Skip to main navigation
Skip to search
Skip to main content
University of Birmingham Home
Help & FAQ
Home
Research output
Profiles
Research units
Projects
Activities
Datasets
Equipment
Prizes
Press/Media
Search by expertise, name or affiliation
Formal verification of deep reinforcement learning agents
Edoardo Bacci
Computer Science
Research output
:
Thesis
›
Doctoral Thesis
Overview
Fingerprint
Fingerprint
Dive into the research topics of 'Formal verification of deep reinforcement learning agents'. Together they form a unique fingerprint.
Sort by
Weight
Alphabetically
Keyphrases
Controller
100%
Formal Verification
100%
Reinforcement Learning Agent
100%
Deep Reinforcement Learning (deep RL)
100%
Uncertainty Sources
66%
Verification Method
33%
Under Uncertainty
16%
Control Task
16%
Actuator
16%
Infinite Horizon
16%
Number of Steps
16%
Competitive Environment
16%
Safety Concerns
16%
Specific Action
16%
Degree of Uncertainty
16%
Input Noise
16%
Abstract Interpretation
16%
Safety-critical
16%
Uncertain Environment
16%
Noise Sensor
16%
Adversary
16%
Partial Observability
16%
Benchmark Control Problem
16%
Trained Agent
16%
Imperfect Data
16%
Horizon Length
16%
Faulty Actuators
16%
Non-probabilistic Analysis
16%
Computer Science
Formal Verification
100%
Learning Agent
100%
Deep Reinforcement Learning
100%
Actuator
100%
Abstract Interpretation
50%
Probabilistic Analysis
50%
Partial Observability
50%
Competitive Environment
50%
Hardware Problem
50%