Meta-Learning Bandit Policies by Gradient Ascent
원문 초록
Most bandit policies are designed to either minimize regret in any problem instance, making very few assumptions about the underlying environment, or in a Bayesian sense, assuming a prior distribution over environment parameters. The former are often too conservative in practical settings, while the latter require assumptions that are hard to verify in practice. We study bandit problems that fall between these two extremes, where the learning agent has access to sampled bandit instances from an unknown prior distribution $\mathcal{P}$ and aims to achieve high reward on average over the bandit instances drawn from $\mathcal{P}$. This setting is of a particular importance because it lays foundations for meta-learning of bandit policies and reflects more realistic assumptions in many practical domains. We propose the use of parameterized bandit policies that are differentiable and can be optimized using policy gradients. This provides a broadly applicable framework that is easy to implement. We derive reward gradients that reflect the structure of bandit problems and policies, for both non-contextual and contextual settings, and propose a number of interesting policies that are both differentiable and have low regret. Our algorithmic and theoretical contributions are supported by extensive experiments that show the importance of baseline subtraction, learned biases, and the practicality of our approach on a range problems.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
A Classification View on Meta Learning Bandits
Geo-ORBIT: A Federated Digital Twin Framework for Scene-Adaptive Lane Geometry Detection
DIP: Unsupervised Dense In-Context Post-training of Visual Representations
Episode-specific Fine-tuning for Metric-based Few-shot Learners with Optimization-based Training
Adaptive Action Duration with Contextual Bandits for Deep Reinforcement Learning in Dynamic Environments
Meta-learning how to Share Credit among Macro-Actions
토론
이 논문과 연결된 포럼 글이 아직 없습니다.