15.04.202114:30-15:00Zhenhui Zhou, M.Sc. Thesis Defense: Approximate Policy Search in Black Box Optimization
15.04.202114:00-14:30Franziska Herbert, B.Sc. Thesis Defense: Using Multimodal Human Feedback for Reinforcement Learning
8.04.202114:30-15:00Jianhang He, M.Sc. Thesis Defense: Imitation Learning using Energy Based Models
8.04.202114:00-14:30Jonas Eschmann, M.Sc. Thesis Defense: Partially Unsupervised Deep Meta Reinforcement Learning
1.04.202114:00-15:00Pascal Klink, Research Talk: Global Optimization in Machine Learning Applications
25.03.202114:30-14:45Jule Brendgen, M.Sc. Intermediate Presentation: The Relation between Social Interaction And Intrinsic Motivation in Reinforcement Learning
25.03.202114:00-14:30Yug Ajmera, M.Sc. Intermediate Presentation: Learning Movement Primitives for Handshaking Behaviours
18.03.202114:00-14:15Haoyi Yang, M.Sc. Intermediate Presentation: Variational Inference for Curriculum Reinforcement Learning
11.03.202115:00-15:30Gabriele Libardi, Invited Talk: Guided Exploration with Proximal Policy Optimization using a Single Demonstration
11.03.202114:00-15:00Julen Urain, Research Talk: Imitation Flows
4.03.202115:00-15:30Marius Zoeller, B.Sc. Thesis Defense: Graph Networks
4.03.202114:30-15:00Moritz Andres, B.Sc. Intermediate Presentation: Person Recognition via Videodata and Audiodata
4.03.202114:00-14:30Kay Hansel, M.Sc. Intermediate Presentation: Probabilistic Dynamic Mode Primitives
25.02.202114:00-15:00Michael Lutter, Research Talk: Inductive Biases for Robot Learning
18.02.202114:15-14:30Yanhua Zhang, M.Sc. Intermediate Presentation: Memory Representations for Partially Observable Reinforcement Learning
18.02.202114:00-14:15Franziska Herbert, B.Sc. Intermediate Presentation: Using Multimodal Human Feedback for Reinforcement Learning
11.02.202114:15-14:30Lanmiao Liu, M.Sc. Intermediate Presentation: Gestures Density Models
11.02.202114:00-14:15Hanyu Sun, M.Sc. Intermediate Presentation: Action Recognition
4.02.202114:30-15:00Janosch Moos, M.Sc. Thesis Defense: Approximate Variational Inference for Mixture Models
4.02.202114:00-14:30Jan Rathjens, M.Sc. Thesis Defense: Accelerated Policy Search
28.01.202115:00-15:15Jianhang He, M.Sc. Intermediate Presentation: Imitation Learning using Energy-Based Model
28.01.202114:00-15:00Claudio Zito (TII), Invited Talk: Feature-Based Transfer Learning for Robotic Push Manipulation
14.01.202114:30-14:45Zhenhui Zhou, M.Sc. Intermediate Presentation: Multi Modal Policy Search using Normalizing Flow
14.01.202114:00-14:30David Rother, M.Sc. Intermediate Presentation: Reinforcement Learning in Decentralized Multi-Goal Multi-Agent Settings
7.01.202114:00-14:30Felix Helfenstein, B.Sc. Thesis Defense: Benchmarking Deep Reinforcement Learning Algorithms
21.12.202016:30-18:00Samuele Tosatto, Ph.D. Thesis Defense: Reinforcement Learning for Robotics
