English
Related papers

Related papers: Policy Optimization as Wasserstein Gradient Flows

200 papers

Policy gradient lies at the core of deep reinforcement learning (RL) in continuous domains. Despite much success, it is often observed in practice that RL training with policy gradient can fail for many reasons, even on standard control…

Machine Learning · Computer Science 2024-01-23 Tao Wang , Sylvia Herbert , Sicun Gao

Although well-established in general reinforcement learning (RL), value-based methods are rarely explored in constrained RL (CRL) for their incapability of finding policies that can randomize among multiple actions. To apply value-based…

Machine Learning · Computer Science 2022-06-28 Tianchi Cai , Wenpeng Zhang , Lihong Gu , Xiaodong Zeng , Jinjie Gu

To overcome the curses of dimensionality and modeling of Dynamic Programming (DP) methods to solve Markov Decision Process (MDP) problems, Reinforcement Learning (RL) methods are adopted in practice. Contrary to traditional RL algorithms…

Machine Learning · Computer Science 2021-08-24 Arghyadip Roy , Vivek Borkar , Abhay Karandikar , Prasanna Chaporkar

We investigate a stochastic program with expected value constraints, addressing the problem in a general context through Distributionally Robust Optimization (DRO) approach using Wasserstein distances, where the ambiguity set depends on the…

Optimization and Control · Mathematics 2023-04-18 Diego Fonseca , Mauricio Junca

In recent years, reinforcement learning (RL) systems with general goals beyond a cumulative sum of rewards have gained traction, such as in constrained problems, exploration, and acting upon prior experiences. In this paper, we consider…

Machine Learning · Computer Science 2020-07-07 Junyu Zhang , Alec Koppel , Amrit Singh Bedi , Csaba Szepesvari , Mengdi Wang

Distributionally Robust Optimization (DRO) is a popular framework for decision-making under uncertainty, but its adversarial nature can lead to overly conservative solutions. To address this, we study ex-ante Distributionally Robust Regret…

Optimization and Control · Mathematics 2025-04-22 Lukas-Benedikt Fiechtner , Jose Blanchet

We study first-order optimality conditions for constrained optimization in the Wasserstein space, whereby one seeks to minimize a real-valued function over the space of probability measures endowed with the Wasserstein distance. Our…

Optimization and Control · Mathematics 2025-03-03 Nicolas Lanzetti , Saverio Bolognani , Florian Dörfler

Traditional policy gradient methods are fundamentally flawed. Natural gradients converge quicker and better, forming the foundation of contemporary Reinforcement Learning such as Trust Region Policy Optimization (TRPO) and Proximal Policy…

Machine Learning · Computer Science 2022-09-07 W. J. A. van Heeswijk

Entropy regularization is an important idea in reinforcement learning, with great success in recent algorithms like Soft Q Network (SQN) and Soft Actor-Critic (SAC1). In this work, we extend this idea into the on-policy realm. We propose…

Machine Learning · Computer Science 2020-10-19 Jingbin Liu , Xinyang Gu , Shuai Liu

Distributionally Robust Optimization (DRO) has enabled to prove the equivalence between robustness and regularization in classification and regression, thus providing an analytical reason why regularization generalizes well in statistical…

Optimization and Control · Mathematics 2020-07-15 Esther Derman , Shie Mannor

Wasserstein policy gradient (WPG) is a policy optimization method for reinforcement learning (RL) that exploits the optimal-transport geometry of action distributions. For the entropy-regularized RL objective, WPG evolves each…

Machine Learning · Computer Science 2026-05-27 Zhaoyu Zhu , Rui Gao , Shuang Li

We consider the optimization problem of minimizing a functional defined over a family of probability distributions, where the objective functional is assumed to possess a variational form. Such a distributional optimization problem arises…

Machine Learning · Computer Science 2024-04-02 Zhuoran Yang , Yufeng Zhang , Yongxin Chen , Zhaoran Wang

We consider constrained policy optimization in Reinforcement Learning, where the constraints are in form of marginals on state visitations and global action executions. Given these distributions, we formulate policy optimization as…

Machine Learning · Computer Science 2021-02-17 Arash Givchi , Pei Wang , Junqi Wang , Patrick Shafto

Performativity means that the deployment of a predictive model incentivizes agents to strategically adapt their behavior, thereby inducing a model-dependent distribution shift. Practitioners often repeatedly retrain the model on data…

Optimization and Control · Mathematics 2026-02-09 Siyi Wang , Zifan Wang , Karl H. Johansson

Humans are masters at quickly learning many complex tasks, relying on an approximate understanding of the dynamics of their environments. In much the same way, we would like our learning agents to quickly adapt to new tasks. In this paper,…

We propose a mathematically principled PDE gradient flow framework for distributionally robust optimization (DRO). Exploiting the recent advances in the intersection of Markov Chain Monte Carlo sampling and gradient flow theory, we show…

Optimization and Control · Mathematics 2026-05-27 Zusen Xu , Jia-Jie Zhu

Reinforcement learning (RL) problems over general state and action spaces are notoriously challenging. In contrast to the tableau setting, one can not enumerate all the states and then iteratively update the policies for each state. This…

Machine Learning · Computer Science 2026-03-24 Caleb Ju , Guanghui Lan

The objective in a traditional reinforcement learning (RL) problem is to find a policy that optimizes the expected value of a performance metric such as the infinite-horizon cumulative discounted or long-run average cost/reward. In…

Machine Learning · Computer Science 2022-05-25 Prashanth L. A. , Michael Fu

In this paper, we consider the problem of learning safe policies for probabilistic-constrained reinforcement learning (RL). Specifically, a safe policy or controller is one that, with high probability, maintains the trajectory of the agent…

Machine Learning · Computer Science 2024-03-14 Weiqin Chen , Dharmashankar Subramanian , Santiago Paternain

We consider statistical methods which invoke a min-max distributionally robust formulation to extract good out-of-sample performance in data-driven optimization and learning problems. Acknowledging the distributional uncertainty in learning…

Statistics Theory · Mathematics 2021-08-05 Jose Blanchet , Karthyek Murthy , Viet Anh Nguyen