Edgar A. Duénez-Guzmán
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Edgar A. Duénez-Guzmán has a total of 12 co-authors. Here are the top co-authors by number of shared publications:
- Alexander Sasha Vezhnevets
DeepMind, London EC4A 3TW, UKwww.jzleibo.com
2 shared publications - Joel Z. Leibo
King's College London
2 shared publications - John P. Agapiou
DeepMind, London EC4A 3TW, UKwww.jzleibo.com
2 shared publications - Andrea Tacchetti
XTX Markets London DeepMind London DeepMind London DeepMind London DeepMind London DeepMind London DeepMind London United Kingdom
1 shared publication - David Balduzzi
XTX Markets London DeepMind London DeepMind London DeepMind London DeepMind London DeepMind London DeepMind London United Kingdom
1 shared publication - Ian Gemp
XTX Markets London DeepMind London DeepMind London DeepMind London DeepMind London DeepMind London DeepMind London United Kingdom
1 shared publication
Latest Publications
- 10 November 2022
- Published by Cambridge University Press (CUP) in Behavioral and Brain Sciences
- Vol. 45, e261
What is the simplest model that can account for high-fidelity imitation?
What inductive biases must be incorporated into multi-agent artificial intelligence models to get them to capture high-fidelity imitation? We think very little is needed. In the right environments, both instrumental- and ritual-stance imitation can emerge from generic learning mechanisms operating on non-deliberative decision architectures. In this view, imitation emerges from trial-and-error learning and does not require explicit deliberation.
- 10 November 2022
- Published by Cambridge University Press (CUP) in Behavioral and Brain Sciences
- Vol. 45, e261
What is the simplest model that can account for high-fidelity imitation?
What inductive biases must be incorporated into multi-agent artificial intelligence models to get them to capture high-fidelity imitation? We think very little is needed. In the right environments, both instrumental- and ritual-stance imitation can emerge from generic learning mechanisms operating on non-deliberative decision architectures. In this view, imitation emerges from trial-and-error learning and does not require explicit deliberation.
- 7 July 2022
- Published by Cambridge University Press (CUP) in Behavioral and Brain Sciences
- Vol. 45, 34-35
Learning agents that acquire representations of social groups
Humans are learning agents that acquire social group representations from experience. Here, we discuss how to construct artificial agents capable of this feat. One approach, based on deep reinforcement learning, allows the necessary representations to self-organize. This minimizes the need for hand-engineering, improving robustness and scalability. It also enables “virtual neuroscience” research on the learned representations.
- 7 July 2022
- Published by Cambridge University Press (CUP) in Behavioral and Brain Sciences
- Vol. 45, 34-35
Learning agents that acquire representations of social groups
Humans are learning agents that acquire social group representations from experience. Here, we discuss how to construct artificial agents capable of this feat. One approach, based on deep reinforcement learning, allows the necessary representations to self-organize. This minimizes the need for hand-engineering, improving robustness and scalability. It also enables “virtual neuroscience” research on the learned representations.
- Open Access
D3C: Reducing the Price of Anarchy in Multi-Agent Learning
In multiagent systems, the complex interaction of fixed incentives can lead agents to outcomes that are poor (inefficient) not only for the group, but also for each individual. Price of anarchy is a technical, game-theoretic definition that quantifies the inefficiency arising in these scenarios -- it compares the welfare that can be achieved through perfect coordination against that achieved by self-interested agents at a Nash equilibrium. We derive a differentiable, upper bound on a price of anarchy that agents can cheaply estimate during learning. Equipped with this estimator, agents can adjust their incentives in a way that improves the efficiency incurred at a Nash equilibrium. Agents do so by learning to mix their reward (equiv. negative loss) with that of other agents by following the gradient of our derived upper bound. We refer to this approach as D3C. In the case where agent incentives are differentiable, D3C resembles the celebrated Win-Stay, Lose-Shift strategy from behavioral game theory, thereby establishing a connection between the global goal of maximum welfare and an established agent-centric learning rule. In the non-differentiable setting, as is common in multiagent reinforcement learning, we show the upper bound can be reduced via evolutionary strategies, until a compromise is reached in a distributed fashion. We demonstrate that D3C improves outcomes for each agent and the group as a whole on several social dilemmas including a traffic network exhibiting Braess's paradox, a prisoner's dilemma, and several multiagent domains.
Open AccessD3C: Reducing the Price of Anarchy in Multi-Agent Learning
In multiagent systems, the complex interaction of fixed incentives can lead agents to outcomes that are poor (inefficient) not only for the group, but also for each individual. Price of anarchy is a technical, game-theoretic definition that quantifies the inefficiency arising in these scenarios -- it compares the welfare that can be achieved through perfect coordination against that achieved by self-interested agents at a Nash equilibrium. We derive a differentiable, upper bound on a price of anarchy that agents can cheaply estimate during learning. Equipped with this estimator, agents can adjust their incentives in a way that improves the efficiency incurred at a Nash equilibrium. Agents do so by learning to mix their reward (equiv. negative loss) with that of other agents by following the gradient of our derived upper bound. We refer to this approach as D3C. In the case where agent incentives are differentiable, D3C resembles the celebrated Win-Stay, Lose-Shift strategy from behavioral game theory, thereby establishing a connection between the global goal of maximum welfare and an established agent-centric learning rule. In the non-differentiable setting, as is common in multiagent reinforcement learning, we show the upper bound can be reduced via evolutionary strategies, until a compromise is reached in a distributed fashion. We demonstrate that D3C improves outcomes for each agent and the group as a whole on several social dilemmas including a traffic network exhibiting Braess's paradox, a prisoner's dilemma, and several multiagent domains.