Coordinate to cooperate or compete: Abstract goals and joint intentions in social interaction

By Max Kleiman-Weiner, Mark K. Ho, Joseph L. Austerweil, Michael L. Littman, Josh Tenenbaum. 2016

135 citations recorded by the source corpus.

Subfields: Cognitive Science & Psychology

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Cognitive Science & Psychology

Citations in the corpus

Multi-agent Reinforcement Learning in Sequential Social Dilemmas (2017, methodology): “In principle, this restriction could be dropped through the use of planning-based reinforcement learning methods like those of [24].”
Discovering Diverse Multi-Agent Strategic Behavior via Reward Randomization (2021, background): “In RL, there are works on learning when to cooperate/compete (Littman, 2001; Peysakhovich & Lerer, 2018a; Kleiman-Weiner et al., 2016; Woodward et al., 2019; McKee et al., 2020), which is a special case of ours, or learning robust policies (Li et al.”
Learning with Opponent-Learning Awareness (2017, neutral): “Outside of purely computational studies the emergence of cooperation and defection in RL settings has also been studied and compared to human data [20].”
Machine Theory of Mind (2018, background): “Such models will be important for value alignment (Hadﬁeld-Menell et al., 2016) and ﬂexible cooperation (Nowak, 2006; Kleiman-Weiner et al., 2016; Barrett et al., 2017; Kris Cao), and will likely be an ingredient in future machines’ ethical decision making (Churchland, 1996).”
A Unified Game-Theoretic Approach to Multiagent Reinforcement Learning (2017, background): “use adaptive learning rates [12], adjust the frequencies of updates [48, 81], or dynamically respond to the other agents actions online [63, 50].”
"Other-Play" for Zero-Shot Coordination (2020, background): “A central challenge for AI is constructing agents that can coordinate and cooperate with partners they have not seen before (Kleiman-Weiner et al., 2016; Lerer & Peysakhovich, 2017; Carroll et al., 2019; Shum et al., 2019).”
Modeling Others using Oneself in Multi-Agent Reinforcement Learning (2018, background): “Recent work in cognitive science attempts to understand human decision-making by using a hierarchical model of social agency that infers the intentions of other human agents in order to decide whether to play a cooperative or competitive strategy (Kleiman-Weiner et al., 2016).”
Arena: A General Evaluation Platform and Building Toolkit for Multi-Agent Intelligence (2019, background): “Many ideas have been raised to address such issues [10, 42, 43, 55, 72].”
Prosocial learning agents solve generalized Stag Hunts better than selfish ones (2017, background): “Understanding how to design human-machine hybrid systems in ways that properly account for human psychology (Crandall et al., 2017; Kleiman-Weiner et al., 2016; Rand et al., 2014; Hauser et al., 2014; Ouss and Peysakhovich, 2015; Arechar et al., 2016; Mao et al., 2017) and also human learning strate”
Maintaining cooperation in complex social dilemmas using deep reinforcement learning (2017, methodology): “Baker et al. (2009); Kleiman-Weiner et al. (2016)).”
Dark, Beyond Deep: A Paradigm Shift to Cognitive AI with Humanlike Common Sense (2020, background): “, cooperation and comptition) [362, 363] and faireness [364] can also be well explained.”
LEMMA: A Multi-view Dataset for Learning Multi-agent Multi-task Activities (2020, background): “As agents’ decision-making processes are deeply aﬀected by their unique social values, task scheduling is signiﬁcantly aﬀected by interactions ( e.g ., co-operation, competition, subordination) among multi-agents [30].”
Inequity aversion improves cooperation in intertemporal social dilemmas (2018, background): “planning [20, 21, 22, 23] to generate cooperation in this setting.”
Off-Belief Learning (2021, background): “In humans this ability is commonly described as theory of mind and a variety of experimental studies (Camerer et al., 2003; Agranov et al., 2012; Kleiman-Weiner et al., 2016) have shown that humans typically carry out a limited number of such reasoning steps, depending on the exact situation, even i”
Consequentialist conditional cooperation in social dilemmas with imperfect information (2017, background): “…A recent stream of research has taken a particular interest in social dilemmas, situations where individuals have incentives to act in ways that undermine socially optimal outcomes (Leibo et al. 2017), (Perolat et al. 2017), (Lerer and Peysakhovich 2017), (Kleiman-Weiner et al. 2016).”
A multi-agent reinforcement learning model of common-pool resource appropriation (2017, background): “This insight is widely applicable to other general-sum Markov games with mixed incentives (e.g. [19, 21]).”
Deep Reinforcement Learning for Multiagent Systems: A Review of Challenges, Solutions, and Applications (2018, methodology): “The DQN is utilized to characterize self-interested independent learning agents to find equilibria of the SSD, which cannot be solved by the standard evolution and learning methods used for MGSD [97].”