Dota 2 Bot Competition

Font, José; Mahlmann, Tobias

doi:10.1109/tg.2018.2834566

Cited by 20 publications

(8 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…These RTS tasks inherently require multiscale computations for agents to play [ 185 ], and thus are a framework that arguably has relevance for behavioral scientists [ 13 , 179 ]. The current RTS games most studied by AI researchers (e.g., Starcraft with several AI systems [ 186 ], Dota 2 with OpenAI’s OpenAI Five [ 184 , 187 ]) have elements of traditional foraging behavior. RTS game agents must calculate the risks-versus-rewards of seeking new resource patches in dangerous environments as their current patches dwindle [ 186 ], while keeping a long-term goal in mind, similar to the paradigm with global risk pressures discussed previously in Wittman et al [ 64 ] Additionally, multiple scales of computation are needed, often involving transformer networks like those described above, because players are presented with a game display screen that only shows a small local environment contained within a larger game map, where the larger map is only presented as a small symbolic display insert in the main game screen ( Figure 7 ) [ 174 , 184 , 185 , 186 ].…”

Section: Multiscale Aimentioning

confidence: 99%

Multiscale Computation and Dynamic Attention in Biological and Artificial Intelligence

2020

View full text Add to dashboard Cite

Biological and artificial intelligence (AI) are often defined by their capacity to achieve a hierarchy of short-term and long-term goals that require incorporating information over time and space at both local and global scales. More advanced forms of this capacity involve the adaptive modulation of integration across scales, which resolve computational inefficiency and explore-exploit dilemmas at the same time. Research in neuroscience and AI have both made progress towards understanding architectures that achieve this. Insight into biological computations come from phenomena such as decision inertia, habit formation, information search, risky choices and foraging. Across these domains, the brain is equipped with mechanisms (such as the dorsal anterior cingulate and dorsolateral prefrontal cortex) that can represent and modulate across scales, both with top-down control processes and by local to global consolidation as information progresses from sensory to prefrontal areas. Paralleling these biological architectures, progress in AI is marked by innovations in dynamic multiscale modulation, moving from recurrent and convolutional neural networks—with fixed scalings—to attention, transformers, dynamic convolutions, and consciousness priors—which modulate scale to input and increase scale breadth. The use and development of these multiscale innovations in robotic agents, game AI, and natural language processing (NLP) are pushing the boundaries of AI achievements. By juxtaposing biological and artificial intelligence, the present work underscores the critical importance of multiscale processing to general intelligence, as well as highlighting innovations and differences between the future of biological and artificial intelligence.

show abstract

Section: Multiscale Aimentioning

confidence: 99%

Multiscale Computation and Dynamic Attention in Biological and Artificial Intelligence

2020

View full text Add to dashboard Cite

show abstract

“…In recent years, many new testing platforms have emerged to verify methods of the IIG [6,7]. In these platforms, the strategy game includes all the base elements of the IIG, such as StarCraft and VizDoom.…”

Section: Introductionmentioning

confidence: 99%

AIBPO: Combine the Intrinsic Reward and Auxiliary Task for 3D Strategy Game

Cao

Wang

et al. 2021

Complexity

View full text Add to dashboard Cite

In recent years, deep reinforcement learning (DRL) achieves great success in many fields, especially in the field of games, such as AlphaGo, AlphaZero, and AlphaStar. However, due to the reward sparsity problem, the traditional DRL-based method shows limited performance in 3D games, which contain much higher dimension of state space. To solve this problem, in this paper, we propose an intrinsic-based policy optimization (IBPO) algorithm for reward sparsity. In the IBPO, a novel intrinsic reward is integrated into the value network, which provides an additional reward in the environment with sparse reward, so as to accelerate the training. Besides, to deal with the problem of value estimation bias, we further design three types of auxiliary tasks, which can evaluate the state value and the action more accurately in 3D scenes. Finally, a framework of auxiliary intrinsic-based policy optimization (AIBPO) is proposed, which improves the performance of the IBPO. The experimental results show that the method is able to deal with the reward sparsity problem effectively. Therefore, the proposed method may be applied to real-world scenarios, such as 3-dimensional navigation and automatic driving, which can improve the sample utilization to reduce the cost of interactive sample collected by the real equipment.

show abstract

“…In Europe, the 1997 "Red Annihilation" tournament was the beginning of the award for competitions (Kocadağ, 2017). The prize money, which was as low as $1,500-2000 during those periods, was worth $20,770,460 in the prize pool for the International in 2016, and the first-place team in the competition won $9,139,000 (Font and Mahlmann, 2019). This situation is inevitably becoming an industry in individuals.…”

Section: Introductionmentioning

confidence: 99%

Examination of the Levels of Digital Game Dependency of the Students of the Faculty of Sports

Karahüseyinoğlu¹,

Altungül²,

Nacar³

et al. 2020

Asian Journal of Education and Training

View full text Add to dashboard Cite

The aim of our study was to examine the digital game addiction levels of the students of the Faculty of Sports Sciences in terms of some variables. The research group of our study consists of 397 randomly selected undergraduate students studying at Firat University Faculty of Sports Sciences and Inonu University Faculty of Sports Sciences in 2019. Frequency of variables (f) and percentage (%) distributions were calculated and two-way variance analysis (ANOVA) was used in multiple group variables and t-test was used for the significance of the difference between the two independent groups. Tukey test was used to determine which groups it was among in the analysis in which significant differences were detected. According to the findings of our study, undergraduate students studying in the departments of Firat University Faculty of Sports Sciences and Inonu University Faculty of Sports Sciences; It was determined that there was no statistically significant difference in the level of digital game dependency of the undergraduate students depending on the department, class, gender and age variables in which they studied. There was a statistically significant difference between digital game dependency levels based on the state of playing the digital game and the daily playing time variables. In line with the study findings, digital game addiction with an average of 2.29 on the digital game addiction scores of undergraduate students studying at

show abstract

Dota 2 Bot Competition

Cited by 20 publications

References 11 publications

Multiscale Computation and Dynamic Attention in Biological and Artificial Intelligence

Multiscale Computation and Dynamic Attention in Biological and Artificial Intelligence

AIBPO: Combine the Intrinsic Reward and Auxiliary Task for 3D Strategy Game

Examination of the Levels of Digital Game Dependency of the Students of the Faculty of Sports

Contact Info

Product

Resources

About