[HTML][HTML] Reward is enough
In this article we hypothesise that intelligence, and its associated abilities, can be
understood as subserving the maximisation of reward. Accordingly, reward is enough to …
understood as subserving the maximisation of reward. Accordingly, reward is enough to …
Emergent multi-agent communication in the deep learning era
A Lazaridou, M Baroni - arXiv preprint arXiv:2006.02419, 2020 - arxiv.org
The ability to cooperate through language is a defining feature of humans. As the
perceptual, motory and planning capabilities of deep artificial networks increase …
perceptual, motory and planning capabilities of deep artificial networks increase …
Emergence of grounded compositional language in multi-agent populations
I Mordatch, P Abbeel - Proceedings of the AAAI conference on artificial …, 2018 - ojs.aaai.org
By capturing statistical patterns in large corpora, machine learning has enabled significant
advances in natural language processing, including in machine translation, question …
advances in natural language processing, including in machine translation, question …
Computational rationality: Linking mechanism and behavior through bounded utility maximization
We propose a framework for including information‐processing bounds in rational analyses.
It is an application of bounded optimality (Russell & Subramanian, 1995) to the challenges …
It is an application of bounded optimality (Russell & Subramanian, 1995) to the challenges …
A cordial sync: Going beyond marginal policies for multi-agent embodied tasks
Autonomous agents must learn to collaborate. It is not scalable to develop a new centralized
agent every time a task's difficulty outpaces a single agent's abilities. While multi-agent …
agent every time a task's difficulty outpaces a single agent's abilities. While multi-agent …
Two body problem: Collaborative visual task completion
Collaboration is a necessary skill to perform tasks that are beyond one agent's capabilities.
Addressed extensively in both conventional and modern AI, multi-agent collaboration has …
Addressed extensively in both conventional and modern AI, multi-agent collaboration has …
Interpretation of emergent communication in heterogeneous collaborative embodied agents
Communication between embodied AI agents has received increasing attention in recent
years. Despite its use, it is still unclear whether the learned communication is interpretable …
years. Despite its use, it is still unclear whether the learned communication is interpretable …
Compositional obverter communication learning from raw visual input
One of the distinguishing aspects of human language is its compositionality, which allows us
to describe complex environments with limited vocabulary. Previously, it has been shown …
to describe complex environments with limited vocabulary. Previously, it has been shown …
Sol: An agent-based framework for cyber situation awareness
In this article, we describe how we augment human perception and cognition through Sol,
an agent-based framework for distributed sensemaking. We describe how our visualization …
an agent-based framework for distributed sensemaking. We describe how our visualization …
A framework for the emergence and analysis of language in social learning agents
TJ Wieczorek, T Tchumatchenko… - Nature …, 2024 - nature.com
Neural systems have evolved not only to solve environmental challenges through internal
representations but also, under social constraints, to communicate these to conspecifics. In …
representations but also, under social constraints, to communicate these to conspecifics. In …