| Type of Material: | Thesis |
| Title: | Improving robustness of deep reinforcement learning systems |
| Researcher: | Gupta, Surbhi |
| Guide: | Singal, Gaurav | Garg, Deepak |
| Department: | School of Computer Science Engineering and Technology |
| Publisher: | Bennett University |
| Place: | Greater Noida |
| Year: | 2021 |
| Language: | English |
| Subject: | Computer Science | Computer Science Information Systems | Engineering and Technology | Reinforcement Learning | Computer Science and Information Technology | Engineering and Technology |
| Dissertation/Thesis Note: | PhD; School of Computer Science Engineering and Technology, Bennett University, Greater Noida; 2021 |
| Fulltext: | Shodhganga |
| 003 | IN-AhILN | |
| 005 | 2026-10-12 17:59:05 | |
| 008 | __ | 261012t2021||||ii#||||g|m||||||||||eng|| |
| 035 | __ | |a(IN-AhILN)th_464116 |
| 040 | __ | |dIN-AhILN|aBENN_201310 |
| 041 | __ | |aeng |
| 100 | __ | |eResearcher|aGupta, Surbhi |
| 110 | __ | |aSchool of Computer Science Engineering and Technology|0U-0890|dGreater Noida|bBennett University|ein |
| 245 | __ | |aImproving robustness of deep reinforcement learning systems |
| 260 | __ | |aGreater Noida|c2021|bBennett University |
| 300 | __ | |dDVD |
| 502 | __ | |d2021|bPhD|cSchool of Computer Science Engineering and Technology, Bennett University, Greater Noida |
| 518 | __ | |d2021|oDate of Award |
| 518 | __ | |d2017|oDate of Registration |
| 518 | __ | |d2021|oDate of Completion |
| 520 | __ | |aReinforcement Learning (RL), a branch of machine learning, is used to solve problems that cannot be dealt with supervised and unsupervised learning techniques. In RL, the actor interacts with the environment and learns by getting a reward signal in a trial-and-error fashion. Reinforcement learning is scaled to deep reinforcement learning (DRL) to handle huge state or action space-based problems. In DRL, deep learning models are used for approximation, auto feature extraction, and generalisation across unvisited states and unexplored actions. Though deep reinforcement learning models are generalisable, they may perform catastrophic actions due to noise in the environment or the perceived state. Incorporating robustness to DRL models is of great importance as when these models are deployed to the real systems, may cause irrelevant behaviour due to noisy scenario. Hence, it would cause hardware damage with increased cost and decreased reliability. This thesis presents a study on deep reinforcement learning tha |
| 650 | __ | |aComputer Science and Information Technology|2UGC |
| 650 | __ | |aEngineering and Technology|2AIU |
| 653 | __ | |aComputer Science |
| 653 | __ | |aComputer Science Information Systems |
| 653 | __ | |aEngineering and Technology |
| 653 | __ | |aReinforcement Learning |
| 700 | __ | |aSingal, Gaurav|eGuide |
| 700 | __ | |aGarg, Deepak|eGuide |
| 856 | __ | |uhttp://shodhganga.inflibnet.ac.in/handle/10603/363195|yShodhganga |
| 905 | __ | |afromsg |
User Feedback Comes Under This section.