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 19, 2022

COptiDICE: Offline Constrained Reinforcement Learning via Stationary Distribution Correction Estimation
Jongmin Lee, Cosmin Paduraru, Daniel J. Mankowitz, Nicolas Heess, Doina Precup, Kee-Eung Kim, Arthur Guez
Reinforcement Learning Optimal Policy Reinforcement Learning Algorithm Policy Evaluation DIstribution Estimation Balancing Efficiency

April 14, 2022

Reinforcement Learning Policy Recommendation for Interbank Network Stability
Alessio Brini, Gabriele Tedeschi, Daniele Tantari
Reinforcement Learning Optimal Policy Recommendation Policy Market Simulation Stable Network Policy Recommendation

April 11, 2022

Automatically Learning Fallback Strategies with Model-Free Reinforcement Learning in Safety-Critical Driving Scenarios
Ugo Lecerf, Christelle Yemdji-Tchassi, Sébastien Aubert, Pietro Michiardi
Autonomous Vehicle Optimal Policy Model Free Reinforcement Learning Safety Critical Driving Scenario

April 4, 2022

Policy Learning with Competing Agents
Roshni Sahoo, Stefan Wager
Agent Smith Optimal Policy Strategic Behavior Policy Constraint Treatment Assignment

March 22, 2022

X-MEN: Guaranteed XOR-Maximum Entropy Constrained Inverse Reinforcement Learning
Fan Ding, Yeiang Xue
Optimal Policy Inverse Reinforcement Learning

March 17, 2022

February 18, 2022

Single-Leg Revenue Management with Advice
Santiago Balseiro, Christian Kroer, Rachitesh Kumar
Optimal Policy Online Allocation Online Combinatorial Advice Quality Revenue Management

February 15, 2022

Pessimistic Minimax Value Iteration: Provably Efficient Equilibrium Learning from Offline Datasets
Han Zhong, Wei Xiong, Jiyuan Tan, Liwei Wang, Tong Zhang, Zhaoran Wang, Zhuoran Yang
Optimal Policy Markov Game Value Iteration Offline Data Approximate Nash Equilibrium Two Player

February 8, 2022

Nonmyopic Multiclass Active Search with Diminishing Returns for Diverse Discovery
Quan Nguyen, Roman Garnett
Optimal Policy Scientific Discovery Customer Service Adaptive Experimental Design Active Search

February 2, 2022

Transfer in Reinforcement Learning via Regret Bounds for Learning Agents
Adrienne Tuynman, Ronald Ortner
Reinforcement Learning Markov Decision Process Optimal Policy Formality Transfer Regret Bound Learning Agent Multi Agent Setting

January 30, 2022

Coordinated Attacks against Contextual Bandits: Fundamental Limits and Defense Mechanisms
Jeongyeol Kwon, Yonathan Efroni, Constantine Caramanis, Shie Mannor
Optimal Policy Contextual Bandit Adversarial Agent Fundamental Limit DEfense Mechanism Multiple Attack Contextual Bandit Setting

January 28, 2022

Learning Stationary Nash Equilibrium Policies in $n$-Player Stochastic Games with Independent Chains
S. Rasoul Etesami
Optimal Policy Reward Function Nash Equilibrium Side Chain

January 24, 2022

GoSafeOpt: Scalable Safe Exploration for Global Optimization of Dynamical Systems
Bhavya Sukhija, Matteo Turchetta, David Lindner, Andreas Krause, Sebastian Trimpe, Dominik Baumann
Real World Dynamical System Optimal Policy Global Optimization Safe Exploration Safe Learning

Optimal Policy

Papers

COptiDICE: Offline Constrained Reinforcement Learning via Stationary Distribution Correction Estimation

Reinforcement Learning Policy Recommendation for Interbank Network Stability

Automatically Learning Fallback Strategies with Model-Free Reinforcement Learning in Safety-Critical Driving Scenarios

Policy Learning with Competing Agents

Near-optimality for infinite-horizon restless bandits with many arms

Neural representation of a time optimal, constant acceleration rendezvous

Learning to act: a Reinforcement Learning approach to recommend the best next activities

Offline Reinforcement Learning Under Value and Density-Ratio Realizability: The Power of Gaps

A Conservative Q-Learning approach for handling distribution shift in sepsis treatment strategies

Randomized Policy Optimization for Optimal Stopping

X-MEN: Guaranteed XOR-Maximum Entropy Constrained Inverse Reinforcement Learning

Semi-Markov Offline Reinforcement Learning for Healthcare

Near Instance-Optimal PAC Reinforcement Learning for Deterministic MDPs

Single-Leg Revenue Management with Advice

Pessimistic Minimax Value Iteration: Provably Efficient Equilibrium Learning from Offline Datasets

Nonmyopic Multiclass Active Search with Diminishing Returns for Diverse Discovery

Transfer in Reinforcement Learning via Regret Bounds for Learning Agents

Coordinated Attacks against Contextual Bandits: Fundamental Limits and Defense Mechanisms

Learning Stationary Nash Equilibrium Policies in $n$-Player Stochastic Games with Independent Chains

GoSafeOpt: Scalable Safe Exploration for Global Optimization of Dynamical Systems