Notice: The reproducibility variables underlying each score are classified using an automated LLM-based pipeline, validated against a manually labeled dataset. LLM-based classification introduces uncertainty and potential bias; scores should be interpreted as estimates. Full accuracy metrics and methodology are described in [1].
Context Uncertainty in Contextual Bandits with Applications to Recommender Systems
Authors: Hao Wang, Yifei Ma, Hao Ding, Yuyang Wang8539-8547
AAAI 2022 | Venue PDF | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | Our empirical study demonstrates that REN can achieve satisfactory long-term rewards on both synthetic and real-world recommendation datasets, outperforming state-of-the-art models. |
| Researcher Affiliation | Collaboration | Hao Wang1,2*, Yifei Ma1, Hao Ding1, Yuyang Wang1 1AWS AI Labs 2Department of Computer Science, Rutgers University EMAIL, EMAIL |
| Pseudocode | Yes | Algorithm 1: Recurrent Exploration Networks (REN) and Algorithm 2: Base REN: Basic REN Inference at Step t are provided. |
| Open Source Code | No | The paper does not provide an explicit statement or a link to its source code for the described methodology. |
| Open Datasets | Yes | We use Movie Lens-1M (Harper and Konstan 2016) containing 3,900 movies and 6,040 users... We also evaluate the proposed methods on Trivago... Finally, we also use Netflix... |
| Dataset Splits | No | The paper describes a rolling online evaluation procedure and mentions different time intervals for data, but it does not provide specific percentages or counts for training, validation, and test splits in a traditional sense. |
| Hardware Specification | No | The paper does not specify any hardware details such as GPU models, CPU types, or memory used for running the experiments. |
| Software Dependencies | No | The paper mentions using RNNs and specific models like GRU4Rec and TCN, but it does not provide version numbers for any software dependencies, programming languages, or libraries used in the experiments. |
| Experiment Setup | Yes | For REN variants we choose λd from {0.001, 0.005, 0.01, 0.05, 0.1} and set λu = 10λd. Other hyperparameters in the RNN base models are kept the same for fair comparison (see the Supplement for more details on neural network architectures, hyperparameters, and their sensitivity analysis). We set the number of hidden neurons to 32 for all models including REN variants. |