Explainable Reinforcement Learning via Rule Extraction in Complex Visual Environments

Explainable Reinforcement Learning via Rule Extraction in Complex Visual Environments

Abstract:

Deep neural networks have allowed for significant advances within the field of reinforcement learning and autonomous agents. However, in contrast to traditional approaches such as expert systems and hand-crafted control systems, deep neural networks introduce a large amount of ambiguity regarding the decision-making of an autonomous agent. Understanding the decision-making process of any autonomous agent is crucial for applications where trusted autonomy is not only paramount but required before an agent can be deployed. In this thesis, we focus on the following problems of explainability and rule extraction from autonomous agents. 1) How does the neural network architecture impact the performance and the explainability of an agent trained using reinforcement learning? 2) Can rules be defined and extracted from observations of an autonomous agent trained using reinforcement learning? 3) Can complex rules be derived from multiple partial observations of autonomous agents? For the first problem, we investigate the common neural network architectures used in reinforcement learning and how attention mechanisms have been used to improve performance in prior works. We devise a novel spatial temporal attention based approach that allows the agent to learn where it should focus its attention in contrast to previous works which favored constraining networks with guided attention mechanisms. For the second problem, we propose a formal definition of a rule for trajectories consisting of state and action pairs. We show that under this definition, rules are extractable using unsupervised learning techniques. Additionally, we investigate the impact of neural network design on an autonomous agent’s ability to learn rules. For the third problem, we introduce a novel method for multi-sequence-tosequence-based tasks that require visual induction and translation. This method allows us to observe multiple partial visual observations of an agent and extract the over-arching rule set that defines the agent’s behavior. We also show that this method is robust with respect to noisy signals.

Explainable Reinforcement Learning via Rule Extraction in Complex Visual Environments. get more COMPUTER SCIENCE PROJECT TOPICS AND MATERIALS

1. DESIGN AND IMPLEMENTATION OF A MULTILINGUAL CHAT APPLICATION

2. DESIGN AND IMPLEMENTATION OF AN ANDROID-BASED ONLINE CLEARANCE SYSTEM FOR GRADUATING STUDENTS

3. DESIGN AND IMPLEMENTATION OF STUDENT RATING OF TEACHER EFFECTIVENESS SYSTEM (A CASE STUDY OF NNAMDI AZIKIWE UNIVERSITY)

4. DESIGN AND IMPLEMENTATION OF A WEB-BASED TIMETABLE SYSTEM FOR THE COMPUTER SCIENCE DEPARTMENT

5. DESIGN AND IMPLEMENTATION OF APPOINTMENT MANAGEMENT SYSTEM (A CASE STUDY OF UNITHECH HOSPITAL)

Sharing is caring!