English
Related papers

Related papers: Safe Policy Improvement with an Estimated Baseline…

200 papers

Recently, it has been shown that the Stochastic Gradient Bandit (SGB) algorithm converges to a globally optimal policy with a constant learning rate. However, these guarantees rely on unrealistic assumptions about the learning process,…

Machine Learning · Computer Science 2026-05-11 Leonardo Cesani , Matteo Papini , Marcello Restelli

A key aspect of Safe Reinforcement Learning (Safe RL) involves estimating the constraint condition for the next policy, which is crucial for guiding the optimization of safe policy updates. However, the existing Advantage-based Estimation…

Machine Learning · Computer Science 2024-12-17 Juntao Dai , Yaodong Yang , Qian Zheng , Gang Pan

We study the effect of baselines in on-policy stochastic policy gradient optimization, and close the gap between the theory and practice of policy optimization methods. Our first contribution is to show that the \emph{state value} baseline…

Machine Learning · Computer Science 2023-01-18 Jincheng Mei , Wesley Chung , Valentin Thomas , Bo Dai , Csaba Szepesvari , Dale Schuurmans

The beneficial effects of treatments vary across individuals in most studies. Treatment heterogeneity motivates practitioners to search for the optimal policy based on personal characteristics. A long-standing common practice in policy…

Statistics Theory · Mathematics 2025-01-06 Xuqiao Li , Ying Yan

This note proposes a data-driven output-feedback stabilizing policy iteration for unknown linear discrete-time systems with unmeasurable states. Existing policy iteration methods for optimal control must start from a stabilizing control…

Systems and Control · Electrical Eng. & Systems 2025-12-01 Dongdong Li , Jiuxiang Dong

Entropy regularized algorithms such as Soft Q-learning and Soft Actor-Critic, recently showed state-of-the-art performance on a number of challenging reinforcement learning (RL) tasks. The regularized formulation modifies the standard RL…

Machine Learning · Statistics 2019-10-15 Elena Smirnova , Elvis Dohmatob

Monotonic policy improvement and off-policy learning are two main desirable properties for reinforcement learning algorithms. In this paper, by lower bounding the performance difference of two policies, we show that the monotonic policy…

Artificial Intelligence · Computer Science 2017-11-02 Ryo Iwaki , Minoru Asada

We address the problem of A/B testing, a widely used protocol for evaluating the potential improvement achieved by a new decision system compared to a baseline. This protocol segments the population into two subgroups, each exposed to a…

Machine Learning · Statistics 2025-06-16 Otmane Sakhi , Alexandre Gilotte , David Rohde

Reinforcement learning is structurally harder than supervised learning because the policy changes the data distribution it learns from. The resulting fragility is especially visible in large-model training, where the training and rollout…

Machine Learning · Computer Science 2026-05-13 Rasool Fakoor , Murdock Aubry , Nicholas Stranges , Alexander J. Smola

Policy gradient methods in reinforcement learning update policy parameters by taking steps in the direction of an estimated gradient of policy value. In this paper, we consider the statistically efficient estimation of policy gradients from…

Machine Learning · Statistics 2020-02-21 Nathan Kallus , Masatoshi Uehara

We investigate the important problem of certifying stability of reinforcement learning policies when interconnected with nonlinear dynamical systems. We show that by regulating the input-output gradients of policies, strong guarantees of…

Systems and Control · Computer Science 2018-10-30 Ming Jin , Javad Lavaei

Policy Gradient (PG) algorithms are among the best candidates for the much-anticipated applications of reinforcement learning to real-world control tasks, such as robotics. However, the trial-and-error nature of these methods poses safety…

Machine Learning · Computer Science 2022-06-20 Matteo Papini , Matteo Pirotta , Marcello Restelli

Designing effective model-based reinforcement learning algorithms is difficult because the ease of data generation must be weighed against the bias of model-generated data. In this paper, we study the role of model usage in policy…

Machine Learning · Computer Science 2021-11-30 Michael Janner , Justin Fu , Marvin Zhang , Sergey Levine

Trust Region Policy Optimization (TRPO) and Proximal Policy Optimization (PPO) are among the most successful policy gradient approaches in deep reinforcement learning (RL). While these methods achieve state-of-the-art performance across a…

Machine Learning · Computer Science 2020-06-22 Ahmed Touati , Amy Zhang , Joelle Pineau , Pascal Vincent

One of the fundamental challenges for offline reinforcement learning (RL) is ensuring robustness to data distribution. Whether the data originates from a near-optimal policy or not, we anticipate that an algorithm should demonstrate its…

Machine Learning · Computer Science 2023-10-18 Xiaohan Hu , Yi Ma , Chenjun Xiao , Yan Zheng , Jianye Hao

The deployment of autonomous robots in safety-critical applications requires safety guarantees. Provably safe reinforcement learning is an active field of research that aims to provide such guarantees using safeguards. These safeguards…

Machine Learning · Computer Science 2026-05-08 Tim Walter , Hannah Markgraf , Jonathan Külz , Matthias Althoff

In reinforcement learning, robust policies for high-stakes decision-making problems with limited data are usually computed by optimizing the percentile criterion, which minimizes the probability of a catastrophic failure. Unfortunately,…

Machine Learning · Computer Science 2021-03-01 Elita A. Lobo , Mohammad Ghavamzadeh , Marek Petrik

This paper proposes a simulation-based reinforcement learning algorithm for controlling systems with uncertain and varying system parameters. While simulators are useful for safely learning control policies, the reality gap remains a major…

Systems and Control · Electrical Eng. & Systems 2026-05-14 Junya Ikemoto

We revisit the stochastic variance-reduced policy gradient (SVRPG) method proposed by Papini et al. (2018) for reinforcement learning. We provide an improved convergence analysis of SVRPG and show that it can find an $\epsilon$-approximate…

Machine Learning · Computer Science 2019-05-30 Pan Xu , Felicia Gao , Quanquan Gu

Reinforcement learning has received high research interest for developing planning approaches in automated driving. Most prior works consider the end-to-end planning task that yields direct control commands and rarely deploy their algorithm…

Robotics · Computer Science 2023-07-31 Marvin Klimke , Benjamin Völz , Michael Buchholz