Autoencoder-augmented Neuroevolution for Visual Doom Playing

2017-07-12 · Samuel Alvernaz, Julian Togelius

Neuroevolution has proven effective at many reinforcement learning tasks, but does not seem to scale well to high-dimensional controller representations, which are needed for tasks where the input is raw pixel data. We propose a novel method where we train an autoencoder to create a comparatively low-dimensional representation of the environment observation, and then use CMA-ES to train neural network controllers acting on this input data. As the behavior of the agent changes the nature of the input data, the autoencoder training progresses throughout evolution. We test this method in the VizDoom environment built on the classic FPS Doom, where it performs well on a health-pack gathering task.

📄 PDF Abstract BibTeX arXiv:1707.03902

Code (0)

등록된 구현이 없습니다.

Tasks

reinforcement-learning Reinforcement Learning Reinforcement Learning (RL)

Methods 이 논문이 사용한 방법론

Solana Customer Service Number +1-833-534-1729 설명 없음

ViZDoom Competitions: Playing Doom from Pixels

2018-09-10 · Marek Wydmuch, Michał Kempka, Wojciech Jaśkowski

This paper presents the first two editions of Visual Doom AI Competition, held in 2016 and 2017. The challenge was to create bots that compete in a multi-player deathmatch in a first-person shooter (FPS) game, Doom. The …

Navigate reinforcement-learning Reinforcement Learning Reinforcement Learning (RL)

Learning Dark Souls Combat Through Pixel Input With Neuroevolution

2025-07-04 · Jim O'Connor, Gary B. Parker, Mustafa Bugti arxiv

This paper investigates the application of Neuroevolution of Augmenting Topologies (NEAT) to automate gameplay in Dark Souls, a notoriously challenging action role-playing game characterized by complex combat mechanics, …

Reinforcement Learning

Playing Doom with SLAM-Augmented Deep Reinforcement Learning

2016-12-01 · Shehroze Bhatti, Alban Desmaison, Ondrej Miksik, Nantas Nardelli 외

A number of recent approaches to policy learning in 2D game domains have been successful going directly from raw input images to actions. However when employed in complex 3D environments, they typically suffer from chall…

Deep Reinforcement Learning object-detection Object Detection Q-Learning+3

Accelerating Deep Neuroevolution on Distributed FPGAs for Reinforcement Learning Problems

2020-05-10 · Alexis Asseman, Nicolas Antoine, Ahmet S. Ozcan

Reinforcement learning augmented by the representational power of deep neural networks, has shown promising results on high-dimensional problems, such as game playing and robotic control. However, the sequential nature o…

Atari Games Computational Efficiency CPU reinforcement-learning+2

Agents that Listen: High-Throughput Reinforcement Learning with Multiple Sensory Systems

2021-07-05 · Shashank Hegde, Anssi Kanervisto, Aleksei Petrenko

Humans and other intelligent animals evolved highly sophisticated perception systems that combine multiple sensory modalities. On the other hand, state-of-the-art artificial agents rely mostly on visual inputs or structu…

Game of Doom reinforcement-learning Reinforcement Learning (RL)Vocal Bursts Intensity Prediction