arXiv subjects

Alexander Grishin

Publications and source records attributed to Alexander Grishin.

4 recordsLinked to original sources

arXiv2024

Can AI Understand Human Personality? -- Comparing Human Experts and AI Systems at Predicting Personality Correlations

We test the abilities of specialised deep neural networks like PersonalityMap as well as general LLMs like GPT-4o and Claude 3 Opus in understanding human personality. Specifically, we compare their ability to predict correlations between personality items to the abilities of lay people and academic experts. We find that when compared with individual humans, all AI models make better predictions than the vast majority of lay people and academic experts. However, when selecting the median prediction for each item, we find a different pattern: Experts and PersonalityMap outperform LLMs and lay people on most measures. Our results suggest that while frontier LLMs' are better than most individual humans at predicting correlations between personality items, specialised models like PersonalityMap continue to match or exceed expert human performance even on some outcome measures where LLMs underperform. This provides evidence both in favour of the general capabilities of large language models and in favour of the continued place for specialised models trained and deployed for specific domains.

cs.CY↗

arXiv2022

Automating Control of Overestimation Bias for Reinforcement Learning

Overestimation bias control techniques are used by the majority of high-performing off-policy reinforcement learning algorithms. However, most of these techniques rely on pre-defined bias correction policies that are either not flexible enough or require environment-specific tuning of hyperparameters. In this work, we present a general data-driven approach for the automatic selection of bias control hyperparameters. We demonstrate its effectiveness on three algorithms: Truncated Quantile Critics, Weighted Delayed DDPG, and Maxmin Q-learning. The proposed technique eliminates the need for an extensive hyperparameter search. We show that it leads to a significant reduction of the actual number of interactions while preserving the performance.

cs.LG↗

arXiv2020

Controlling Overestimation Bias with Truncated Mixture of Continuous Distributional Quantile Critics

The overestimation bias is one of the major impediments to accurate off-policy learning. This paper investigates a novel way to alleviate the overestimation bias in a continuous control setting. Our method---Truncated Quantile Critics, TQC,---blends three ideas: distributional representation of a critic, truncation of critics prediction, and ensembling of multiple critics. Distributional representation and truncation allow for arbitrary granular overestimation control, while ensembling provides additional score improvements. TQC outperforms the current state of the art on all environments from the continuous control benchmark suite, demonstrating 25% improvement on the most challenging Humanoid environment.

cs.LG↗

arXiv2020

UV-laser modification and selective ion-beam etching of amorphous vanadium pentoxide thin films

We present the results on excimer laser modification and patterning of amorphous vanadium pentoxide films. Wet positive resist-type and Ar ion-beam negative resist-type etching techniques were employed to develop UV-modified films. V2O5 films were found to possess sufficient resistivity compared to standard electronic materials thus to be promising masks for sub-micron lithog-raphy

physics.app-ph↗