Optimal Policy

Optimal policy research focuses on finding the best course of action within a given system, often modeled as a Markov Decision Process (MDP), to maximize a desired outcome (e.g., reward, efficiency). Current research emphasizes developing efficient algorithms, such as policy gradient methods and diffusion models, to solve these problems, particularly in complex settings with high dimensionality or uncertainty, often incorporating techniques like variance reduction and bias correction. These advancements are significant for various fields, including robotics, finance, and AI, enabling improved decision-making in scenarios ranging from controlling robots to optimizing resource allocation. The development of more efficient and robust algorithms for finding optimal policies continues to be a central focus.

Papers

April 18, 2023

Using Offline Data to Speed-up Reinforcement Learning in Procedurally Generated Environments
Alain Andres, Lukas Schäfer, Esther Villar-Rodriguez, Stefano V. Albrecht, Javier Del Ser
Reinforcement Learning Imitation Learning Optimal Policy Environment Feature Offline Data Procedural Text Trajectory Generalization

April 10, 2023

Epidemic Control on a Large-Scale-Agent-Based Epidemiology Model using Deep Deterministic Policy Gradient
Gaurav Deshkar, Jayanta Kshirsagar, Harshal Hayatnagarkar, Janani Venugopalan
Optimal Policy Policy Optimization Deep Deterministic Policy Gradient Pandemic Control Optimal Intervention

March 26, 2023

Balancing policy constraint and ensemble size in uncertainty-based offline reinforcement learning
Alex Beeson, Giovanni Montana
Offline Reinforcement Learning Optimal Policy Robust Policy Online Fine Tuning Policy Constraint Robust Offline Reinforcement Learning

March 20, 2023

A Unified Framework of Policy Learning for Contextual Bandit with Confounding Bias and Missing Observations
Siyu Chen, Yitan Wang, Zhaoran Wang, Zhuoran Yang
Optimal Policy Policy Learning Unobserved Confounders Partial Observation Confounding Bias Offline Contextual Bandit

March 16, 2023

March 15, 2023

Policy Gradient Converges to the Globally Optimal Policy for Nearly Linear-Quadratic Regulators
Yinbin Han, Meisam Razaviyayn, Renyuan Xu
Reinforcement Learning Optimal Policy Linear Quadratic Regulator Nonlinear Control Policy Gradient Algorithm

March 13, 2023

On the Regret of Online Edge Service Hosting
R Sri Prakash, Nikhil Karamchandani, Sharayu Moharir
Optimal Policy Simple Regret Follow the Regularized Leader Performance Guarantee Edge Server

March 9, 2023

Beware of Instantaneous Dependence in Reinforcement Learning
Zhengmao Zhu, Yuren Liu, Honglong Tian, Yang Yu, Kun Zhang
Reinforcement Learning Optimal Policy Model Based Reinforcement Learning Linear Dependence Sub Optimal Policy

March 8, 2023

Inference on Optimal Dynamic Policies via Softmax Approximation
Qizhao Chen, Morgane Austern, Vasilis Syrgkanis
Scientific Inference Optimal Policy Softmax Function Dynamic Treatment Regime Optimal Treatment Optimal Regime

March 6, 2023

Online Learning and Optimization for Queues with Unknown Demand Curve and Service Distribution
Xinyun Chen, Yunan Liu, Guiyu Hong
Optimization Purpose Optimal Policy Online Learning Optimization Problem Optimal Solution Predict Then Optimize Demand Curve Customer Side Queue

March 1, 2023

Planning for Attacker Entrapment in Adversarial Settings
Brittany Cates, Anagha Kulkarni, Sarath Sreedharan
Task Planning Optimal Policy Adversarial Setting

February 27, 2023

February 23, 2023

Intermittently Observable Markov Decision Processes
Gongpu Chen, Soung-Chang Liew
Markov Decision Process Optimal Policy Near Optimal Policy Belief MDP

February 10, 2023

Towards Minimax Optimality of Model-based Robust Reinforcement Learning
Pierre Clavier, Erwan Le Pennec, Matthieu Geist
Markov Decision Process Sample Complexity Optimal Policy Robust Reinforcement Learning Minimax Optimality MDP Model

February 7, 2023

February 3, 2023

Stochastic Policy Gradient Methods: Improved Sample Complexity for Fisher-non-degenerate Policies
Ilyas Fatkhullin, Anas Barakat, Anastasia Kireeva, Niao He
Policy Gradient Sample Complexity Optimal Policy Policy Parameterization Stochastic Policy Gradient

Optimal Policy

Papers

Using Offline Data to Speed-up Reinforcement Learning in Procedurally Generated Environments

Epidemic Control on a Large-Scale-Agent-Based Epidemiology Model using Deep Deterministic Policy Gradient

Balancing policy constraint and ensemble size in uncertainty-based offline reinforcement learning

A Unified Framework of Policy Learning for Contextual Bandit with Confounding Bias and Missing Observations

Decentralized Multi-Agent Reinforcement Learning for Continuous-Space Stochastic Games

Recommending the optimal policy by learning to act from temporal data

Policy Gradient Converges to the Globally Optimal Policy for Nearly Linear-Quadratic Regulators

On the Regret of Online Edge Service Hosting

Beware of Instantaneous Dependence in Reinforcement Learning

Inference on Optimal Dynamic Policies via Softmax Approximation

Online Learning and Optimization for Queues with Unknown Demand Curve and Service Distribution

Planning for Attacker Entrapment in Adversarial Settings

Reinforcement Learning with Depreciating Assets

Distributional Method for Risk Averse Reinforcement Learning

Intermittently Observable Markov Decision Processes

Towards Minimax Optimality of Model-based Robust Reinforcement Learning

Eliciting User Preferences for Personalized Multi-Objective Decision Making through Comparative Feedback

Layered State Discovery for Incremental Autonomous Exploration

Population-size-Aware Policy Optimization for Mean-Field Games

Stochastic Policy Gradient Methods: Improved Sample Complexity for Fisher-non-degenerate Policies