[其他] ICML-Structured World Belief for Reinforcement Learning in POMDP [推广有奖]

1关注
167
粉丝

已卖：5667份资源

泰斗

还不是VIP/贵宾

威望: 0 级
论坛币: 13312 个
通用积分: 711.3950
学术水平: 459 点
热心指数: 484 点
信用等级: 414 点
经验: 116099 点
帖子: 4684
精华: 0
在线时间: 16723 小时
注册时间: 2013-1-2
最后登录: 2026-1-8

楼主

Mujahida

发表于 2025-7-27 11:39:56 |AI写论文

是否 +2 论坛币

k人参与回答

经管之家送您一份

应届毕业生专属福利!

求职就业群

赵安豆老师微信：zhaoandou666

经管之家联合CDA

送您一个全额奖学金名额~ !

立即领取

感谢您参与论坛问题回答

经管之家送您两个论坛币！

+2 论坛币

Structured World Belief for Reinforcement Learning in POMDP

      Gautam Singh 1 Skand Peri 1 Junghyun Kim 1 Hyunseok Kim 2 Sungjin Ahn 1 3

         Abstract                generalization to novel scenes (Chen et al., 2020).
Object-centric world models provide structured       Of particular interest is whether this representation can
representation of the scene and can be an im-       help Reinforcement Learning (RL) and planning. Although
portant backbone in reinforcement  ...