Meta-reinforcement learning for mastering multiple skills and generalizing across environments in text-based games
Text-based games can be used to develop task-oriented text agents for accomplishing tasks with high-level language instructions, which has potential applications in domains such as human-robot interaction. Given a text instruction, reinforcement learning is commonly used to train agents to complete...
Главные авторы: | Zhao, Z, Sun, M, Ma, X |
---|---|
Формат: | Conference item |
Язык: | English |
Опубликовано: |
Association for Computational Linguistics
2021
|
Схожие документы
-
Master of the Game /
по: Sheldon, Sidney, 1917-2007, author 252709
Опубликовано: (1982) -
Master of the game /
по: Sheldon, Sidney, 1917-2007 author
Опубликовано: (1993) -
The development and mastering of the skills of self-regulation in the course of game biofeedback: psychological analysis
по: K. G. Mazhirina, и др.
Опубликовано: (2010-04-01) -
Mastering accounting skills /
по: 371066 Nicholson, Margaret
Опубликовано: (2006) -
Mastering mathematical skills /
по: 415294 Ganis, Antonios, и др.
Опубликовано: (1981)