video-games

FPS Games

3260 papers • 126 benchmarks • 313 datasets

First-person shooter (FPS) games Involve like call of duty so enjoy ( Image credit: Procedural Urban Environments for FPS Games )

(Image credit: Papersgraph)

Benchmarks

These leaderboards are used to track progress in video-games

Trend

Dataset

Best Model

Actions

No benchmarks available.

Libraries

i

Use these libraries to find video-games models and implementations

Datasets

No datasets available.

Subtasks

Game of Doom

Most implemented papers

ViZDoom: A Doom-based AI research platform for visual reinforcement learning

Michal Kempka, Marek Wydmuch, Grzegorz Runc, Jakub Toczek, Wojciech Jaśkowski•Thu May 05 2016

A novel test-bed platform for reinforcement learning research from raw visual information which employs the first-person perspective in a semi-realistic 3D world and confirms the utility of ViZDoom as an AI research platform and implies that visual reinforcement learning in 3D realistic first- person perspective environments is feasible.

736

Content

0

Paper Graph

Playing FPS Games with Deep Reinforcement Learning

Guillaume Lample, Devendra Singh Chaplot•Sat Sep 17 2016

This paper presents the first architecture to tackle 3D environments in first-person shooter games, that involve partially observable states, and substantially outperforms built-in AI agents of the game as well as average humans in deathmatch scenarios.

620 0

Paper Graph

Counter-Strike Deathmatch with Large-Scale Behavioural Cloning

Jun Zhu, Tim Pearce•Thu Apr 08 2021

An AI agent that plays the modern first-person-shooter video game ‘Counter-Strike; Global Offensive’ (CSGO) from pixel input, a deep neural network that matches the performance of a casual human gamer on the deathmatch game mode whilst adopting a humanlike play style.

67 0

Paper Graph

Sample Factory: Egocentric 3D Control from Pixels at 100000 FPS with Asynchronous Reinforcement Learning

V. Koltun, Aleksei Petrenko, G. Sukhatme, Zhehui Huang, T. Kumar•Sat Jun 20 2020

The "Sample Factory" is presented, a high-throughput training system optimized for a single-machine setting that combines a highly efficient, asynchronous, GPU-based sampler with off-policy correction techniques, allowing for throughput higher than $10^5$ environment frames/second on non-trivial control problems in 3D without sacrificing sample efficiency.

122 0

Paper Graph

Deep Successor Reinforcement Learning

Tejas D. Kulkarni, A. Saeedi, Simanta Gautam, S. Gershman•Tue Jun 07 2016

DSR is presented, which generalizes Successor Representations within an end-to-end deep reinforcement learning framework and has several appealing properties including: increased sensitivity to distal reward changes due to factorization of reward and world dynamics, and the ability to extract bottleneck states given successor maps trained under a random policy.

220 0

Paper Graph

Active Neural Localization

R. Salakhutdinov, Emilio Parisotto, Devendra Singh Chaplot•Tue Jan 23 2018

The proposed model incorporates ideas of traditional filtering-based localization methods, by using a structured belief of the state with multiplicative interactions to propagate belief, and combines it with a policy model to localize accurately while minimizing the number of steps required.

88 0

Paper Graph

Learning-Driven Exploration for Reinforcement Learning

Muhammad Usama, D. Chang•Sun Jun 16 2019

This work introduces entropy-based exploration (EBE) that enables an agent to explore efficiently the unexplored regions of state space and quantifies the agent's learning in a state using state-dependent action values and adaptively explores the state space.

11 0

Paper Graph

Understanding Cyber Athletes Behaviour Through a Smart Chair: CS:GO and Monolith Team Scenario

Anton Smerdov, A. Somov, Anastasia Kiskun, Rostislav Shaniiazov, E. Burnaev•Sun Mar 31 2019

This work proposes a smart chair platform - an unobtrusive approach to the collection of data on the eSports athletes and data further processing with machine learning methods and demonstrates that the professional athletes can be identified by their behaviour on the chair while playing the game.

11 0

Paper Graph

eSports Pro-Players Behavior During the Game Events: Statistical Analysis of Data Obtained Using the Smart Chair

Anton Smerdov, A. Somov, E. Burnaev•Wed Jul 31 2019

The smart chair platform is proposed which is to collect data on the person's behavior on the chair using an integrated accelerometer, a gyroscope and a magnetometer to distinguish between the low-skilled and high-skilled players.

10 0

Paper Graph

AI-enabled Prediction of eSports Player Performance Using the Data from Heterogeneous Sensors

Evgeny Burnaev, Anton Smerdov, A. Somov•Sun Dec 06 2020

An Artificial Intelligence (AI) enabled solution for predicting the eSports player in-game performance using exclusively the data from sensors and has a number of promising applications for Pro eSports teams as well as a learning tool for amateur players.

2 0

Paper Graph

Adding a benchmark result helps the community track progress.