Stochastic Reward

Stochastic reward, a core concept in reinforcement learning and related fields, focuses on optimizing decision-making in environments where outcomes are probabilistic rather than deterministic. Current research emphasizes efficient exploration strategies within these uncertain environments, employing techniques like reward randomization and confidence-bound methods within various model architectures, including linear bandits, neural networks, and Markov Decision Processes (MDPs). This research is crucial for advancing the capabilities of AI agents in complex, real-world scenarios, particularly in areas like resource allocation, personalized recommendations, and control systems where uncertainty is inherent. Improved algorithms for handling stochastic rewards directly translate to more robust and effective AI systems across diverse applications.

Papers

October 14, 2024

Improved Regret Bound for Safe Reinforcement Learning via Tighter Cost Pessimism and Reward Optimism
Kihyun Yu, Duksang Lee, William Overman, Dabeen Lee
Markov Decision Process Safe Reinforcement Learning Regret Bound Value Function Stochastic Reward

October 12, 2024

A Complete Characterization of Learnability for Stochastic Noisy Bandits
Steve Hanneke, Kun Wang
Stochastic Bandit Stochastic Reward Complete Characterization

October 8, 2024

Contextual Bandits with Non-Stationary Correlated Rewards for User Association in MmWave Vehicular Networks
Xiaoyang He, Xiaoxia Huang, Lanhua Li
Contextual Bandit mmWave Signal USER Provided Name Contextual Multi Armed Bandit Stochastic Reward Vehicular Communication mmWave Vehicular Communication

July 18, 2024

Random Latent Exploration for Deep Reinforcement Learning
Srinath Mahankali, Zhang-Wei Hong, Ayush Sekhari, Alexander Rakhlin, Pulkit Agrawal
Deep Reinforcement Learning Stochastic Reward Latent Exploration

June 3, 2024

Sparsity-Agnostic Linear Bandits with Adaptive Adversaries
Tianyuan Jin, Kyoungseok Jang, Nicolò Cesa-Bianchi
Regret Bound Linear Bandit Adversarial Behavior Stochastic Reward Adaptive Adversary Linear Reward Sparse Linear Bandit

May 23, 2024

Learning Constrained Markov Decision Processes With Non-stationary Rewards and Constraints
Francesco Emanuele Stradi, Anna Lunghi, Matteo Castiglioni, Alberto Marchesi, Nicola Gatti
Participation Constraint Bandit Feedback Constrained Markov Decision Process Stochastic Reward Adversarial Markov Decision Process Constraint Violation Adversarial Reward

April 5, 2024

A proximal policy optimization based intelligent home solar management
Kode Creer, Imitiaz Parvez
Proximal Policy Optimization Smart Grid Electricity Market Stochastic Reward

March 16, 2024

Incentivized Exploration of Non-Stationary Stochastic Bandits
Sourav Chakraborty, Lijun Chen
Multi Armed Bandit Sublinear Regret Stochastic Reward Biased Feedback Exploration Algorithm Incentivized Exploration

February 14, 2024

Steady-State Error Compensation for Reinforcement Learning with Quadratic Rewards
Liyao Wang, Zishun Zheng, Yuan Lin
Reinforcement Learning Reward Function Adaptive Cruise Control Stochastic Reward

February 10, 2024

Learning the Expected Core of Strictly Convex Stochastic Cooperative Games
Nam Phuong Tran, The Anh Ta, Shuqing Shi, Debmalya Mandal, Yali Du, Long Tran-Thanh
LeArning Abstract Stochastic Game Stochastic Convex Optimization Stochastic Reward Complex ECC Core Convex Game Stable Payoff Allocation

February 5, 2024

Non-Stationary Latent Auto-Regressive Bandits
Anna L. Trella, Walter Dempsey, Finale Doshi-Velez, Susan A. Murphy
Multi Armed Bandit Non Stationary Environment Stochastic Reward Latent Bandit \Mathcal{o}}$ Revenue Regret

February 3, 2024

Off-Policy Evaluation of Slate Bandit Policies via Optimizing Abstraction
Haruka Kiyohara, Masahiro Nomura, Yuta Saito
Contextual Bandit Policy Evaluation Cognitive Abstraction Stochastic Reward Inverse Propensity Bandit Policy

August 29, 2023

Pure Exploration under Mediators' Feedback
Riccardo Poiani, Alberto Maria Metelli, Marcello Restelli
Human Feedback Sequential Decision Stochastic Reward Pure Exploration Stochastic Multi Armed Bandit Observed Mediator

June 20, 2023

Provably Robust Temporal Difference Learning for Heavy-Tailed Rewards
Semih Cayci, Atilla Eryilmaz
Stochastic Gradient Temporal Difference Learning Stochastic Reward Heavy Tailed Reward Truly Robust Case

June 4, 2023

A Unified Framework for Factorizing Distributional Value Functions for Multi-Agent Reinforcement Learning
Wei-Fang Sun, Cheng-Kuang Lee, Simon See, Chun-Yi Lee
Multi Agent Reinforcement Learning Unified Framework Distributional Reinforcement Learning Multi Agent Challenge Stochastic Reward Value Function Factorization

May 23, 2023

Disincentivizing Polarization in Social Networks
Christian Borgs, Jennifer Chayes, Christian Ikeokwu, Ellen Vitercik
Social Network Political Polarization Stochastic Reward

May 18, 2023

Online Resource Allocation in Episodic Markov Decision Processes
Duksang Lee, William Overman, Dabeen Lee
Markov Decision Process Resource Allocation Optimal Regret Episodic Markov Decision Process Stochastic Reward Online Resource Allocation

April 30, 2023

ICQ: A Quantization Scheme for Best-Arm Identification Over Bit-Constrained Channels
Fathima Zarin Faizal, Adway Girish, Manjesh Kumar Hanawal, Nikhil Karamchandani
Multi Armed Bandit Sample Complexity Best Arm Identification Stochastic Reward Constrained Channel

March 31, 2023

Online Reinforcement Learning in Markov Decision Process Using Linear Programming
Vincent Leon, S. Rasoul Etesami
Markov Decision Process Online Reinforcement Learning Linear Programming Episodic Markov Decision Process Stochastic Reward Regret Rate

January 9, 2023

Exploration in Model-based Reinforcement Learning with Randomized Reward
Lingxiao Wang, Ping Li
Environment Exploration Model Based Reinforcement Learning Optimal Regret Stochastic Reward