Zobrazeno 1 - 10
of 146
pro vyhledávání: '"Georgescu Raluca"'
The performance of embodied agents has been shown to improve by increasing model parameters, dataset size, and compute. This has been demonstrated in domains from robotics to video games, when generative learning objectives on offline datasets (pre-t
Externí odkaz:
http://arxiv.org/abs/2411.04434
Autor:
Schäfer, Lukas, Jones, Logan, Kanervisto, Anssi, Cao, Yuhan, Rashid, Tabish, Georgescu, Raluca, Bignell, Dave, Sen, Siddhartha, Gavito, Andrea Treviño, Devlin, Sam
Video games have served as useful benchmarks for the decision making community, but going beyond Atari games towards training agents in modern games has been prohibitively expensive for the vast majority of the research community. Recent progress in
Externí odkaz:
http://arxiv.org/abs/2312.02312
Publikováno v:
SHS Web of Conferences, Vol 129, p 09003 (2021)
Research background: This paper highlights the evolution of the way we communicate, especially on how it accelerated to today’s means of communication, resulted as a secondary outcome of the actual covid19 pandemic. We try to elaborate on the evolu
Externí odkaz:
https://doaj.org/article/bd1b91f92b2f41a2a1c1cbdeb6c415ac
Publikováno v:
SHS Web of Conferences, Vol 74, p 06026 (2020)
Education is the path to sustainable evolution and acceleration of the catching up process in emerging economies. Without education there is no technological breakthrough, no increase in the created added value and also no improvement in the overall
Externí odkaz:
https://doaj.org/article/968471df5e854fe697332e91ebb54360
Autor:
Milani, Stephanie, Juliani, Arthur, Momennejad, Ida, Georgescu, Raluca, Rzpecki, Jaroslaw, Shaw, Alison, Costello, Gavin, Fang, Fei, Devlin, Sam, Hofmann, Katja
We aim to understand how people assess human likeness in navigation produced by people and artificially intelligent (AI) agents in a video game. To this end, we propose a novel AI agent with the goal of generating more human-like behavior. We collect
Externí odkaz:
http://arxiv.org/abs/2303.02160
Autor:
Pearce, Tim, Rashid, Tabish, Kanervisto, Anssi, Bignell, Dave, Sun, Mingfei, Georgescu, Raluca, Macua, Sergio Valcarcel, Tan, Shan Zheng, Momennejad, Ida, Hofmann, Katja, Devlin, Sam
Publikováno v:
ICLR 2023
Diffusion models have emerged as powerful generative models in the text-to-image domain. This paper studies their application as observation-to-action models for imitating human behaviour in sequential environments. Human behaviour is stochastic and
Externí odkaz:
http://arxiv.org/abs/2301.10677
Autor:
Carroll, Micah, Paradise, Orr, Lin, Jessy, Georgescu, Raluca, Sun, Mingfei, Bignell, David, Milani, Stephanie, Hofmann, Katja, Hausknecht, Matthew, Dragan, Anca, Devlin, Sam
Randomly masking and predicting word tokens has been a successful approach in pre-training language models for a variety of downstream tasks. In this work, we observe that the same idea also applies naturally to sequential decision-making, where many
Externí odkaz:
http://arxiv.org/abs/2211.10869
Modern AAA video games feature huge game levels and maps which are increasingly hard for level testers to cover exhaustively. As a result, games often ship with catastrophic bugs such as the player falling through the floor or being stuck in walls. W
Externí odkaz:
http://arxiv.org/abs/2209.00570
Autor:
Carroll, Micah, Lin, Jessy, Paradise, Orr, Georgescu, Raluca, Sun, Mingfei, Bignell, David, Milani, Stephanie, Hofmann, Katja, Hausknecht, Matthew, Dragan, Anca, Devlin, Sam
Randomly masking and predicting word tokens has been a successful approach in pre-training language models for a variety of downstream tasks. In this work, we observe that the same idea also applies naturally to sequential decision making, where many
Externí odkaz:
http://arxiv.org/abs/2204.13326
Autor:
Anichitoae, Florina Magdalena a, b, Dobrean, Anca a, c, ⁎, Georgescu, Raluca Diana c, Roman, Gabriela Diana d
Publikováno v:
In Aggression and Violent Behavior January 2025 80