Online Learning With Costly Features In Non-stationary Environments

Abstract

Maximizing long-term rewards is the primary goal in sequential decision-making problems. The majority of existing methods assume that side information is freely available, enabling the learning agent to observe all features' states before making a decision. In real-world problems, however, collecting beneficial information is often costly. That implies that, besides individual arms' reward, learning the observations of the features' states is essential to improve the decision-making strategy. The problem is aggravated in a non-stationary environment where reward and cost distributions undergo abrupt changes over time. To address the aforementioned dual learning problem, we extend the contextual bandit setting and allow the agent to observe subsets of features' states. The objective is to maximize the long-term average gain, which is the difference between the accumulated rewards and the paid costs on average. Therefore, the agent faces a trade-off between minimizing the cost of informa

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keyghoorchian2023online

Related papers

• A New Bandit Setting Balancing Information From State Evolution And Corrupted Context (2020)0.00
• Decision Market Based Learning For Multi-agent Contextual Bandit Problems (2022)0.00
• Principal-agent Bandit Games With Self-interested And Exploratory Learning Agents (2024)0.00
• A Survey Of Learning In Multiagent Environments: Dealing With Non-stationarity (2017)0.00
• Inverse Contextual Bandits Without Rewards: Learning From A Non-stationary Learner Via Suffix Imitation (2026)0.00
• Bandit Social Learning: Exploration Under Myopic Behavior (2023)0.00
• Near-optimal Collaborative Learning In Bandits (2022)0.00
• Goal-oriented Inference Of Environment From Redundant Observations (2023)3.58