scholarly journals A Measure of Real-Time Intelligence

2013 ◽  
Vol 4 (1) ◽  
pp. 31-48 ◽  
Author(s):  
Vaibhav Gavane
Keyword(s):  
Reinforcement Learning ◽  
Computational Complexity ◽  
Parallel Processing ◽  
Real Time ◽  
Intelligence Test ◽  
Natural Manner ◽  
Learning Agents ◽  
Processing Capability ◽  
Theoretical Maximum ◽  
High Intelligence

Abstract We propose a new measure of intelligence for general reinforcement learning agents, based on the notion that an agent’s environment can change at any step of execution of the agent. That is, an agent is considered to be interacting with its environment in real-time. In this sense, the resulting intelligence measure is more general than the universal intelligence measure (Legg and Hutter, 2007) and the anytime universal intelligence test (Hernández-Orallo and Dowe, 2010). A major advantage of the measure is that an agent’s computational complexity is factored into the measure in a natural manner. We show that there exist agents with intelligence arbitrarily close to the theoretical maximum, and that the intelligence of agents depends on their parallel processing capability. We thus believe that the measure can provide a better evaluation of agents and guidance for building practical agents with high intelligence.

scholarly journals The Realization of Rapid Median Filter Algorithm on FPGA

2012 ◽  
Vol 6-7 ◽  
pp. 659-664
Author(s):  
En Shun Kang ◽  
Yu Xi Zhao
Keyword(s):  
Image Processing ◽  
Parallel Processing ◽  
Real Time ◽  
Processing Time ◽  
Median Filter ◽  
Processing System ◽  
Processing Capability ◽  
Real Time Image ◽  
High Level ◽  
Time Image

Traditional median filter algorithm has the long processing time, which goes against the real-time image processing. According to its shortcomings, this paper puts forward the rapid median filter algorithm, and uses DE2 board of the company called Altera to do the realization on FPGA (CycloneII 2C35). The experimental results show that the image pre-processing system is able to complete a variety of high-level image algorithms in milliseconds, and FPGA's parallel processing capability and pipeline operations can dramatically improve the speed of image processing, so the FPGA-based image processing system has broad prospects for development．

scholarly journals A Normative Supervisor for Reinforcement Learning Agents

2021 ◽  
pp. 565-576
Author(s):  
Emery Neufeld ◽  
Ezio Bartocci ◽  
Agata Ciabattoni ◽  
Guido Governatori
Keyword(s):  
Reinforcement Learning ◽  
Real Time ◽  
Deontic Logic ◽  
Theorem Prover ◽  
Event Recorder ◽  
Learning Agents ◽  
Learning Agent

AbstractWe introduce a modular and transparent approach for augmenting the ability of reinforcement learning agents to comply with a given norm base. The normative supervisor module functions as both an event recorder and real-time compliance checker w.r.t. an external norm base. We have implemented this module with a theorem prover for defeasible deontic logic, in a reinforcement learning agent that we task with playing a “vegan” version of the arcade game Pac-Man.

Training effective deep reinforcement learning agents for real-time life-cycle production optimization

2021 ◽  
pp. 109766
Author(s):  
Kai Zhang ◽  
Zhongzheng Wang ◽  
Guodong Chen ◽  
Liming Zhang ◽  
Yongfei Yang ◽  
...  
Keyword(s):  
Life Cycle ◽  
Reinforcement Learning ◽  
Real Time ◽  
Production Optimization ◽  
Learning Agents

scholarly journals Design of a Reinforcement Learning-Based Lane Keeping Planning Agent for Automated Vehicles

2020 ◽  
Vol 10 (20) ◽  
pp. 7171
Author(s):  
Bálint Kővári ◽  
Ferenc Hegedüs ◽  
Tamás Bécsi
Keyword(s):  
Reinforcement Learning ◽  
Real Time ◽  
Autonomous Vehicles ◽  
High Performance ◽  
Search Algorithm ◽  
Tree Search ◽  
Monte Carlo Tree Search ◽  
Learning Agents ◽  
Combined Solution ◽  
Lane Keeping

Reinforcement learning-based approaches are widely studied in the literature for solving different control tasks for Connected and Autonomous Vehicles, from which this paper deals with the problem of lateral control of a dynamic nonlinear vehicle model, performing the task of lane-keeping. In this area, the appropriate formulation of the goals and environment information is crucial, for which the research outlines the importance of lookahead information, enabling to accomplish maneuvers with complex trajectories. Another critical part is the real-time manner of the problem. On the one hand, optimization or search based methods, such as the presented Monte Carlo Tree Search method, can solve the problem with the trade-off of high numerical complexity. On the other hand, single Reinforcement Learning agents struggle to learn these tasks with high performance, though they have the advantage that after the training process, they can operate in a real-time manner. Two planning agent structures are proposed in the paper to resolve this duality, where the machine learning agents aid the tree search algorithm. As a result, the combined solution provides high performance and low computational needs.

