1 code implementation • NeurIPS 2023 • Zhijing Jin, Yuen Chen, Felix Leeb, Luigi Gresele, Ojasv Kamal, Zhiheng Lyu, Kevin Blin, Fernando Gonzalez Adauto, Max Kleiman-Weiner, Mrinmaya Sachan, Bernhard Schölkopf
Much of the existing work in natural language processing (NLP) focuses on evaluating commonsense causal reasoning in LLMs, thus failing to assess whether a model can perform causal inference in accordance with a set of well-defined formal rules.
no code implementations • 29 Jan 2022 • Mingwei Ma, Jizhou Liu, Samuel Sokota, Max Kleiman-Weiner, Jakob Foerster
An unaddressed challenge in multi-agent coordination is to enable AI agents to exploit the semantic relationships between the features of actions and the features of observations.
no code implementations • 19 Jan 2022 • Edmond Awad, Sydney Levine, Andrea Loreggia, Nicholas Mattei, Iyad Rahwan, Francesca Rossi, Kartik Talamadupula, Joshua Tenenbaum, Max Kleiman-Weiner
We can invent novel rules on the fly.
no code implementations • 29 Sep 2021 • Mingwei Ma, Jizhou Liu, Samuel Sokota, Max Kleiman-Weiner, Jakob Nicolaus Foerster
An unaddressed challenge in zero-shot coordination is to take advantage of the semantic relationship between the features of an action and the features of observations.
no code implementations • 3 Jun 2021 • Stephanie Stacy, Chenfei Li, Minglu Zhao, Yiling Yun, Qingyi Zhao, Max Kleiman-Weiner, Tao Gao
We propose a computational account of overloaded signaling from a shared agency perspective which we call the Imagined We for Communication.
1 code implementation • 26 Mar 2020 • Rose E. Wang, Sarah A. Wu, James A. Evans, Joshua B. Tenenbaum, David C. Parkes, Max Kleiman-Weiner
Underlying the human ability to collaborate is theory-of-mind, the ability to infer the hidden mental states that drive others to act.
1 code implementation • NeurIPS 2019 • Jack Serrino, Max Kleiman-Weiner, David C. Parkes, Joshua B. Tenenbaum
Here we develop the DeepRole algorithm, a multi-agent reinforcement learning agent that we test on The Resistance: Avalon, the most popular hidden role game.
no code implementations • 18 Jan 2019 • Michael Shum, Max Kleiman-Weiner, Michael L. Littman, Joshua B. Tenenbaum
This representation is grounded in the formalism of stochastic games and multi-agent reinforcement learning.
no code implementations • 13 Oct 2018 • Joseph Y. Halpern, Max Kleiman-Weiner
We provide formal definitions of degree of blameworthiness and intention relative to an epistemic state (a probability over causal models and a utility function on outcomes).
1 code implementation • NeurIPS 2018 • DJ Strouse, Max Kleiman-Weiner, Josh Tenenbaum, Matt Botvinick, David Schwab
We show how to optimize these regularizers in a way that is easy to integrate with policy gradient reinforcement learning.
Multi-agent Reinforcement Learning reinforcement-learning +1
no code implementations • 19 Mar 2018 • Edmond Awad, Sydney Levine, Max Kleiman-Weiner, Sohan Dsouza, Joshua B. Tenenbaum, Azim Shariff, Jean-François Bonnefon, Iyad Rahwan
However, when both drivers make errors in cases of shared control between a human and a machine, the blame and responsibility attributed to the machine is reduced.
no code implementations • 12 Jan 2018 • Richard Kim, Max Kleiman-Weiner, Andres Abeliuk, Edmond Awad, Sohan Dsouza, Josh Tenenbaum, Iyad Rahwan
We introduce a new computational model of moral decision making, drawing on a recent theory of commonsense moral learning via social dynamics.