17.12.202015:00-16:00Matthew Gombolay (Georgia Tech), Invited Talk: Democratizing Robot Learning for Human-Robot Teaming
17.12.202014:30-15:00Jonas Eschmann, M.Sc. Intermediate Presentation: Partially Supervised Deep Meta Reinforcement Learning for Sim2Real Transfer
17.12.202014:00-14:30Janosch Moos, M.Sc. Intermediate Presentation: Approximate Variational Inference for Mixture Models
10.12.202015:00-15:20Axel Patzwahl, M.Sc. Intermediate presentation: Multi-sensor Fusion for Target Motion Prediction with an Application to Robot Baseball
10.12.202014:30-15:00Fabian Damken, B.Sc. Thesis Defense: Variational Autoenconders for Koopman Dynamical Systems
10.12.202014:00-14:30Moritz Schramm, B.Sc. Thesis Defense: Development of an Interactive Gesture Recognition System for an Assistive Robot
8.12.202015:30-18:00Roberto Lampariello, Ph.D. Thesis Defense: Optimal Motion Planning for Object Interception and Grasping
3.12.202015:30-17:30Daniel Tanneberg, Ph.D. Thesis Defense: Understand-Compute-Adapt: Neural Networks for Intelligent Agents
3.12.202011:30-12:30Mario Zanon (IMT Lucca), Invited Talk at MPI-IS-EI: Reinforcement Learning based on Model Predictive Control
26.11.202014:30-15:00Rustam Galljamov, M.Sc. Thesis Defense: Sample-efficient learning-based controller for bipedal walking in robotic systems
26.11.202014:00-14:30Albert Schotschneider, M.Sc. Thesis Defense: Learning High-Level Behavior for Autonomous Vehicles
20.11.202013:00-13:30Maximilian Stasica, M.Sc. Thesis Defense: Comparison of human motor control models and their application to robotics
19.11.202015:00-15:30Tim Dorau, M.Sc. Thesis Defense: Distributionally Robust Optimization for Optimal Control
19.11.202014:00-15:00Zico Kolter (CMU), Invited Talk: Equilibrium approaches to deep learning: One (implicit) layer is all you need,
12.11.202015:00-16:00Nathan Ratliff (NVIDIA), Invited Talk: Geometric fabrics: Transparent tools for behavior engineering
5.11.202014:00-15:00Emtiyaz Khan (RIKEN AIP), Invited Talk: Bayesian Principles for Learning Machines
29.10.202014:00-15:00Gergely Neu (UPF), Invited Talk: Logistic Q-Learning
22.10.202014:00-14:15Moritz Schramm, B.Sc. Intermediate Presentation: Development of an Interactive Gesture Recognition System for an Assistive Robot
20.10.202011:00-12:00Martin Pecka, Research Talk: Safe Autonomous Reinforcement Learning
15.10.202014:15-14:30Mark Baierl, B.Sc. Thesis Defense: Learning action representations for primitives-based Humanoid control
15.10.202014:00-14:15Erik Samstag, B.Sc. Thesis Defense: Bayesian Optimization for Biochemical Dose Response Measurements
1.10.202014:30-15:00Patrick Krabbe, M.Sc. Thesis Defense: Learning Riemannian Movement Primitives for Manipulation
1.10.202014:00-14:30Okan Koc (Amazon), Invited Talk: Safe Learning Control: What is out there and what is not?
