , Dominik Baumann

In this paper, we formalize the almost sure convergence of $Q$-learning and linear temporal difference (TD) learning with Markovian samples using the Lean 4 theorem prover based on the Mathlib library. $Q$-learning and linear TD are among…

Machine Learning · Computer Science 2025-11-06 Shangtong Zhang

We present Graph-$Q$-SAT, a branching heuristic for a Boolean SAT solver trained with value-based reinforcement learning (RL) using Graph Neural Networks for function approximation. Solvers using Graph-$Q$-SAT are complete SAT solvers that…

Machine Learning · Computer Science 2020-11-26 Vitaly Kurin , Saad Godil , Shimon Whiteson , Bryan Catanzaro

The analysis of Temporal Difference (TD) learning in the average-reward setting faces notable theoretical difficulties because the Bellman operator is not contractive with respect to any norm. This complicates standard analyses of…

Machine Learning · Computer Science 2026-05-05 Haoxing Tian , Zaiwei Chen , Ioannis Ch. Paschalidis , Alex Olshevsky