Spatial Interpolators for Intra-Frame Resampling of SAR Videos: A Comparative Study Using Real-Time HD, Medical and Radar Data

2020 ◽  
Vol 15 (2) ◽  
pp. 144-196 ◽  
Author(s):  
Mohammad R. Khosravi ◽  
Sadegh Samadi ◽  
Reza Mohseni
Keyword(s):  
Computational Complexity ◽  
Real Time ◽  
Video Compression ◽  
Nearest Neighbor ◽  
Radar Data ◽  
Edge Preservation ◽  
Edge Information ◽  
Video Codecs ◽  
Comparative Results ◽  
Interesting Area

Background: Real-time video coding is a very interesting area of research with extensive applications into remote sensing and medical imaging. Many research works and multimedia standards for this purpose have been developed. Some processing ideas in the area are focused on second-step (additional) compression of videos coded by existing standards like MPEG 4.14. Materials and Methods: In this article, an evaluation of some techniques with different complexity orders for video compression problem is performed. All compared techniques are based on interpolation algorithms in spatial domain. In details, the acquired data is according to four different interpolators in terms of computational complexity including fixed weights quartered interpolation (FWQI) technique, Nearest Neighbor (NN), Bi-Linear (BL) and Cubic Cnvolution (CC) interpolators. They are used for the compression of some HD color videos in real-time applications, real frames of video synthetic aperture radar (video SAR or ViSAR) and a high resolution medical sample. Results: Comparative results are also described for three different metrics including two reference- based Quality Assessment (QA) measures and an edge preservation factor to achieve a general perception of various dimensions of the mentioned problem. Conclusion: Comparisons show that there is a decidable trade-off among video codecs in terms of more similarity to a reference, preserving high frequency edge information and having low computational complexity.

scholarly journals An Evaluation Methodology for Interactive Reinforcement Learning with Simulated Users

Biomimetics ◽  
2021 ◽  
Vol 6 (1) ◽  
pp. 13
Author(s):  
Adam Bignold ◽  
Francisco Cruz ◽  
Richard Dazeley ◽  
Peter Vamplew ◽  
Cameron Foale
Keyword(s):  
Reinforcement Learning ◽  
Information Source ◽  
Human Interaction ◽  
Evaluation Methodology ◽  
External Information ◽  
Preliminary Evaluation ◽  
Learning Agents ◽  
Learning Agent ◽  
Knowledge Bias ◽  
The Impact

Interactive reinforcement learning methods utilise an external information source to evaluate decisions and accelerate learning. Previous work has shown that human advice could significantly improve learning agents’ performance. When evaluating reinforcement learning algorithms, it is common to repeat experiments as parameters are altered or to gain a sufficient sample size. In this regard, to require human interaction every time an experiment is restarted is undesirable, particularly when the expense in doing so can be considerable. Additionally, reusing the same people for the experiment introduces bias, as they will learn the behaviour of the agent and the dynamics of the environment. This paper presents a methodology for evaluating interactive reinforcement learning agents by employing simulated users. Simulated users allow human knowledge, bias, and interaction to be simulated. The use of simulated users allows the development and testing of reinforcement learning agents, and can provide indicative results of agent performance under defined human constraints. While simulated users are no replacement for actual humans, they do offer an affordable and fast alternative for evaluative assisted agents. We introduce a method for performing a preliminary evaluation utilising simulated users to show how performance changes depending on the type of user assisting the agent. Moreover, we describe how human interaction may be simulated, and present an experiment illustrating the applicability of simulating users in evaluating agent performance when assisted by different types of trainers. Experimental results show that the use of this methodology allows for greater insight into the performance of interactive reinforcement learning agents when advised by different users. The use of simulated users with varying characteristics allows for evaluation of the impact of those characteristics on the behaviour of the learning agent.

Sign in / Sign up

Export Citation Format

Share Document