16 Publikationen
-
2024 | Zeitschriftenaufsatz | Veröffentlicht | PUB-ID: 2988533Face Generation and Editing With StyleGAN: A SurveyPUB | PDF | DOI
Melnik, Andrew, Face Generation and Editing With StyleGAN: A Survey. IEEE Transactions on Pattern Analysis and Machine Intelligence 46 (5). , 2024 -
2021 | Zeitschriftenaufsatz | Veröffentlicht | PUB-ID: 2958662Decentralized control and local information for robust and adaptive decentralized Deep Reinforcement LearningPUB | DOI | Download (ext.) | WoS | PubMed | Europe PMC
Schilling, Malte, Decentralized control and local information for robust and adaptive decentralized Deep Reinforcement Learning. Neural Networks 144 (). , 2021 -
2021 | Zeitschriftenaufsatz | Veröffentlicht | PUB-ID: 2956099Using Tactile Sensing to Improve the Sample Efficiency and Performance of Deep Deterministic Policy Gradients for Simulated In-Hand Manipulation TasksPUB | PDF | DOI | Download (ext.) | WoS | PubMed | Europe PMC
Melnik, Andrew, Using Tactile Sensing to Improve the Sample Efficiency and Performance of Deep Deterministic Policy Gradients for Simulated In-Hand Manipulation Tasks. Frontiers in Robotics and AI 8 (). , 2021 -
2020 | Preprint | PUB-ID: 2948844Solving Physics Puzzles by Reasoning about PathsPUB | Download (ext.) | arXiv
Harter, Augustin, Solving Physics Puzzles by Reasoning about Paths. arXiv:2011.07357 (). , 2020 -
2020 | Konferenzbeitrag | PUB-ID: 2945886Learn to Move Through a Combination of Policy Gradient Algorithms: DDPG, D4PG, and TD3PUB | PDF
Bach, Nicolas, Learn to Move Through a Combination of Policy Gradient Algorithms: DDPG, D4PG, and TD3. 6th International Conference, LOD 2020, Siena, Italy, Proceedings (). , 2020 -
2020 | Konferenzbeitrag | PUB-ID: 2945884An error-based addressing architecture for dynamic model learningPUB | PDF
Bach, Nicolas, An error-based addressing architecture for dynamic model learning. 6th International Conference, LOD 2020, Siena, Italy, Proceedings (). , 2020 -
2019 | Zeitschriftenaufsatz | PUB-ID: 2937519Multisensory Assisted In-hand Manipulation of Objects with a Dexterous HandPUB | PDF
Korthals, Timo, Multisensory Assisted In-hand Manipulation of Objects with a Dexterous Hand. 2019 IEEE International Conference on Robotics and Automation Workshop on Integrating Vision and Touch for Multimodal and Cross-modal Perception, (ViTac) 2019, Montreal, CA, May 20-25, 2019 (). , 2019 -
2019 | Zeitschriftenaufsatz | PUB-ID: 2937517Biologically-Inspired Deep Reinforcement Learning of Modular Control for a Six-Legged RobotPUB | PDF
Konen, Kai, Biologically-Inspired Deep Reinforcement Learning of Modular Control for a Six-Legged Robot. 2019 IEEE International Conference on Robotics and Automation Workshop on Learning Legged Locomotion Workshop, (ICRA) 2019, Montreal, CA, May 20-25, 2019 (). , 2019 -
2019 | Konferenzbeitrag | Veröffentlicht | PUB-ID: 2939836Combining Causal Modelling and Deep Reinforcement Learning for Autonomous Agents in MinecraftPUB | Download (ext.)
Melnik, Andrew, Combining Causal Modelling and Deep Reinforcement Learning for Autonomous Agents in Minecraft. (). , 2019 -
2019 | Konferenzbeitrag | PUB-ID: 2937521Jointly Trained Variational Autoencoder for Multi-Modal Sensor FusionPUB | PDF
Korthals, Timo, Jointly Trained Variational Autoencoder for Multi-Modal Sensor Fusion. 22st International Conference on Information Fusion, (FUSION) 2019, Ottawa, CA, July 2-5, 2019 (). , 2019 -
2019 | Konferenzbeitrag | PUB-ID: 2933988Modularization of End-to-End Learning: Case Study in Arcade GamesPUB | arXiv
Melnik, Andrew, Modularization of End-to-End Learning: Case Study in Arcade Games. 32nd Conference on Neural Information Processing Systems (NeurIPS 2018), Workshop on Causal Learning (). , 2019 -
2018 | Zeitschriftenaufsatz | Veröffentlicht | PUB-ID: 2932767The World as an External Memory. The Price of Saccades in a Sensorimotor TaskPUB | DOI | Download (ext.) | WoS | PubMed | Europe PMC
Melnik, Andrew, The World as an External Memory. The Price of Saccades in a Sensorimotor Task. FRONTIERS IN BEHAVIORAL NEUROSCIENCE 12 (). , 2018 -
2018 | Konferenzbeitrag | Veröffentlicht | PUB-ID: 2940661Learning to Run challenge solutions: Adapting reinforcement learning methods for neuromusculoskeletal environmentsPUB | Download (ext.) | arXiv
Kidziński, Łukasz, Learning to Run challenge solutions: Adapting reinforcement learning methods for neuromusculoskeletal environments. (). , 2018 -
2018 | Konferenzbeitrag | Veröffentlicht | PUB-ID: 2934190An Approach to Hierarchical Deep Reinforcement Learning for a Decentralized Walking Control ArchitecturePUB | DOI
Schilling, Malte, An Approach to Hierarchical Deep Reinforcement Learning for a Decentralized Walking Control Architecture. Biologically Inspired Cognitive Architectures 2018. Proceedings of the Ninth Annual Meeting of the BICA Society 848 (). Cham, 2018 -
2017 | Zeitschriftenaufsatz | Veröffentlicht | PUB-ID: 2940668Systems, Subjects, Sessions: To What Extent Do These Factors Influence EEG Data?PUB | DOI | Download (ext.) | WoS | PubMed | Europe PMC
Melnik, Andrew, Systems, Subjects, Sessions: To What Extent Do These Factors Influence EEG Data?. Frontiers in Human Neuroscience 11 (). , 2017 -
2017 | Zeitschriftenaufsatz | Veröffentlicht | PUB-ID: 2940669EEG correlates of sensorimotor processing: independent components involved in sensory and motor processingPUB | DOI | Download (ext.) | WoS | PubMed | Europe PMC
Melnik, Andrew, EEG correlates of sensorimotor processing: independent components involved in sensory and motor processing. Scientific Reports 7 (1). , 2017