ru
ru
Source
IWANN
DATE OF PUBLICATION
08/21/2021
Authors
Ilya Makarov Maria Bakhanova
Share

Deep Reinforcement Learning in VizDoom via DQN and Actor-Critic Agents

Deep reinforcement learning, DQN, A3C, A2C, VizDoom

Abstract

In this work, we study the problem of learning reinforcement learning-based agents in a first-person shooter environment VizDoom. We compare several well-known architectures, such as DQN, DDQN, A3C, and Curiosity-driven model, while highlighting the main differences in learned policies of agents trained via these models.

Full text

Similar publications

ECAI
CA-SER: Cross-Attention Feature Fusion for Speech Emotion Recognition
Bashar M. Deeb, Andrey Savchenko​, Ilya Makarov
SOURCE
ECAI
Device-Specific Facial Descriptors: Winning a Lottery with a SuperNet
Andrey Savchenko​, Ilya Makarov, Dmitrii Maslov
SOURCE
SIGSPATIAL
From Data to Decisions: Streamlining Geospatial Operations with Multimodal GlobeFlowGPT
Danil Kononykhin, Mikhail Mozikov, Kirill Mishtal, Dmitrii Abramov, Pavel Kuznetsov, Nazar Sotiriadi, Yury Maximov, Andrey Savchenko​, Ilya Makarov
SOURCE
ISMAR
Benchmarking and Data Synthesis for Colorization of Manga Sequential Pages for Augmented Reality
Maksim Golyadkin, Sergey Saraev, Ilya Makarov
SOURCE
ISMAR
Pose Networks Unveiled: Bridging the Gap for Monocular Depth Perception
Yazan Dayoub, Andrey Savchenko​, Ilya Makarov
SOURCE
IEEE Open Journal of the Industrial Electronics Society
Adversarial Attacks and Defenses in Automated Control Systems: A Comprehensive Benchmark
Vitaliy Pozdnyakov, Alexander Kovalenko, Ilya Makarov, Mikhail Drobyshevskiy, Kirill Lukyanov
SOURCE
IEEE Access
From Esperanto to Volapük: Interpretable Graph Features for Assessing Linguistic Complexity in Constructed Languages
Irina Sokolova, Ilya Makarov
SOURCE
Contact us
Join AIRI
You can ask us a question or suggest a joint project in the field of AI

Message sent.

Thank you!

Something went wrong. Try again