23.09.202010:00-11:00Oleg Arenz, Ph.D. Thesis Defense: Sample-Efficient I-Projections for Robot Learning
22.09.202011:30-12:00Jia-Jie Zhu, Research Talk: Robust Learning Meets Robust Optimization -- Introduction to Distributionally Robust OptimizationLink on request
17.09.202016:30-17:00Thomas Lautenschläger, M.Sc. Thesis Defense: Variational Inference For Switching Dynamics
17.09.202016:00-16:30Alexander Klein, M.Sc. Thesis Defense: Learning Robot Grasping of Industrial Work Pieces using Dense Object Descriptors
17.09.202015:00-16:00Marc Toussaint (TU Berlin), Invited Talk: Learning to do as planned
10.09.202015:00-15:30Markus Semmler, M.Sc. Thesis Defense: Sequential Bayesian Optimal Experimental Design
10.09.202014:00-15:00Michael Gienger (Honda Research Institute), Invited Talk: Dexterous Cooperation
3.09.202014:45-15:30Oleg Arenz, Research Talk: Sample-Efficient I-Projections for Robot Learning
3.09.202014:00-14:45Simon Guist, Research Talk: Hindsight State Manipulation
27.08.202014:00-14:45Guilherme Maeda (Preferred Networks), Invited Talk: Phase portraits as movement primitives for fast humanoid robot control
20.08.202015:00-16:00Stephen Tu (Google Brain), Invited Talk: Learning Stability Certificates from Data
20.08.202014:30-14:45Jan Rathjens, M.Sc. Intermediate Presentation: Accelerated Policy Search
13.08.202017:30-18:15Abdeslam Boularias (Rutgers U), Invited Talk: Model Identification for Robotic Manipulation
13.08.202014:45-15:00Fabian Damken, B.Sc. Intermediate Presentation: Variational Autoenconders for Koopman Dynamical Systems
13.08.202014:30-14:45Mark Baierl, B.Sc. Intermediate Presentation: Learning action representations for primitives-based Humanoid control
13.08.202014:00-14:30Janosch Moos, Kay Hansel, Honor Thesis Defense: Survey on Robust Reinforcement Learning
6.08.202014:45-15:30Tuan Dam, Research Talk: Convex Regularization in Monte-Carlo Tree Search
6.08.202014:00-14:45Andras Kupcsik (BCAI), Invited Talk: Fast Learning and Sequencing of Object-centric Robot Manipulation Skills
30.07.202014:45-15:15Rustam Galljamov, M.Sc. Intermediate Presentation: Sample-efficient learning-based controller for bipedal walking in robotic systems
30.07.202014:00-14:45Takayuki Osa (Kyushu U), Invited Talk: Motion Planning by Learning Latent Representations
28.07.202011:00-12:00Max Welling (Uni Amsterdam), Invited Talk: Graph Nets and Equivariance: The Next Generation
23.07.202014:00-14:30Eike Mentzendorff, M.Sc. Thesis Defense: Multi-Objective Deep Reinforcement Learning through Manifold Optimization
16.07.202014:00-14:30Johannes Silberbauer, M.Sc. Thesis Defense: A Differentiable Newton Euler Algorithm for Multi-body Model Learning
15.07.202014:00-16:00IP Intermediate Presentation's Zoom Meeting 0alFVaGIwQT09
9.07.202014:00-14:45Jens Kober (TU Delft), Invited Talk: Robots Learning [Through] Interactions
2.07.202014:00-14:30Claas Voelcker, Honor Thesis Defense: Sequential Monte Carlo Input Inference for Control
25.06.202014:45-15:15Vini Marconie Tengang, M.Sc. Thesis Defense: 3D Pose Estimation for Robot Mikado
25.06.202014:00-14:45Philip Becker-Ehmck, Research Talk: Deep Onboard Quadcopter Control via Model-Based Reinforcement Learning
18.06.202017:45-18:30Simon Guist, Research Talk: Hindsight State Manipulation
18.06.202017:00-17:45Roberto Calandra (Facebook), Invited Talk: Rethinking Model-based Reinforcement Learning
18.06.202016:00-17:00Yijiang Huang (MIT), Invited Talk: Scalable and Probabilistically Complete Planning for Robotic Spatial Extrusion
11.06.202015:30-16:00Qin Li, Research Talk: Human Motion Prediction Based on Graph Convolutional Network
11.06.202015:00-15:30Stephane Tekam, M.Sc. Thesis defense: Policy Optimization via Gaussian Mixture Model
11.06.202014:00-15:00Herke van Hoof (UVA), Invited Talk: Learning heuristics for combinatorial optimization
4.06.202014:00-14:30Yang Weng (U. Tokyo), Invited Talk: Reinforcement Learning Based Underwater Wireless Optical Communication Alignment for Multiple Autonomous Underwater Vehicles
28.05.202014:00-14:45Christoph Zimmer (BCAI), Invited Talk: Safe active learning for time series modeling with gaussian processes


zum Seitenanfang