中文
相关论文

相关论文: From Relative Entropy to Minimax: A Unified Framew…

200 篇论文

In the zero-shot policy transfer (ZSPT) setting for contextual Markov decision processes (MDP), agents train on a fixed set of contexts and must generalise to new ones. Recent work has argued and demonstrated that increased exploration can…

机器学习 · 计算机科学 2025-05-23 Max Weltevrede , Caroline Horsch , Matthijs T. J. Spaan , Wendelin Böhmer

We study the model-based reward-free reinforcement learning with linear function approximation for episodic Markov decision processes (MDPs). In this setting, the agent works in two phases. In the exploration phase, the agent interacts with…

机器学习 · 计算机科学 2022-01-03 Weitong Zhang , Dongruo Zhou , Quanquan Gu

While learning in an unknown Markov Decision Process (MDP), an agent should trade off exploration to discover new information about the MDP, and exploitation of the current knowledge to maximize the reward. Although the agent will…

机器学习 · 计算机科学 2020-07-16 Evrard Garcelon , Mohammad Ghavamzadeh , Alessandro Lazaric , Matteo Pirotta

We consider the problem of controlling a fully specified Markov decision process (MDP), also known as the planning problem, when the state space is very large and calculating the optimal policy is intractable. Instead, we pursue the more…

最优化与控制 · 数学 2019-01-09 Yasin Abbasi-Yadkori , Peter L. Bartlett , Xi Chen , Alan Malek

We study the problem of efficient exploration in order to learn an accurate model of an environment, modeled as a Markov decision process (MDP). Efficient exploration in this problem requires the agent to identify the regions in which…

In environments with uncertain dynamics exploration is necessary to learn how to perform well. Existing reinforcement learning algorithms provide strong exploration guarantees, but they tend to rely on an ergodicity assumption. The essence…

机器学习 · 计算机科学 2012-07-10 Teodor Mihai Moldovan , Pieter Abbeel

We introduce the active exploration problem in Markov decision processes (MDPs). Each state of the MDP is characterized by a random value and the learner should gather samples to estimate the mean value of each state as accurately as…

机器学习 · 统计学 2019-03-01 Jean Tarbouriech , Alessandro Lazaric

Markov Decision Processes (MDPs) have been used to formulate many decision-making problems in science and engineering. The objective is to synthesize the best decision (action selection) policies to maximize expected rewards (minimize…

最优化与控制 · 数学 2015-07-08 Mahmoud El Chamie , Behcet Acikmese

A popular perspective in Reinforcement learning (RL) casts the problem as probabilistic inference on a graphical model of the Markov decision process (MDP). The core object of study is the probability of each state-action pair being visited…

机器学习 · 计算机科学 2023-11-23 Jean Tarbouriech , Tor Lattimore , Brendan O'Donoghue

We study Concave Constrained Markov Decision Processes (Concave CMDPs) where both the objective and constraints are defined as concave functions of the state-action occupancy measure. We propose the Variance-Reduced Primal-Dual Policy…

机器学习 · 计算机科学 2024-05-28 Donghao Ying , Mengzi Amy Guo , Hyunin Lee , Yuhao Ding , Javad Lavaei , Zuo-Jun Max Shen

Having access to an exploring restart distribution (the so-called wide coverage assumption) is critical with policy gradient methods. This is due to the fact that, while the objective function is insensitive to updates in unlikely states,…

机器学习 · 计算机科学 2021-06-30 Marco Miani , Maurizio Parton , Marco Romito

Markov Decision Processes (MDPs) are mathematical models of sequential decision-making under uncertainty that have found applications in healthcare, manufacturing, logistics, and others. In these models, a decision-maker observes the state…

最优化与控制 · 数学 2024-05-22 Madeleine Pollack , Lauren N. Steimle

Learning a Markov Decision Process (MDP) from a fixed batch of trajectories is a non-trivial task whose outcome's quality depends on both the amount and the diversity of the sampled regions of the state-action space. Yet, many MDPs are…

机器学习 · 计算机科学 2022-03-08 Giorgio Angelotti , Nicolas Drougard , Caroline P. C. Chanel

In this paper, we consider a Markov decision process (MDP), where the ego agent has a nominal objective to pursue while needs to hide its state from detection by an adversary. After formulating the problem, we first propose a value…

系统与控制 · 电气工程与系统科学 2019-08-22 Nan Li , Ilya Kolmanovsky , Anouck Girard

Value iteration is a well-known method of solving Markov Decision Processes (MDPs) that is simple to implement and boasts strong theoretical convergence guarantees. However, the computational cost of value iteration quickly becomes…

机器学习 · 计算机科学 2021-07-26 Guanting Chen , Johann Demetrio Gaebler , Matt Peng , Chunlin Sun , Yinyu Ye

Policy gradient methods are widely used in reinforcement learning. Yet, the nonconvexity of policy optimization poses significant challenges in understanding the global convergence of policy gradient methods. For a class of finite-horizon…

最优化与控制 · 数学 2026-03-10 Xin Chen , Yifan Hu , Minda Zhao

Markov decision processes (MDPs) is viewed as an optimization of an objective function over certain linear operators over general function spaces. A new existence result is established for the existence of optimal policies in general MDPs,…

机器学习 · 计算机科学 2026-04-01 Abhishek Gupta , Aditya Mahajan

Model-based reinforcement learning (RL) is appealing because (i) it enables planning and thus more strategic exploration, and (ii) by decoupling dynamics from rewards, it enables fast transfer to new reward functions. However, learning an…

Exploration is widely regarded as one of the most challenging aspects of reinforcement learning (RL), with many naive approaches succumbing to exponential sample complexity. To isolate the challenges of exploration, we propose a new…

机器学习 · 计算机科学 2020-02-10 Chi Jin , Akshay Krishnamurthy , Max Simchowitz , Tiancheng Yu

A key challenge to deploying reinforcement learning in practice is avoiding excessive (harmful) exploration in individual episodes. We propose a natural constraint on exploration -- \textit{uniformly} outperforming a conservative policy…

机器学习 · 计算机科学 2023-02-27 Wanqiao Xu , Jason Yecheng Ma , Kan Xu , Hamsa Bastani , Osbert Bastani