Fundamental Tradeoffs in Learning with Prior Information

Authors: Anirudha Majumdar

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

Reproducibility Variable Result LLM Response
Research Type Experimental We illustrate the ability of our framework to provide insights into tradeoffs between prior information and learning performance for problems in estimation, regression, and reinforcement learning.
Researcher Affiliation Academia Department of Mechanical and Aerospace Engineering, Princeton University, Princeton, NJ, USA.
Pseudocode No The paper describes mathematical reductions and theoretical tools but does not contain any formally labeled pseudocode blocks or algorithms.
Open Source Code No The paper does not provide any concrete access information (e.g., URL, explicit statement of release) for the source code related to its methodology.
Open Datasets Yes Specifically, we build on the Zipfian Gridworld environments from Chan et al. (2022)
Dataset Splits No The paper mentions 'training' (e.g., 'For training, the agent receives n environments from Pθ.') but does not specify any training/validation/test dataset splits, percentages, or methodology for partitioning data.
Hardware Specification No The paper does not provide specific details about the hardware (e.g., CPU, GPU models, memory) used to run its experiments.
Software Dependencies No The paper mentions IMPALA (Espeholt et al., 2018) as a method used for training policies but does not provide specific version numbers for software dependencies or libraries.
Experiment Setup No The paper refers to using a 'pre-computed set A of policies' and training with IMPALA, but it does not provide concrete hyperparameter values or detailed system-level training settings for its experiments.