Understanding and Diagnosing Deep Reinforcement Learning

Authors: Ezgi Korkmaz

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

Reproducibility Variable Result LLM Response
Research Type Experimental Through experiments in the Arcade Learning Environment (ALE), we demonstrate the effectiveness of our technique for identifying correlated directions of instability, and for measuring how sample shifts remold the set of sensitive directions in the neural policy landscape.
Researcher Affiliation Academia 1University College London (UCL). Correspondence to: Ezgi Korkmaz <ezgikorkmazmail@gmail.com>.
Pseudocode Yes Algorithm 1 RA-NLD: Robustness Analysis via Non Lipschitz Directions in the Deep Neural Policy Manifold
Open Source Code No No concrete access to source code for the methodology described in this paper is provided.
Open Datasets Yes Through experiments in the Arcade Learning Environment (ALE), we demonstrate the effectiveness of our technique for identifying correlated directions of instability...
Dataset Splits No The set of states S is collected over 10 episodes.
Hardware Specification No No specific hardware details (like GPU models, CPU types, or memory) used for running experiments are provided in the paper.
Software Dependencies No The paper mentions algorithms used (Double Deep Q-Network, State-Adversarial Double Deep Q-Network) but does not provide specific software dependencies with version numbers (e.g., Python, PyTorch, TensorFlow versions).
Experiment Setup Yes The adversarial perturbation hyperparameters are: for the Carlini&Wagner formulation κ is 10, learning rate is 0.01, initial constant is 10, for the elastic-net regularization formulation β is 0.0001, learning rate is 0.1, maximum iteration is 300, for Nesterov Momentum ϵ is 0.001, and decay factor is 0.1.