Learning Behaviorally Grounded State Representations for Reinforcement Learning Agents
نویسندگان
چکیده
The learning and reasoning capabilities of biological systems by far exceed those of robots and artificial agents. Part of this stems from their ability to efficiently learn behavioral skills and increasingly complex, symbolic representations that capture the important aspects of their environment. This paper presents an autonomous learning approach by which artificial reinforcement learning agents can acquire general symbolic state descriptions that are grounded in the agents’ functional capabilities and take the form of behavioral goals and affordances. This actionspecific vocabulary provides the agent with a means of representing the state of the world more concisely. Task-specific symbols are added to this vocabulary to construct an internal state space over which tasks can be represented as Markov Decision Processes. This learning framework is applied to feature-based mobile robot navigation and foraging.
منابع مشابه
Hierarchical Functional Concepts for Knowledge Transfer among Reinforcement Learning Agents
This article introduces the notions of functional space and concept as a way of knowledge representation and abstraction for Reinforcement Learning agents. These definitions are used as a tool of knowledge transfer among agents. The agents are assumed to be heterogeneous; they have different state spaces but share a same dynamic, reward and action space. In other words, the agents are assumed t...
متن کاملGrounding Hierarchical Reinforcement Learning Models for Knowledge Transfer
Methods of deep machine learning enable to to reuse low-level representations efficiently for generating more abstract high-level representations. Originally, deep learning has been applied passively (e.g., for classification purposes). Recently, it has been extended to estimate the value of actions for autonomous agents within the framework of reinforcement learning (RL). Explicit models of th...
متن کاملRelational Reinforcement Learning in Infinite Mario
Relational representations in reinforcement learning allow for the use of structural information like the presence of objects and relationships between them in the description of value functions. Through this paper, we show that such representations allow for the inclusion of background knowledge that qualitatively describes a state and can be used to design agents that demonstrate learning beh...
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 کاملMetric learning for reinforcement learning agents
A key component of any reinforcement learning algorithm is the underlying representation used by the agent. While reinforcement learning (RL) agents have typically relied on hand-coded state representations, there has been a growing interest in learning this representation. While inputs to an agent are typically fixed (i.e., state variables represent sensors on a robot), it is desirable to auto...
متن کامل