From be5788729f9bb0c04618bf1cd778d104b518ff81 Mon Sep 17 00:00:00 2001 From: Hongbo Guo Date: Thu, 15 Feb 2024 20:32:52 -0800 Subject: [PATCH] add reference Summary: We have these information in Reagent which has been useful for customers and ourselfs as well. This quick fix aligned with reagent code base. Reviewed By: rodrigodesalvobraz Differential Revision: D53694510 fbshipit-source-id: fa53d69028faabb457b90553dc3aa03fa68699b4 --- .../policy_learners/contextual_bandits/neural_linear_bandit.py | 3 +++ 1 file changed, 3 insertions(+) diff --git a/pearl/policy_learners/contextual_bandits/neural_linear_bandit.py b/pearl/policy_learners/contextual_bandits/neural_linear_bandit.py index 56cd3c5c..0a2cc32d 100644 --- a/pearl/policy_learners/contextual_bandits/neural_linear_bandit.py +++ b/pearl/policy_learners/contextual_bandits/neural_linear_bandit.py @@ -50,6 +50,9 @@ class NeuralLinearBandit(ContextualBanditBase): Here _deep_represent_layers can be treated as featuer processing, and then processed features are fed into a linear regression layer to output predicted score. For example : features --> neural networks --> LinUCB --> UCB score + + The implementation of LinearBandit refers to https://arxiv.org/pdf/1003.0146.pdf + The implementation of NeuralLinearBandit refers to https://arxiv.org/pdf/2012.01780.pdf """ def __init__(