Playing First-Person-Shooter Games with A3C-Anticipator Network Based Agents Using Reinforcement Learning

Sun, Yibo; Khan, Adil; Yang, Kai; Jiang, Feng; Liu, Shaohui

doi:10.1007/978-3-030-24268-8_43

Cited by 5 publications

(5 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The most common method of quantitative comparison is to use the obtained reward to compare two or more trained agents; we found find this used in [10][11][12][13][14][15][16]. It is indeed a reliable metric to use in a local environment; however, it leads to results that cannot be compared to anything outside of that paper as the reward will differ from project to project.…”

Section: Metricsmentioning

confidence: 99%

“…The A3C algorithm was tested against a A3C-Anticipator network in [13] but it was concluded that there was not a significant difference between the two.…”

Section: Asynchronous Advantage Actor-criticmentioning

confidence: 99%

“…An Asynchronous Actor-Critic Agent (A3C) algorithm with an anticipator network was pitted against a regular A3C algorithm [13]. This anticipator predicts the next frame according to the current frame and inputs it to the A3C algorithm.…”

mentioning

confidence: 99%

See 2 more Smart Citations

Reinforcement Learning Applied to AI Bots in First-Person Shooters: A Systematic Review

2023

View full text Add to dashboard Cite

Reinforcement Learning is one of the many machine learning paradigms. With no labelled data, it is concerned with balancing the exploration and exploitation of an environment with one or more agents present in it. Recently, many breakthroughs have been made in the creation of these agents for video game machine learning development, especially in first-person shooters with platforms such as ViZDoom, DeepMind Lab, and Unity’s ML-Agents. In this paper, we review the state-of-the-art of creation of Reinforcement Learning agents for use in multiplayer deathmatch first-person shooters. We selected various platforms, frameworks, and training architectures from various papers and examined each of them, analysing their uses. We compared each platform and training architecture, and then concluded whether machine learning agents can now face off against humans and whether they make for better gameplay than traditional Artificial Intelligence. In the end, we thought about future research and what researchers should keep in mind when exploring and testing this area.

show abstract

Section: Metricsmentioning

confidence: 99%

“…The A3C algorithm was tested against a A3C-Anticipator network in [13] but it was concluded that there was not a significant difference between the two.…”

Section: Asynchronous Advantage Actor-criticmentioning

confidence: 99%

See 1 more Smart Citation

Reinforcement Learning Applied to AI Bots in First-Person Shooters: A Systematic Review

2023

View full text Add to dashboard Cite

show abstract

“…Gamification. A significant feature of RL agents lies in the simulation of the task, which often revolves around learning a game (Mnih et al, 2013;Sun et al, 2019). These agents require a reward function in order to train their algorithms correctly, which means that any task an individual creates must center around a gamified component.…”

Section: Figure 3 Hat Experiments Platform Frameworkmentioning

confidence: 99%

Designing Human-Autonomy Teaming Experiments Through Reinforcement Learning

Schelble

Canonico

McNeese

et al. 2020

Proceedings of the Human Factors and Ergonomics Society Annual

View full text Add to dashboard Cite

This paper creates and defines a framework for building and implementing human-autonomy teaming experiments that enable the utilization of modern reinforcement learning models. These models are used to train artificial agents to then interact alongside humans in a human-autonomy team. The framework was synthesized from experience gained redesigning a previously known and validated team task simulation environment known as NeoCITIES. Through this redesign, several important high-level distinctions were made that regarded both the artificial agent and the task simulation itself. The distinctions within the framework include gamification, access to high-performance computing, a proper reward function, an appropriate team task simulation, and customizability. This framework enables researchers to create experiments that are more usable for the human and more closely resemble real-world human-autonomy interactions. The framework also allows researchers to create veritable and robust experimental platforms meant to study human-autonomy teaming for years to come.

show abstract

“…The result emphasized the promising capabilities of DQN and DRQN in game AI, showcasing the potential for the DQN and DRQN algorithms to outperform human players when making decisions based solely on raw screen pixels. The work proposed in [26] addresses the limitations of common built-in game agents, which often rely on pre-written scripts and potentially unfair information. Instead, the paper focuses on utilizing deep learning and reinforcement learning methods to create game agents that make decisions more flexibly, akin to human players who rely solely on the game screen.…”

Section: Introductionmentioning

confidence: 99%

Using VizDoom Research Platform Scenarios for Benchmarking Reinforcement Learning Algorithms in First-Person Shooter Games

Khan,

Shah,

Khan

et al. 2024

IEEE Access

View full text Add to dashboard Cite

Advances in deep reinforcement learning have made it possible to create artificial intelligencebased agents for games that use visual information to make decisions as accurately as humans. Novel procedures are often evaluated in two-dimensional games. However, they are relatively easy compared to three-dimensional games, which have a significantly larger state and action space and, more prominently, contain partially observable states. Thus, this paper trains agents with different reinforcement learning algorithms that work fine in contradiction of human players and in-built agents by evaluating them in the first-person shooter (FPS) game Doom using the VizDoom platform. The agents learned in three different scenarios (maps): ' Defend the Center,' 'Deadly Corridor,' and 'Health gathering.' C51-DDQN, DFP, and REINFORCE algorithms have been proven effective in this study. To assess how well the trained agents performed using various reinforcement learning algorithms, we compared the results of our research with other findings in the literature. Finally, this paper presents a comparative analysis and future research directions.

show abstract

Playing First-Person-Shooter Games with A3C-Anticipator Network Based Agents Using Reinforcement Learning

Cited by 5 publications

References 11 publications

Reinforcement Learning Applied to AI Bots in First-Person Shooters: A Systematic Review

Reinforcement Learning Applied to AI Bots in First-Person Shooters: A Systematic Review

Designing Human-Autonomy Teaming Experiments Through Reinforcement Learning

Using VizDoom Research Platform Scenarios for Benchmarking Reinforcement Learning Algorithms in First-Person Shooter Games

Contact Info

Product

Resources

About