English
Related papers

Related papers: Finite-Sample Analysis of Off-Policy Natural Actor…

200 papers

Recent policy optimization approaches (Schulman et al., 2015a; 2017) have achieved substantial empirical successes by constructing new proxy optimization objectives. These proxy objectives allow stable and low variance policy learning, but…

Machine Learning · Computer Science 2020-02-24 Marcin B. Tomczak , Dongho Kim , Peter Vrancx , Kee-Eung Kim

Existing work on risk-sensitive reinforcement learning - both for symmetric and downside risk measures - has typically used direct Monte-Carlo estimation of policy gradients. While this approach yields unbiased gradient estimates, it also…

Machine Learning · Computer Science 2020-07-09 Thomas Spooner , Rahul Savani

We analyze the convergence rate of the unregularized natural policy gradient algorithm with log-linear policy parametrizations in infinite-horizon discounted Markov decision processes. In the deterministic case, when the Q-value is known…

Machine Learning · Computer Science 2023-03-15 Carlo Alfano , Patrick Rebeschini

Consider a two-player zero-sum stochastic game where the transition function can be embedded in a given feature space. We propose a two-player Q-learning algorithm for approximating the Nash equilibrium strategy via sampling. The algorithm…

Machine Learning · Computer Science 2019-06-04 Zeyu Jia , Lin F. Yang , Mengdi Wang

We propose an actor-critic framework to solve the time-continuous stochastic optimal control problem. A least square temporal difference method is applied to compute the value function for the critic. The policy gradient method is…

Optimization and Control · Mathematics 2025-01-27 Mo Zhou , Jianfeng Lu

Off-policy actor-critic algorithms have shown strong potential in deep reinforcement learning for continuous control tasks. Their success primarily comes from leveraging pessimistic state-action value function updates, which reduce function…

Machine Learning · Computer Science 2025-08-21 Bahareh Tasdighi , Nicklas Werge , Yi-Shan Wu , Melih Kandemir

Off-policy learning in dynamic decision problems is essential for providing strong evidence that a new policy is better than the one in use. But how can we prove superiority without testing the new policy? To answer this question, we…

Machine Learning · Statistics 2015-02-12 Assaf Hallak , François Schnitzler , Timothy Mann , Shie Mannor

We consider the problem of detecting anomalies among a given set of processes using their noisy binary sensor measurements. The noiseless sensor measurement corresponding to a normal process is 0, and the measurement is 1 if the process is…

Signal Processing · Electrical Eng. & Systems 2020-06-02 Geethu Joseph , M. Cenk Gursoy , Pramod K. Varshney

Value-based algorithms are a cornerstone of off-policy reinforcement learning due to their simplicity and training stability. However, their use has traditionally been restricted to discrete action spaces, as they rely on estimating…

Machine Learning · Computer Science 2025-10-23 Yigit Korkmaz , Urvi Bhuwania , Ayush Jain , Erdem Bıyık

In recent years, deep off-policy actor-critic algorithms have become a dominant approach to reinforcement learning for continuous control. One of the primary drivers of this improved performance is the use of pessimistic value updates to…

Machine Learning · Computer Science 2022-04-07 Ted Moskovitz , Jack Parker-Holder , Aldo Pacchiano , Michael Arbel , Michael I. Jordan

Current model-based reinforcement learning approaches use the model simply as a learned black-box simulator to augment the data for policy optimization or value function learning. In this paper, we show how to make more effective use of the…

Machine Learning · Computer Science 2020-05-19 Ignasi Clavera , Violet Fu , Pieter Abbeel

Policy optimization methods remain a powerful workhorse in empirical Reinforcement Learning (RL), with a focus on neural policies that can easily reason over complex and continuous state and/or action spaces. Theoretical understanding of…

Machine Learning · Computer Science 2021-03-23 Fei Feng , Wotao Yin , Alekh Agarwal , Lin F. Yang

Off-policy policy estimators that use importance sampling (IS) can suffer from high variance in long-horizon domains, and there has been particular excitement over new IS methods that leverage the structure of Markov decision processes. We…

Machine Learning · Computer Science 2020-06-09 Yao Liu , Pierre-Luc Bacon , Emma Brunskill

We consider the problem of finding stationary Nash equilibria (NE) in a finite discounted general-sum stochastic game. We first generalize a non-linear optimization problem from Filar and Vrieze [2004] to a $N$-player setting and break down…

Computer Science and Game Theory · Computer Science 2015-07-06 H. L Prasad , L. A. Prashanth , Shalabh Bhatnagar

We study the global convergence and global optimality of actor-critic, one of the most popular families of reinforcement learning algorithms. While most existing works on actor-critic employ bi-level or two-timescale updates, we focus on…

Machine Learning · Computer Science 2021-06-15 Zuyue Fu , Zhuoran Yang , Zhaoran Wang

Actor-critic algorithms are widely used in reinforcement learning, but are challenging to mathematically analyse due to the online arrival of non-i.i.d. data samples. The distribution of the data samples dynamically changes as the model is…

Machine Learning · Computer Science 2023-09-20 Ziheng Wang , Justin Sirignano

We show that on-policy policy gradient (PG) and its variance reduction variants can be derived by taking finite difference of function evaluations supplied by estimators from the importance sampling (IS) family for off-policy evaluation…

Machine Learning · Computer Science 2020-06-25 Jiawei Huang , Nan Jiang

Deep Reinforcement Learning (DRL) algorithms for continuous action spaces are known to be brittle toward hyperparameters as well as \cut{being}sample inefficient. Soft Actor Critic (SAC) proposes an off-policy deep actor critic algorithm…

Machine Learning · Computer Science 2019-06-10 Patrick Nadeem Ward , Ariella Smofsky , Avishek Joey Bose

Policy gradient methods are powerful reinforcement learning algorithms and have been demonstrated to solve many complex tasks. However, these methods are also data-inefficient, afflicted with high variance gradient estimates, and frequently…

Machine Learning · Computer Science 2019-05-15 Andreas Doerr , Michael Volpp , Marc Toussaint , Sebastian Trimpe , Christian Daniel

We consider the off-policy evaluation problem of reinforcement learning using deep convolutional neural networks. We analyze the deep fitted Q-evaluation method for estimating the expected cumulative reward of a target policy, when the data…

Machine Learning · Computer Science 2022-10-05 Xiang Ji , Minshuo Chen , Mengdi Wang , Tuo Zhao