Parallel Fault Tolerant Multi-Agent Reinforcement Learning
نویسنده
چکیده
Reinforcement learning is a powerful tool for training an agent in a sequential decision based environment and has been successful in many simulated [6] as well as practical [5] domains. In this paper we investigate methods of strengthening the rate of convergence of a single agent RL learner by sharing observations with other independent agents. In contrast to multi-agent reinforcement methods that investigate cooperative learning between agents using a shared policy [4], this paper is instead interested in agent’s that learn independently and share observations through periodic, asynchronous message passing. In addition to the goal of increasing optimal policy convergence, we investigate methods of fault tolerance in the parallel multi-agent RL framework where multiple adversarial agents may attempt to hinder the learning of the other agents.
منابع مشابه
Fault-Tolerant Multi-Agent Exact Belief Propagation
Multiply sectioned Bayesian networks (MSBNs) support multiagent probabilistic inference in distributed large problem domains, where agents (subdomains) are organized by a tree structure (called hypertree). In earlier work, all belief updating methods on a hypertree are made of two rounds of propagation, each of which is implemented as a recursive process. Both processes need to be started from ...
متن کاملAdaptive load balancing of parallel applications with multi-agent reinforcement learning on heterogeneous systems
We report on the improvements that can be achieved by applying machine learning techniques, in particular reinforcement learning, for the dynamic load balancing of parallel applications. The applications being considered here are coarse grain data intensive applications. Such applications put high pressure on the interconnect of the hardware. Synchronization and load balancing in complex, heter...
متن کاملMulti-Task Coalition Parallel Formation Strategy Based on Reinforcement Learning
Agent coalition is an important manner of agents’ coordination and cooperation. Forming a coalition, agents can enhance their ability to solve problems and obtain more utility. In this paper, a novel multi-task coalition parallel formation strategy is presented, and the conclusion that the process of multi-task coalition formation is a Markov Decision Process is testified theoretically. Moreove...
متن کاملUsing Sliding Mode Controller and Eligibility Traces for Controlling the Blood Glucose in Diabetic Patients at the Presence of Fault
Some people suffering from diabetes use insulin injection pumps to control the blood glucose level. Sometimes, the fault may occur in the sensor or actuator of these pumps. The main objective of this paper is controlling the blood glucose level at the desired level and fault-tolerant control of these injection pumps. To this end, the eligibility traces algorithm is combined with the sliding mod...
متن کاملDistributed Adaptive Fault-Tolerant Control of Uncertain Multi-Agent Systems
This paper presents an adaptive fault-tolerant control (FTC) scheme for a class of nonlinear uncertain multi-agent systems. A local FTC scheme is designed for each agent using local measurements and suitable information exchanged between neighboring agents. Each local FTC scheme consists of a fault diagnosis module and a reconfigurable controller module comprised of a baseline controller and tw...
متن کامل