Matches in SemOpenAlex for { <https://semopenalex.org/work/W2904154061> ?p ?o ?g. }
Showing items 1 to 72 of
72
with 100 items per page.
- W2904154061 abstract "Deep reinforcement learning (deep RL) has achieved superior performance in complex sequential tasks by learning directly from image input. A deep neural network is used as a function approximator and requires no specific state information. However, one drawback of using only images as input is that this approach requires a prohibitively large amount of training time and data for the model to learn the state feature representation and approach reasonable performance. This is not feasible in real-world applications, especially when the data are expansive and training phase could introduce disasters that affect human safety. In this work, we use a human demonstration approach to speed up training for learning features and use the resulting pre-trained model to replace the neural network in the deep RL Deep Q-Network (DQN), followed by human interaction to further refine the model. We empirically evaluate our approach by using only a human demonstration model and modified DQN with human demonstration model included in the Microsoft AirSim car simulator. Our results show that (1) pre-training with human demonstration in a supervised learning approach is better and much faster at discovering features than DQN alone, (2) initializing the DQN with a pre-trained model provides a significant improvement in training time and performance even with limited human demonstration, and (3) providing the ability for humans to supply suggestions during DQN training can speed up the network's convergence on an optimal policy, as well as allow it to learn more complex policies that are harder to discover by random exploration." @default.
- W2904154061 created "2018-12-22" @default.
- W2904154061 creator A5019383629 @default.
- W2904154061 creator A5032507644 @default.
- W2904154061 date "2018-07-01" @default.
- W2904154061 modified "2023-10-03" @default.
- W2904154061 title "Parallelized Interactive Machine Learning on Autonomous Vehicles" @default.
- W2904154061 cites W1522301498 @default.
- W2904154061 cites W1623881903 @default.
- W2904154061 cites W1986014385 @default.
- W2904154061 cites W2121863487 @default.
- W2904154061 cites W2145339207 @default.
- W2904154061 cites W2149933564 @default.
- W2904154061 cites W2257979135 @default.
- W2904154061 cites W2290874868 @default.
- W2904154061 cites W2342840547 @default.
- W2904154061 cites W2606321545 @default.
- W2904154061 cites W2607198029 @default.
- W2904154061 cites W2615547864 @default.
- W2904154061 cites W2619240030 @default.
- W2904154061 cites W2626804490 @default.
- W2904154061 cites W2788862220 @default.
- W2904154061 cites W2962938178 @default.
- W2904154061 doi "https://doi.org/10.1109/naecon.2018.8556776" @default.
- W2904154061 hasPublicationYear "2018" @default.
- W2904154061 type Work @default.
- W2904154061 sameAs 2904154061 @default.
- W2904154061 citedByCount "0" @default.
- W2904154061 crossrefType "proceedings-article" @default.
- W2904154061 hasAuthorship W2904154061A5019383629 @default.
- W2904154061 hasAuthorship W2904154061A5032507644 @default.
- W2904154061 hasBestOaLocation W29041540612 @default.
- W2904154061 hasConcept C108583219 @default.
- W2904154061 hasConcept C114466953 @default.
- W2904154061 hasConcept C119857082 @default.
- W2904154061 hasConcept C138885662 @default.
- W2904154061 hasConcept C154945302 @default.
- W2904154061 hasConcept C199360897 @default.
- W2904154061 hasConcept C2776401178 @default.
- W2904154061 hasConcept C41008148 @default.
- W2904154061 hasConcept C41895202 @default.
- W2904154061 hasConcept C50644808 @default.
- W2904154061 hasConcept C97541855 @default.
- W2904154061 hasConceptScore W2904154061C108583219 @default.
- W2904154061 hasConceptScore W2904154061C114466953 @default.
- W2904154061 hasConceptScore W2904154061C119857082 @default.
- W2904154061 hasConceptScore W2904154061C138885662 @default.
- W2904154061 hasConceptScore W2904154061C154945302 @default.
- W2904154061 hasConceptScore W2904154061C199360897 @default.
- W2904154061 hasConceptScore W2904154061C2776401178 @default.
- W2904154061 hasConceptScore W2904154061C41008148 @default.
- W2904154061 hasConceptScore W2904154061C41895202 @default.
- W2904154061 hasConceptScore W2904154061C50644808 @default.
- W2904154061 hasConceptScore W2904154061C97541855 @default.
- W2904154061 hasLocation W29041540611 @default.
- W2904154061 hasLocation W29041540612 @default.
- W2904154061 hasOpenAccess W2904154061 @default.
- W2904154061 hasPrimaryLocation W29041540611 @default.
- W2904154061 hasRelatedWork W2795261237 @default.
- W2904154061 hasRelatedWork W3014300295 @default.
- W2904154061 hasRelatedWork W3164822677 @default.
- W2904154061 hasRelatedWork W4223943233 @default.
- W2904154061 hasRelatedWork W4225161397 @default.
- W2904154061 hasRelatedWork W4312200629 @default.
- W2904154061 hasRelatedWork W4360585206 @default.
- W2904154061 hasRelatedWork W4364306694 @default.
- W2904154061 hasRelatedWork W4380075502 @default.
- W2904154061 hasRelatedWork W4380086463 @default.
- W2904154061 isParatext "false" @default.
- W2904154061 isRetracted "false" @default.
- W2904154061 magId "2904154061" @default.
- W2904154061 workType "article" @default.