Attention Schema in Neural Agents
- URL: http://arxiv.org/abs/2305.17375v3
- Date: Fri, 14 Jul 2023 01:43:24 GMT
- Title: Attention Schema in Neural Agents
- Authors: Dianbo Liu, Samuele Bolotta, He Zhu, Yoshua Bengio, Guillaume Dumas
- Abstract summary: In cognitive neuroscience, Attention Theory (AST) supports the idea of distinguishing attention from AS.
AST predicts that an agent can use its own AS to also infer the states of other agents' attention.
We explore different ways in which attention and AS interact with each other.
- Score: 66.43628974353683
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: Attention has become a common ingredient in deep learning architectures. It
adds a dynamical selection of information on top of the static selection of
information supported by weights. In the same way, we can imagine a
higher-order informational filter built on top of attention: an Attention
Schema (AS), namely, a descriptive and predictive model of attention. In
cognitive neuroscience, Attention Schema Theory (AST) supports this idea of
distinguishing attention from AS. A strong prediction of this theory is that an
agent can use its own AS to also infer the states of other agents' attention
and consequently enhance coordination with other agents. As such, multi-agent
reinforcement learning would be an ideal setting to experimentally test the
validity of AST. We explore different ways in which attention and AS interact
with each other. Our preliminary results indicate that agents that implement
the AS as a recurrent internal control achieve the best performance. In
general, these exploratory experiments suggest that equipping artificial agents
with a model of attention can enhance their social intelligence.
Related papers
- Interactive Autonomous Navigation with Internal State Inference and
Interactivity Estimation [58.21683603243387]
We propose three auxiliary tasks with relational-temporal reasoning and integrate them into the standard Deep Learning framework.
These auxiliary tasks provide additional supervision signals to infer the behavior patterns other interactive agents.
Our approach achieves robust and state-of-the-art performance in terms of standard evaluation metrics.
arXiv Detail & Related papers (2023-11-27T18:57:42Z) - Revisiting Attention Weights as Explanations from an Information
Theoretic Perspective [4.499369811647602]
We show that attention mechanisms have the potential to function as a shortcut to model explanations when they are carefully combined with other model elements.
Our findings indicate that attention mechanisms do have the potential to function as a shortcut to model explanations when they are carefully combined with other model elements.
arXiv Detail & Related papers (2022-10-31T12:53:20Z) - Be Your Own Neighborhood: Detecting Adversarial Example by the
Neighborhood Relations Built on Self-Supervised Learning [64.78972193105443]
This paper presents a novel AE detection framework, named trustworthy for predictions.
performs the detection by distinguishing the AE's abnormal relation with its augmented versions.
An off-the-shelf Self-Supervised Learning (SSL) model is used to extract the representation and predict the label.
arXiv Detail & Related papers (2022-08-31T08:18:44Z) - Guiding Visual Question Answering with Attention Priors [76.21671164766073]
We propose to guide the attention mechanism using explicit linguistic-visual grounding.
This grounding is derived by connecting structured linguistic concepts in the query to their referents among the visual objects.
The resultant algorithm is capable of probing attention-based reasoning models, injecting relevant associative knowledge, and regulating the core reasoning process.
arXiv Detail & Related papers (2022-05-25T09:53:47Z) - Joint Attention for Multi-Agent Coordination and Social Learning [108.31232213078597]
We show that joint attention can be useful as a mechanism for improving multi-agent coordination and social learning.
Joint attention leads to higher performance than a competitive centralized critic baseline across multiple environments.
Taken together, these findings suggest that joint attention may be a useful inductive bias for multi-agent learning.
arXiv Detail & Related papers (2021-04-15T20:14:19Z) - Hard Attention Control By Mutual Information Maximization [4.56877715768796]
Biological agents have adopted the principle of attention to limit the rate of incoming information from the environment.
We propose an approach for learning how to control a hard attention window by maximizing the mutual information between the environment state and the attention location at each step.
arXiv Detail & Related papers (2021-03-10T22:38:28Z) - Attention Transfer Network for Aspect-level Sentiment Classification [30.704053194980528]
Aspect-level sentiment classification (ASC) aims to detect the sentiment polarity of a given opinion target in a sentence.
Data scarcity causes the attention mechanism sometimes to fail to focus on the corresponding sentiment words of the target.
We propose a novel Attention Transfer Network (ATN) in this paper, which can successfully exploit attention knowledge from document-level sentiment classification datasets.
arXiv Detail & Related papers (2020-10-23T04:26:33Z) - Noisy Agents: Self-supervised Exploration by Predicting Auditory Events [127.82594819117753]
We propose a novel type of intrinsic motivation for Reinforcement Learning (RL) that encourages the agent to understand the causal effect of its actions.
We train a neural network to predict the auditory events and use the prediction errors as intrinsic rewards to guide RL exploration.
Experimental results on Atari games show that our new intrinsic motivation significantly outperforms several state-of-the-art baselines.
arXiv Detail & Related papers (2020-07-27T17:59:08Z) - Attention or memory? Neurointerpretable agents in space and time [0.0]
We design a model incorporating a self-attention mechanism that implements task-state representations in semantic feature-space.
To evaluate the agent's selective properties, we add a large volume of task-irrelevant features to observations.
In line with neuroscience predictions, self-attention leads to increased robustness to noise compared to benchmark models.
arXiv Detail & Related papers (2020-07-09T15:04:26Z)
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.