Dealing With Unbounded Gradients in Stochastic Saddle-point Optimization

Authors: Gergely Neu, Nneka Okolo

ICML 2024 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Theoretical Besides providing a set of general results, we also apply our algorithm to a specific problem in reinforcement learning, where it leads to performance guarantees for finding near-optimal policies in an average-reward MDP without prior knowledge of the bias span.
Researcher Affiliation Academia 1Universitat Pompeu Fabra, Barcelona, Spain. Correspondence to: Gergely Neu <gergely.neu@gmail.com>, Nneka Okolo <nnekamaureen.okolo@upf.edu>.
Pseudocode Yes Algorithm 1 COMIDA-MDP
Open Source Code No The paper does not provide an explicit statement or link for open-sourcing the code for the described methodology.
Open Datasets No The paper discusses applying the method to Average-Reward Markov Decision Processes (AMDPs) and mentions using 'a simulator (or generative model) of the transition function P', but it does not specify or provide access information for a public dataset for training.
Dataset Splits No The paper does not provide specific dataset split information (e.g., percentages, sample counts, or citations to predefined splits) needed to reproduce data partitioning for validation, as it is a theoretical paper.
Hardware Specification No The paper does not provide specific hardware details (e.g., CPU/GPU models, memory) used for running experiments.
Software Dependencies No The paper does not provide specific ancillary software details, such as library names with version numbers.
Experiment Setup No While the paper defines parameters for its theoretical algorithms and bounds (e.g., ϱx, ϱy, ηx, ηy), it does not describe a concrete experimental setup with hyperparameters or system-level training settings for an empirical evaluation.