Related papers: Online Learning in Iterated Prisoner's Dilemma to …
Game theory formalizes certain interactions between physical particles or between living beings in biology, sociology, and economics, and quantifies the outcomes by payoffs. The prisoner's dilemma (PD) describes situations in which it is…
This paper investigates how natural language communication with an AI agent affects human cooperative behaviour in indefinitely repeated Prisoner's Dilemma games. We conduct a laboratory experiment (n = 126) with two between-subjects…
We study a modified prisoner's dilemma game taking place on two-dimensional disordered square lattices. The players are pure strategists and can either cooperate or defect with their immediate neighbors. In the generations each player…
Imitation learning algorithms learn a policy from demonstrations of expert behavior. We show that, for deterministic experts, imitation learning can be done by reduction to reinforcement learning with a stationary reward. Our theoretical…
Learning how to adapt to complex and dynamic environments is one of the most important factors that contribute to our intelligence. Endowing artificial agents with this ability is not a simple task, particularly in competitive scenarios. In…
Active learning agents typically employ a query selection algorithm which solely considers the agent's learning objectives. However, this may be insufficient in more realistic human domains. This work uses imitation learning to enable an…
Human behaviors are regularized by a variety of norms or regulations, either to maintain orders or to enhance social welfare. If artificially intelligent (AI) agents make decisions on behalf of human beings, we would hope they can also…
We investigate two paradigms for studying the evolution of cooperation--Prisoner's Dilemma and Snowdrift game in an online friendship network obtained from a social networking site. We demonstrate that such social network has small-world…
AI systems that learn through reward feedback about the actions they take are increasingly deployed in domains that have significant impact on our daily life. However, in many cases the online rewards should not be the only guiding…
We seek to align agent policy with human expert behavior in a reinforcement learning (RL) setting, without any prior knowledge about dynamics, reward function, and unsafe states. There is a human expert knowing the rewards and unsafe states…
In many online decision processes, the optimizing agent is called to choose between large numbers of alternatives with many inherent similarities; in turn, these similarities imply closely correlated losses that may confound standard…
The Multi-Armed Bandit problem provides a fundamental framework for analyzing the tension between exploration and exploitation in sequential learning. This paper explores Information Directed Sampling (IDS) policies, a class of heuristics…
Artificial behavioral agents are often evaluated based on their consistent behaviors and performance to take sequential actions in an environment to maximize some notion of cumulative reward. However, human decision making in real life…
This paper studies algorithmic decision-making under human's strategic behavior, where a decision maker uses an algorithm to make decisions about human agents, and the latter with information about the algorithm may exert effort…
The staggering feats of AI systems have brought to attention the topic of AI Alignment: aligning a "superintelligent" AI agent's actions with humanity's interests. Many existing frameworks/algorithms in alignment study the problem on a…
While advances in multi-agent learning have enabled the training of increasingly complex agents, most existing techniques produce a final policy that is not designed to adapt to a new partner's strategy. However, we would like our AI agents…
The paper studies the emergence and stability of cooperative behavior in populations of agents who interact among themselves in Prisoner's Dilemma games and who are allowed to choose their partners. The population is then subject to…
We present and study a partial-information model of online learning, where a decision maker repeatedly chooses from a finite set of actions, and observes some subset of the associated losses. This naturally models several situations where…
With the prospect of autonomous artificial intelligence (AI) agents, studying their tendency for cooperative behavior becomes an increasingly relevant topic. This study is inspired by the super-additive cooperation theory, where the…
Deep Reinforcement Learning has been shown to be very successful in complex games, e.g. Atari or Go. These games have clearly defined rules, and hence allow simulation. In many practical applications, however, interactions with the…