Bayesian role discovery for multi-agent reinforcement learning
نویسندگان
چکیده
In this paper we develop a Bayesian policy search approach for Multi-Agent RL (MARL), which is model-free and allows for priors on policy parameters. We present a novel optimization algorithm based on hybrid MCMC, which leverages both the prior and gradient information estimated from trajectories. Our experiments demonstrate the automatic discovery of roles through reinforcement learning in a real-time strategy game.
منابع مشابه
Bayesian Policy Search for Multi-Agent Role Discovery
Bayesian inference is an appealing approach for leveraging prior knowledge in reinforcement learning (RL). In this paper we describe an algorithm for discovering different classes of roles for agents via Bayesian inference. In particular, we develop a Bayesian policy search approach for Multi-Agent RL (MARL), which is model-free and allows for priors on policy parameters. We present a novel opt...
متن کاملLearning and Transferring Roles in Multi-Agent Reinforcement
Many real-world domains contain multiple agents that play distinct roles in achieving an overall mission. For instance, in tactical battle scenarios, a tank fulfills a much different role than a foot soldier. When learning an overall multi-agent strategy, it is clearly advantageous to have knowledge of the agent roles and the typical behavioral characteristics associated with each role. The goa...
متن کاملA Bayesian Approach to Imitation in Reinforcement Learning
In multiagent environments, forms of social learning such as teaching and imitation have been shown to aid the transfer of knowledge from experts to learners in reinforcement learning (RL). We recast the problem of imitation in a Bayesian framework. Our Bayesian imitation model allows a learner to smoothly pool prior knowledge, data obtained through interaction with the environment, and informa...
متن کاملMulti-Task Reinforcement Learning Using Hierarchical Bayesian Models
For this project, the objective was to build a working implementation of a multi-task reinforcement learning (MTRL) agent using a hierarchical Bayesian model (HBM) framework described in the paper “Multitask reinforcement learning: A hierarchical Bayesian approach” (Wilson, et al. 2007). This agent was then to play a modified version of the game of Pacman. In this version of the classic arcade ...
متن کاملReinforcement Learning with Action Discovery
The design of reinforcement learning solutions to many problems artificially constrain the action set available to an agent, in order to limit the exploration/sample complexity. While exploring, if an agent can discover new actions that can break through the constraints of its basic/atomic action set, then the quality of the learned decision policy could improve. On the flipside, considering al...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
عنوان ژورنال:
دوره شماره
صفحات -
تاریخ انتشار 2010