Zobrazeno 1 - 4
of 4
pro vyhledávání: '"Volovikova, Zoya"'
In this study, we address the issue of enabling an artificial intelligence agent to execute complex language instructions within virtual environments. In our framework, we assume that these instructions involve intricate linguistic structures and mul
Externí odkaz:
http://arxiv.org/abs/2407.09287
Autor:
Skrynnik, Alexey, Volovikova, Zoya, Côté, Marc-Alexandre, Voronov, Anton, Zholus, Artem, Arabzadeh, Negar, Mohanty, Shrestha, Teruel, Milagro, Awadallah, Ahmed, Panov, Aleksandr, Burtsev, Mikhail, Kiseleva, Julia
The adoption of pre-trained language models to generate action plans for embodied agents is a promising research strategy. However, execution of instructions in real or simulated environments requires verification of the feasibility of actions as wel
Externí odkaz:
http://arxiv.org/abs/2211.00688
Autor:
Zholus, Artem, Skrynnik, Alexey, Mohanty, Shrestha, Volovikova, Zoya, Kiseleva, Julia, Szlam, Artur, Coté, Marc-Alexandre, Panov, Aleksandr I.
We present the IGLU Gridworld: a reinforcement learning environment for building and evaluating language conditioned embodied agents in a scalable way. The environment features visual agent embodiment, interactive learning through collaboration, lang
Externí odkaz:
http://arxiv.org/abs/2206.00142
Autor:
Kiseleva, Julia, Skrynnik, Alexey, Zholus, Artem, Mohanty, Shrestha, Arabzadeh, Negar, Côté, Marc-Alexandre, Aliannejadi, Mohammad, Teruel, Milagro, Li, Ziming, Burtsev, Mikhail, ter Hoeve, Maartje, Volovikova, Zoya, Panov, Aleksandr, Sun, Yuxuan, Srinet, Kavya, Szlam, Arthur, Awadallah, Ahmed
Human intelligence has the remarkable ability to adapt to new tasks and environments quickly. Starting from a very young age, humans acquire new skills and learn how to solve new tasks either by imitating the behavior of others or by following provid
Externí odkaz:
http://arxiv.org/abs/2205.13771