Safety-Aware Algorithms for Adversarial Contextual Bandit

Authors: Wen Sun, Debadeepta Dey, Ashish Kapoor

ICML 2017 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental We support our theoretical results by demonstrating our algorithm on a simple simulated robotics reactive control task.
Researcher Affiliation Collaboration 1Robotics Institute, Carnegie Mellon University, USA 2Microsoft Research, Redmond, USA.
Pseudocode Yes Algorithm 1 OCP with Sequential Constraints via OMD; Algorithm 2 EXP4 with Risk Constraints (EXP4.R)
Open Source Code No The paper does not provide any explicit statement or link to open-source code for the described methodology.
Open Datasets No The paper describes a "simple synthetic robotics reactive control task" and its "Environment", but it does not specify or provide access information for a publicly available dataset or a generated dataset.
Dataset Splits No The paper describes a simulation environment but does not provide specific details on dataset splits (e.g., training, validation, testing percentages or counts) or cross-validation methods.
Hardware Specification No The paper mentions "paralleling computing" but does not provide any specific details about the hardware (e.g., CPU, GPU models, memory) used for running the simulation.
Software Dependencies No The paper does not provide specific version numbers for any ancillary software, libraries, or programming languages used.
Experiment Setup No The paper describes the environment setup for the simulation and some general configurations (e.g., "initialize the weight over all experts uniformly") but does not provide specific hyperparameters (e.g., learning rates, batch sizes) or system-level training settings.