Skip Nav Destination
Close Modal
Update search
NARROW
Format
TocHeadingTitle
Date
Availability
1-8 of 8
Christoph Salge
Close
Follow your search
Access your saved searches in your account
Would you like to receive an alert when new items match your search?
Sort by
Proceedings Papers
. isal2023, ALIFE 2023: Ghost in the Machine: Proceedings of the 2023 Artificial Life Conference125, (July 24–28, 2023) 10.1162/isal_a_00588
Abstract
View Paper
PDF
We examine the effect of noise on societies of agents using an agent-based model of evolutionary norm emergence. Generally, we see that noisy societies are more selfish, smaller and discontent, and are caught in rounds of perpetual punishment preventing them from flourishing. Surprisingly, despite the detrimental effect of noise on the population, it does not seem to evolve away. In fact, in some cases it seems the level of noise increases. We carry out further analysis and provide reasons for why this might be the case. Furthermore, we claim that our framework that evolves the noise/ambiguity of norms is a new way to model the tight/loose framework of norms, suggesting that despite ambiguous norms’ detrimental effect on society, evolution does not favour clarity.
Proceedings Papers
. isal2023, ALIFE 2023: Ghost in the Machine: Proceedings of the 2023 Artificial Life Conference125, (July 24–28, 2023) 10.1162/isal_a_00706
Abstract
View Paper
PDF
This is an erratum to The Effect of Noise on the Emergence of Continuous Norms and its Evolutionary Dynamics , published in the Proceedings of the 2023 Conference on Artificial Life. After publication, we discovered an error in the mutation operator. In this correction, we will describe the error, outline what dynamics would produce the results we initially presented, and then compare them with simulation results with the mutation operator working as described in the original paper. We go through the claims of the original paper, discussing any possible differences in the outcomes. Overall, the main results of the paper still hold, although with some minor differences.
Proceedings Papers
Reliably Re-Acting to Partner’s Actions with the Social Intrinsic Motivation of Transfer Empowerment
. isal2022, ALIFE 2022: The 2022 Conference on Artificial Life30, (July 18–22, 2022) 10.1162/isal_a_00512
Abstract
View Paper
PDF
We consider multi-agent reinforcement learning (MARL) for cooperative communication and coordination tasks. MARL agents can be brittle because they can overfit their training partners’ policies. This overfitting can produce agents that adopt policies that act under the expectation that other agents will act in a certain way rather than react to their actions. Our objective is to bias the learning process towards finding reactive strategies towards other agents’ behaviors. Our method, transfer empowerment, measures the potential influence between agents’ actions. Results from three simulated cooperation scenarios support our hypothesis that transfer empowerment improves MARL performance. We discuss how transfer empowerment could be a useful principle to guide multi-agent coordination by ensuring reactiveness to one’s partner.
Proceedings Papers
. ecal2017, ECAL 2017, the Fourteenth European Conference on Artificial Life360-367, (September 4–8, 2017) 10.1162/isal_a_061
Abstract
View Paper
PDF
Being able to measure time, whether directly or indirectly, is a significant advantage for an organism. It permits it to predict regular events, and prepare for them on time. Thus, clocks are ubiquitous in biology. In the present paper, we consider the most minimal abstract pure clocks and investigate their characteristics with respect to their ability to measure time. Amongst other, we find fundamentally diametral clock characteristics, such as oscillatory behaviour for local time measurement or decay-based clocks measuring time periods in scales global to the problem. We include also cascades of independent clocks (“clock bags”) and composite clocks with controlled dependency; the latter show various regimes of markedly different dynamics.
Proceedings Papers
. alif2016, ALIFE 2016, the Fifteenth International Conference on the Synthesis and Simulation of Living Systems704-711, (July 4–6, 2016) 10.1162/978-0-262-33936-0-ch112
Abstract
View Paper
PDF
The enactive AI framework wants to overcome the sense-making limitations of embodied AI by drawing on the bio-systemic foundations of enactive cognitive science. While embodied AI tries to ground meaning in sensorimotor interaction, enactive AI adds further requirements by grounding sensorimotor interaction in autonomous agency. At the core of this shift is the requirement for a truly intrinsic value function. We suggest that empowerment, an information-theoretic quantity based on an agents embodiment, represents such a function. We highlight the role of empowerment maximisation in satisfying the requirements of enactive AI, i.e. establishing constitutive autonomy and adaptivity, in detail. We then argue that empowerment, grounded in a precarious existence, allows an agent to enact a world based on the relevance of environmental features in respect to its own identity.
Proceedings Papers
. alife2014, ALIFE 14: The Fourteenth International Conference on the Synthesis and Simulation of Living Systems949-956, (July 30–August 2, 2014) 10.1162/978-0-262-32621-6-ch154
Proceedings Papers
. ecal2013, ECAL 2013: The Twelfth European Conference on Artificial Life118-125, (September 2–6, 2013) 10.1162/978-0-262-31709-2-ch018
Proceedings Papers
. ecal2011, ECAL 2011: The 11th European Conference on Artificial Life104, (August 8–12, 2011) 10.7551/978-0-262-29714-1-ch104