GMAC: A Distributional Perspective on Actor-Critic Framework

Authors: Daniel W Nam, Younghoon Kim, Chan Y Park

ICML 2021 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental We empirically show that GMAC captures the correct representation of value distributions and improves the performance of a conventional actor-critic method with low computational cost, in both discrete and continuous action spaces using Arcade Learning Environment (ALE) and Py Bullet environment.
Researcher Affiliation Industry 1KC Machine Learning Lab, Seoul, Korea. Correspondence to: Daniel <dwtnam@kc-ml2.com>.
Pseudocode Yes Algorithm 1 SR(λ)
Open Source Code No The paper does not contain an explicit statement about releasing source code for the described methodology or a direct link to a code repository.
Open Datasets Yes in both discrete and continuous action spaces using Arcade Learning Environment (ALE) and Py Bullet environment.
Dataset Splits No The paper mentions using Arcade Learning Environment (ALE) and Py Bullet environment, but it does not specify exact percentages, sample counts, or explicit references to predefined train/validation/test splits.
Hardware Specification No The paper does not provide specific hardware details such as exact GPU/CPU models or memory amounts used for running its experiments.
Software Dependencies No The paper does not provide specific software dependencies with version numbers (e.g., library names with versions).
Experiment Setup Yes For a fair comparison, we keep all common hyperparameters consistent across the algorithms except for the value heads and their respective hyperparameters (see Appendix F).