[Re]: Value Alignment Verification
Nov 28, 2022
Speakers
Siba Smarak Panigrahi
Speaker · 0 followers
Sohan Patnaik
Speaker · 0 followers
About
Scope of Reproducibility: The main goal of the paper 'Value Alignment Verification' is to test the alignment of a robot's behavior efficiently with human expectations by constructing a minimal set of questions. To accomplish this, the authors propose algorithms and heuristics to create the above questionnaire. They choose a wide range of gridworld environments and a continuous autonomous driving domain to validate their put forth claims. We explore value alignment verification for gridworlds incorporating a non-linear feature reward mapping as well as an extended action space. Methodology: We re-implemented the pipeline with Python using mathematical libraries such as Numpy and Scipy. We spent approximately two months reproducing the targeted claims in the paper with the first month aimed at reproducing the results for algorithms and heuristics for exact value alignment verification. The second month focused on extending the action space, additional experiments, and refining the structure of our code. Since our experiments were not computationally expensive, we carried out the experiments on CPU. Results: The techniques proposed by authors can successfully address the value alignment verification problem in different settings. We empirically demonstrate the effectiveness of their proposals by performing exhaustive experiments with several variations to their original claims. We show high accuracy and low false positive and false negative rates in the value alignment verification task with a minimum number of questions for different algorithms and heuristics. What was easy: The problem statement, as well as the implementation of algorithms and heuristics, were straightforward. We also took aid from the original repository published with the paper. However, we implemented the entire pipeline from scratch and incorporated several variations to our code to perform additional designed experiments. What was difficult: Comprehending different algorithms and heuristics proposed in prior works along with their mathematical formulation and reasoning for their success in the given task was considerably difficult. Additionally, the original code base had several redundant files, which created initial confusion. We iterated and discussed the arguments in the paper and prior work several times to thoroughly understand the pipeline. Nevertheless, once the basics were clear, the implementation was comparatively simple. Communication with original authors: We reached out to the authors numerous times via email to seek clarifications and additional implementation details. The authors were incredibly receptive to our inquiries, and we appreciate their thorough and prompt responses.Scope of Reproducibility: The main goal of the paper 'Value Alignment Verification' is to test the alignment of a robot's behavior efficiently with human expectations by constructing a minimal set of questions. To accomplish this, the authors propose algorithms and heuristics to create the above questionnaire. They choose a wide range of gridworld environments and a continuous autonomous driving domain to validate their put forth claims. We explore value alignment verification for gridworlds inc…
Organizer
NeurIPS 2022
Account · 952 followers
Like the format? Trust SlidesLive to capture your next event!
Professional recording and live streaming, delivered globally.
Sharing
Recommended Videos
Presentations on similar topic, category or speaker
Global Convergence of Federated Learning for Mixed Regression
Watch later
Jiaming Xu, …
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
Asynchronous SGD Beats Minibatch SGD Under Arbitrary Delays
Watch later
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
Provably Efficient Reinforcement Learning in Partially Observable Dynamical Systems
Watch later
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
Leveraging the Hints: Adaptive Bidding in Repeated First-Price Auctions
Watch later
Wei Zhang, …
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
In-context Reinforcement Learning with Algorithm Distillation
Watch later
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
Reasoning and Abstraction as Challenges for AI
Watch later
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%