ADVANTAGES OF UNPREDICTABLE MULTIAGENT SYSTEMS: RANDOMIZED POLICIES FOR SINGLE AGENTS AND AGENT-TEAMS by
نویسندگان
چکیده
ADVANTAGES OF UNPREDICTABLE MULTIAGENT SYSTEMS: RANDOMIZED POLICIES FOR SINGLE AGENTS AND AGENT-TEAMS In adversarial settings, action randomization can effectively deteriorate an opponent’s capability to predict and exploit an agent’s or an agent team’s policies. Unfortunately, little attention has been paid to intentional randomization of agents’ policies in single-agent or decentralized (PO)MDPs (without sacrificing rewards or breaking down coordination). This thesis provides two key contributions to remedy this situation. First, it provides novel algorithms, one based on a non-linear program and one on a linear program (LP), to randomize single-agent policies, while attaining a certain level of reward. Second, it provides RDR, a new algorithm that efficiently generates randomized policies for decentralized POMDPs via the single-agent LP method. ADVANTAGES OF UNPREDICTABLE MULTIAGENT SYSTEMS: RANDOMIZED POLICIES FOR SINGLE AGENTS AND AGENT-TEAMS
منابع مشابه
Coordinating Randomized Policies for Increasing Security in Multiagent Systems
Despite significant recent advances in decision theoretic frameworks for reasoning about multiagent teams, little attention has been paid to applying such frameworks in adversarial domains, where the agent team may face security threats from other agents. This paper focuses on domains where such threats are caused by unseen adversaries whose actions or payoffs are unknown. In such domains, acti...
متن کاملIncreasing Security through Communication and Policy Randomization in Multiagent Systems
Despite significant recent advances in decision theoretic frameworks for reasoning about multiagent teams, little attention has been paid to applying such frameworks in adversarial domains, where the agent team may face security threats from other agents. This paper focuses on domains where such threats are caused by unseen adversaries whose actions or payoffs are unknown. In such domains, acti...
متن کاملScalable multiagent learning through indirect encoding of policy geometry
Multiagent systems present many challenging, real-world problems to artificial intelligence. Because it is difficult to engineer the behaviors of multiple cooperating agents by hand, multiagent learning has become a popular approach to their design. While there are a variety of traditional approaches to multiagent learning, many suffer from increased computational costs for large teams and the ...
متن کاملA Multiagent Reinforcement Learning algorithm to solve the Community Detection Problem
Community detection is a challenging optimization problem that consists of searching for communities that belong to a network under the assumption that the nodes of the same community share properties that enable the detection of new characteristics or functional relationships in the network. Although there are many algorithms developed for community detection, most of them are unsuitable when ...
متن کاملExecution-time Communication Decisions for Coordination of Multi-agent Teams
MULTI-AGENT teams can be used to perform tasks that would be very difficult or impossible for single agents. Although such teams provide additional functionality and robustness over single-agent systems, they also present additional challenges, mainly due to the difficulty of coordinating multiple agents in the presence of uncertainty and partial observability. Agents in a multi-agent team must...
متن کامل