Multi-agent Relational Reinforcement Learning
نویسندگان
چکیده
In this paper we study Relational Reinforcement Learning in a multi-agent setting. There is growing evidence in the Reinforcement Learning research community that a relational representation of the state space has many benefits over a propositional one. Complex tasks as planning or information retrieval on the web can be represented more naturally in relational form. Yet, this relational structure has not been exploited for multi-agent reinforcement learning tasks and has only been studied in a single agent context so far. This paper is a first attempt in bridging the gap between Relation Reinforcement Learning (RRL) and Multi-agent Systems (MAS). More precisely, we will explore how a relational structure of the state space can be used in a Multi-Agent Reinforcement Learning context.
منابع مشابه
Multi-Agent Relational Reinforcement Learning Explorations in Multi-State Coordination Tasks
In this paper we report on using a relational state space in multi-agent reinforcement learning. There is growing evidence in the Reinforcement Learning research community that a relational representation of the state space has many benefits over a propositional one. Complex tasks as planning or information retrieval on the web can be represented more naturally in relational form. Yet, this rel...
متن کاملLearning with Whom to Communicate Using Relational Reinforcement Learning
Relational reinforcement learning is a promising direction within reinforcement learning research. It upgrades reinforcement learning techniques by using relational representations for states, actions, and learned value-functions or policies to allow natural representations and abstractions of complex tasks. Multiagent systems are characterized by their relational structure and present a good e...
متن کاملRelational Spatial Features in Reinforcement Learning of Multi-Agent Search Strategies
We address a partially observable twodimensional multi-pursuer evader searching task. Belief compression for each pursuer is achieved using spatial basis functions to obtain a set of relational features describing the uncertainty in the evader’s position. These features are used a inputs to a nonlinear parameterized policy that is optimized by direct search. A comparison is made between identic...
متن کاملRelational Reinforcement Learning for Agents in Worlds with Objects
In reinforcement learning, an agent tries to learn a policy, i.e., how to select an action in a given state of the environment, so that it maximizes the total amount of reward it receives when interacting with the environment. We argue that a relational representation of states is natural and useful when the environment is complex and involves many interrelated objects. Relational reinforcement...
متن کاملDistributed relational temporal difference learning
Relational representations have great potential for rapidly generalizing learned knowledge in large Markov decision processes such as multi-agent problems. In this work, we introduce relational temporal difference learning for the distributed case where the communication links among agents are dynamic. Thus no critical components of the system should reside in any one agent. Relational generali...
متن کامل