Active Reasoning in an Open-World Environment
- URL: http://arxiv.org/abs/2311.02018v1
- Date: Fri, 3 Nov 2023 16:24:34 GMT
- Title: Active Reasoning in an Open-World Environment
- Authors: Manjie Xu, Guangyuan Jiang, Wei Liang, Chi Zhang, Yixin Zhu
- Abstract summary: $Conan$ is an interactive open-world environment devised for the assessment of active reasoning.
$Conan$ facilitates active exploration and promotes multi-round abductive inference, reminiscent of rich, open-world settings like Minecraft.
Our analysis underscores the shortcomings of contemporary state-of-the-art models in active exploration and understanding complex scenarios.
- Score: 29.596555383319814
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: Recent advances in vision-language learning have achieved notable success on
complete-information question-answering datasets through the integration of
extensive world knowledge. Yet, most models operate passively, responding to
questions based on pre-stored knowledge. In stark contrast, humans possess the
ability to actively explore, accumulate, and reason using both newfound and
existing information to tackle incomplete-information questions. In response to
this gap, we introduce $Conan$, an interactive open-world environment devised
for the assessment of active reasoning. $Conan$ facilitates active exploration
and promotes multi-round abductive inference, reminiscent of rich, open-world
settings like Minecraft. Diverging from previous works that lean primarily on
single-round deduction via instruction following, $Conan$ compels agents to
actively interact with their surroundings, amalgamating new evidence with prior
knowledge to elucidate events from incomplete observations. Our analysis on
$Conan$ underscores the shortcomings of contemporary state-of-the-art models in
active exploration and understanding complex scenarios. Additionally, we
explore Abduction from Deduction, where agents harness Bayesian rules to recast
the challenge of abduction as a deductive process. Through $Conan$, we aim to
galvanize advancements in active reasoning and set the stage for the next
generation of artificial intelligence agents adept at dynamically engaging in
environments.
Related papers
- Mars: Situated Inductive Reasoning in an Open-World Environment [77.14465960780726]
In this paper, we design Mars, an interactive environment devised for situated inductive reasoning.
It introduces counter-commonsense game mechanisms by modifying terrain, survival setting and task dependency.
In Mars, agents need to actively interact with their surroundings, derive useful rules and perform decision-making tasks in specific contexts.
arXiv Detail & Related papers (2024-10-10T17:10:34Z) - WESE: Weak Exploration to Strong Exploitation for LLM Agents [95.6720931773781]
This paper proposes a novel approach, Weak Exploration to Strong Exploitation (WESE) to enhance LLM agents in solving open-world interactive tasks.
WESE involves decoupling the exploration and exploitation process, employing a cost-effective weak agent to perform exploration tasks for global knowledge.
A knowledge graph-based strategy is then introduced to store the acquired knowledge and extract task-relevant knowledge, enhancing the stronger agent in success rate and efficiency for the exploitation task.
arXiv Detail & Related papers (2024-04-11T03:31:54Z) - Open-world Machine Learning: A Review and New Outlooks [83.6401132743407]
This paper aims to provide a comprehensive introduction to the emerging open-world machine learning paradigm.
It aims to help researchers build more powerful AI systems in their respective fields, and to promote the development of artificial general intelligence.
arXiv Detail & Related papers (2024-03-04T06:25:26Z) - A Survey of Imitation Learning: Algorithms, Recent Developments, and
Challenges [9.288673880680033]
imitation learning (IL) is a process where desired behavior is learned by imitating an expert's behavior.
This paper aims to provide an introduction to IL and an overview of its underlying assumptions and approaches.
It also offers a detailed description of recent advances and emerging areas of research in the field.
arXiv Detail & Related papers (2023-09-05T11:56:07Z) - Brain in a Vat: On Missing Pieces Towards Artificial General
Intelligence in Large Language Models [83.63242931107638]
We propose four characteristics of generally intelligent agents.
We argue that active engagement with objects in the real world delivers more robust signals for forming conceptual representations.
We conclude by outlining promising future research directions in the field of artificial general intelligence.
arXiv Detail & Related papers (2023-07-07T13:58:16Z) - Embodied Agents for Efficient Exploration and Smart Scene Description [47.82947878753809]
We tackle a setting for visual navigation in which an autonomous agent needs to explore and map an unseen indoor environment.
We propose and evaluate an approach that combines recent advances in visual robotic exploration and image captioning on images.
Our approach can generate smart scene descriptions that maximize semantic knowledge of the environment and avoid repetitions.
arXiv Detail & Related papers (2023-01-17T19:28:01Z) - Curious Exploration via Structured World Models Yields Zero-Shot Object
Manipulation [19.840186443344]
We propose to use structured world models to incorporate inductive biases in the control loop to achieve sample-efficient exploration.
Our method generates free-play behavior that starts to interact with objects early on and develops more complex behavior over time.
arXiv Detail & Related papers (2022-06-22T22:08:50Z) - Information is Power: Intrinsic Control via Information Capture [110.3143711650806]
We argue that a compact and general learning objective is to minimize the entropy of the agent's state visitation estimated using a latent state-space model.
This objective induces an agent to both gather information about its environment, corresponding to reducing uncertainty, and to gain control over its environment, corresponding to reducing the unpredictability of future world states.
arXiv Detail & Related papers (2021-12-07T18:50:42Z) - Explore and Explain: Self-supervised Navigation and Recounting [43.52107532692226]
We devise a novel embodied setting in which an agent needs to explore a previously unknown environment while recounting what it sees during the path.
In this context, the agent needs to navigate the environment driven by an exploration goal, select proper moments for description, and output natural language descriptions of relevant objects and scenes.
Our model integrates a novel self-supervised exploration module with penalty, and a fully-attentive captioning model for explanation.
arXiv Detail & Related papers (2020-07-14T18:00:49Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.