Reaching pareto-optimality in prisoner’s dilemma using conditional joint action learning

By Dipyaman Banerjee, Sandip Sen. 2007

65 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Safety Research, Sociology and Political Science

How researchers see this paper

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

In Artificial Intelligence

In Safety Research

In Sociology and Political Science

Citations in the corpus

Learning with Opponent-Learning Awareness (2017, background): “Seminal work includes the family of WoLF algorithms (Bowling and Veloso, 2002), which achieve convergence by using different learning rates depending on whether an agent is winning or losing, Joint-action-learners, (Claus and Boutilier, 1998; Banerjee and Sen, 2007) and friend-or-foe learning (Littm”
Learning to cooperate in multi-agent social dilemmas (2006, background): “in [5, 1 ]. Thus, an agent’s experience at any stage game is characterized not only by its own action and payoff but also from all the actions actually executed by the agents in the environment h ai,a i, rii . The main steps of Q-learning are reported in Algorithm 1.”
Comparative evaluation of MAL algorithms in a diverse set of ad hoc team problems (2012, background): “First, we note that most MAL algorithms (e.g. [ 1,3,5,6,8,14,17,23,32]) were primarily evaluated in homogeneous groups of agents, meaning that all agents in the group were identical, and all agents were a priori aware of this fact.”
Learning to compete, coordinate, and cooperate in repeated games using reinforcement learning (2011, unknown): “CJAL (Banerjee and Sen 2007) N = 400, = 0”
Autonomous agents modelling other agents: A comprehensive survey and open problems (2017, background): “For instance, Sen and Arora [240] and Banerjee and Sen [28] propose agents that learn the action frequencies of other agents conditioned on the modelling agent’s own action, and Davison and Hirsh [85] propose a user model which learns conditional probabilities of user commands based on the user’s pr”