Model-Based Reinforcement Learning with Multinomial Logistic Function Approximation

Authors: Taehyun Hwang, Min-hwan Oh

AAAI 2023 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental We also comprehensively evaluate our proposed algorithm numerically and show that it consistently outperforms the existing methods, hence achieving both provable efficiency and practical superior performance. Numerical Experiments In this section, we evaluate the performances of our proposed algorithm, UCRL-MNL in numerical experiments.
Researcher Affiliation Academia Taehyun Hwang, Min-hwan Oh* Seoul National University, Seoul, Republic of Korea th.hwang@snu.ac.kr, minoh@snu.ac.kr
Pseudocode Yes Algorithm 1: Upper Confidence Model-based RL for MNL Transition Model (UCRL-MNL)
Open Source Code No The paper does not contain an unambiguous statement of releasing the code for the described methodology or a direct link to a source-code repository.
Open Datasets No The paper uses the 'River Swim environment' but does not provide a specific link, DOI, or repository for a publicly available dataset, nor does it provide a formal citation with author/year for a dataset itself, only for the description of the environment.
Dataset Splits No The paper does not specify exact split percentages, absolute sample counts, or reference predefined splits with citations for training, validation, or test sets. It mentions '10 independent runs' but not data partitioning for model validation.
Hardware Specification No The paper does not provide specific details about the hardware used, such as GPU or CPU models, memory, or cloud instance types.
Software Dependencies No The paper does not mention specific software components with version numbers required for replication.
Experiment Setup No The paper states 'To set the hyperparameters for each algorithm, we performed a grid search over certain ranges' but does not provide the specific hyperparameter values, training configurations, or system-level settings used.