paper-with-me

Papers

Offline Contextual Bandits with Overparameterized Models

2020-06-27 · David Brandfonbrener, William F. Whitney, Rajesh Ranganath, Joan Bruna

Recent results in supervised learning suggest that while overparameterized models have the capacity to overfit, they in fact generalize quite well. We ask whether the same phenomenon occurs for offline contextual bandits. Our results are mixed. Value-based algorithms benefit from the same generalization behavior as overparameterized supervised learning, but policy-based algorithms do not. We show that this discrepancy is due to the \emph{action-stability} of their objectives. An objective is action-stable if there exists a prediction (action-value vector or action distribution) which is optimal no matter which action is observed. While value-based objectives are action-stable, policy-based objectives are unstable. We formally prove upper bounds on the regret of overparameterized value-based learning and lower bounds on the regret for policy-based algorithms. In our experiments with large neural networks, this gap between action-stable value-based objectives and unstable policy-based objectives leads to significant performance differences.

📄 PDF Abstract BibTeX arXiv:2006.15368

Code (1)

davidbrandfonbrener/deep-offline-bandits 공식 구현 pytorch

Tasks

Multi-Armed BanditsQ-Learning

Methods 이 논문이 사용한 방법론

Q-Learning Q-Learning is an off-policy temporal difference control algorithm: $$Q\left(S\_{t}, A\_{t}\right) \leftarrow Q\left(S\_{t}, A\_{t}\right) + \alpha\left[R_{t+1} +…

Similar Papers 제목 키워드 기반

Provably and Practically Efficient Neural Contextual Bandits

2022-05-31 · Sudeep Salgia, Sattar Vakili, Qing Zhao

We consider the neural contextual bandit problem. In contrast to the existing work which primarily focuses on ReLU neural nets, we consider a general set of smooth activation functions. Under this more general setting, (…

Multi-Armed Bandits

Bypassing the Monster: A Faster and Simpler Optimal Algorithm for Contextual Bandits under Realizability

2020-03-28 · David Simchi-Levi, Yunzong Xu

We consider the general (stochastic) contextual bandit problem under the realizability assumption, i.e., the expected reward, as a function of contexts and actions, belongs to a general function class $\mathcal{F}$. We d…

Multi-Armed Banditsregression

Improving Offline Contextual Bandits with Distributional Robustness

2020-11-13 · Otmane Sakhi, Louis Faury, Flavian vasile

This paper extends the Distributionally Robust Optimization (DRO) approach for offline contextual bandits. Specifically, we leverage this framework to introduce a convex reformulation of the Counterfactual Risk Minimizat…

counterfactualMulti-Armed BanditsStochastic Optimization

Group-Sensitive Offline Contextual Bandits

2025-10-31 · Yihong Guo, Junjie Luo, Guodong Gao, Ritu Agarwal 외 arxiv

Offline contextual bandits allow one to learn policies from historical/offline data without requiring online interaction. However, offline policy optimization that maximizes overall expected rewards can unintentionally a…

Upper Counterfactual Confidence Bounds: a New Optimism Principle for Contextual Bandits

2020-07-15 · Yunbei Xu, Assaf Zeevi

The principle of optimism in the face of uncertainty is one of the most widely used and successful ideas in multi-armed bandits and reinforcement learning. However, existing optimistic algorithms (primarily UCB and its v…

counterfactualMulti-Armed Banditsregression