English
Related papers

Related papers: The Role of Baselines in Policy Gradient Optimizat…

200 papers

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

Standard reinforcement learning methods aim to master one way of solving a task whereas there may exist multiple near-optimal policies. Being able to identify this collection of near-optimal policies can allow a domain expert to efficiently…

Machine Learning · Computer Science 2019-06-04 Muhammad A. Masood , Finale Doshi-Velez

Policy optimization is a core component of reinforcement learning (RL), and most existing RL methods directly optimize parameters of a policy based on maximizing the expected total reward, or its surrogate. Though often achieving…

Machine Learning · Computer Science 2018-08-10 Ruiyi Zhang , Changyou Chen , Chunyuan Li , Lawrence Carin

This paper considers the problem of learning safe policies in the context of reinforcement learning (RL). In particular, we consider the notion of probabilistic safety. This is, we aim to design policies that maintain the state of the…

Machine Learning · Computer Science 2023-04-20 Weiqin Chen , Dharmashankar Subramanian , Santiago Paternain

We consider policy optimization methods in reinforcement learning settings where the state space is arbitrarily large, or even countably infinite. The motivation arises from control problems in communication networks, matching markets, and…

Machine Learning · Computer Science 2024-09-23 Yashaswini Murthy , Isaac Grosof , Siva Theja Maguluri , R. Srikant

We study the efficient off-policy evaluation of natural stochastic policies, which are defined in terms of deviations from the behavior policy. This is a departure from the literature on off-policy evaluation where most work consider the…

Machine Learning · Computer Science 2020-11-05 Nathan Kallus , Masatoshi Uehara

Standard policy gradients weight each sampled action by advantage alone, regardless of how likely that action was under the current policy. This creates two pathologies: within a single decision context (e.g. one image or prompt), a rare…

Machine Learning · Computer Science 2026-03-17 Ian Osband

Off-policy policy optimization is a challenging problem in reinforcement learning (RL). The algorithms designed for this problem often suffer from high variance in their estimators, which results in poor sample efficiency, and have issues…

Machine Learning · Computer Science 2020-09-15 Daoming Lyu , Qi Qi , Mohammad Ghavamzadeh , Hengshuai Yao , Tianbao Yang , Bo Liu

We consider infinite-horizon discounted Markov decision processes and study the convergence rates of the natural policy gradient (NPG) and the Q-NPG methods with the log-linear policy class. Using the compatible function approximation…

Machine Learning · Computer Science 2023-02-22 Rui Yuan , Simon S. Du , Robert M. Gower , Alessandro Lazaric , Lin Xiao

This work revisits standard policy gradient methods used on restricted policy classes, which are known to get stuck in suboptimal critical points. We identify an important cause for this phenomenon to be that the policy gradient is itself…

Machine Learning · Computer Science 2026-05-12 Alex DeWeese , Guannan Qu

We study Markov potential games under the infinite horizon average reward criterion. Most previous studies have been for discounted rewards. We prove that both algorithms based on independent policy gradient and independent natural policy…

Machine Learning · Computer Science 2024-03-12 Min Cheng , Ruida Zhou , P. R. Kumar , Chao Tian

We develop a normative framework for hierarchical model-based policy optimization based on applying second-order methods in the space of all possible state-action paths. The resulting natural path gradient performs policy updates in a…

Machine Learning · Computer Science 2020-01-03 Daniel McNamee

We study a new two-time-scale stochastic gradient method for solving optimization problems, where the gradients are computed with the aid of an auxiliary variable under samples generated by time-varying MDPs controlled by the underlying…

Optimization and Control · Mathematics 2024-08-27 Sihan Zeng , Thinh T. Doan , Justin Romberg

We provide global convergence rates for vanilla and entropy-regularized federated softmax stochastic policy gradient (FedPG) with local training. We show that FedPG converges to a near-optimal policy in terms of the average agent value,…

Machine Learning · Computer Science 2026-04-02 Safwan Labbi , Paul Mangold , Daniil Tiapkin , Eric Moulines

While nowadays most gradient-based optimization methods focus on exploring the high-dimensional geometric features, the random error accumulated in a stochastic version of any algorithm implementation has not been stressed yet. In this…

Machine Learning · Computer Science 2020-08-14 Tong Yang , Long Sha , Pengyu Hong

We propose networked policy gradient play for solving Markov potential games with continuous and/or discrete state-action pairs. During the game, agents use parametrized and differentiable policies that depend on the current state and the…

Systems and Control · Electrical Eng. & Systems 2025-10-02 Sarper Aydin , Ceyhun Eksin

Policy gradient methods have been successfully applied to many complex reinforcement learning problems. However, policy gradient methods suffer from high variance, slow convergence, and inefficient exploration. In this work, we introduce a…

Machine Learning · Computer Science 2017-04-11 Yang Liu , Prajit Ramachandran , Qiang Liu , Jian Peng

In order to model risk aversion in reinforcement learning, an emerging line of research adapts familiar algorithms to optimize coherent risk functionals, a class that includes conditional value-at-risk (CVaR). Because optimizing the…

Machine Learning · Computer Science 2021-03-09 Audrey Huang , Liu Leqi , Zachary C. Lipton , Kamyar Azizzadenesheli

Compared to on-policy counterparts, off-policy model-free deep reinforcement learning can improve data efficiency by repeatedly using the previously gathered data. However, off-policy learning becomes challenging when the discrepancy…

Machine Learning · Computer Science 2023-09-27 Baturay Saglam , Dogan C. Cicek , Furkan B. Mutlu , Suleyman S. Kozat

We propose expected policy gradients (EPG), which unify stochastic policy gradients (SPG) and deterministic policy gradients (DPG) for reinforcement learning. Inspired by expected sarsa, EPG integrates (or sums) across actions when…

Machine Learning · Statistics 2020-05-05 Kamil Ciosek , Shimon Whiteson