Results 11 to 20 of about 5,721,941 (348)
End-to-End Driving Via Conditional Imitation Learning [PDF]
IEEE International Conference on Robotics and Automation, 2018 Deep networks trained on demonstrations of human driving have learned to follow roads and avoid obstacles. However, driving policies trained via imitation learning cannot be controlled at test time.
Felipe Codevilla +4 more
openalex +3 more sources
Bridging Offline Reinforcement Learning and Imitation Learning: A Tale of Pessimism [PDF]
IEEE Transactions on Information Theory, 2021 Offline reinforcement learning (RL) algorithms seek to learn an optimal policy from a fixed dataset without active data collection. Based on the composition of the offline dataset, two main methods are used: imitation learning which is suitable for ...
Paria Rashidinejad +4 more
semanticscholar +1 more source
A Survey of Imitation Learning: Algorithms, Recent Developments, and Challenges [PDF]
IEEE Transactions on Cybernetics, 2023 In recent years, the development of robotics and artificial intelligence (AI) systems has been nothing short of remarkable. As these systems continue to evolve, they are being utilized in increasingly complex and unstructured environments, such as ...
Maryam Zare +3 more
semanticscholar +1 more source
MimicPlay: Long-Horizon Imitation Learning by Watching Human Play [PDF]
Conference on Robot Learning, 2023 Imitation learning from human demonstrations is a promising paradigm for teaching robots manipulation skills in the real world. However, learning complex long-horizon tasks often requires an unattainable amount of demonstrations.
Chen Wang +7 more
semanticscholar +1 more source
Goal-Conditioned Imitation Learning using Score-based Diffusion Policies [PDF]
Robotics: Science and Systems, 2023 We propose a new policy representation based on score-based diffusion models (SDMs). We apply our new policy representation in the domain of Goal-Conditioned Imitation Learning (GCIL) to learn general-purpose goal-specified policies from large uncurated ...
Moritz Reuss +3 more
semanticscholar +1 more source
Small Object Detection via Coarse-to-fine Proposal Generation and Imitation Learning [PDF]
IEEE International Conference on Computer Vision, 2023 The past few years have witnessed the immense success of object detection, while current excellent detectors struggle on tackling size-limited instances.
Xiang Yuan +4 more
semanticscholar +1 more source
Waypoint-Based Imitation Learning for Robotic Manipulation [PDF]
Conference on Robot Learning, 2023 While imitation learning methods have seen a resurgent interest for robotic manipulation, the well-known problem of compounding errors continues to afflict behavioral cloning (BC).
Lu Shi +3 more
semanticscholar +1 more source
Deep Imitation Learning for Humanoid Loco-manipulation Through Human Teleoperation [PDF]
IEEE-RAS International Conference on Humanoid Robots, 2023 We tackle the problem of developing humanoid loco-manipulation skills with deep imitation learning. The difficulty of collecting task demonstrations and training policies for humanoids with a high degree of freedom presents substantial challenges.
Mingyo Seo +6 more
semanticscholar +1 more source
HYDRA: Hybrid Robot Actions for Imitation Learning [PDF]
Conference on Robot Learning, 2023 Imitation Learning (IL) is a sample efficient paradigm for robot learning using expert demonstrations. However, policies learned through IL suffer from state distribution shift at test time, due to compounding errors in action prediction which lead to ...
Suneel Belkhale +2 more
semanticscholar +1 more source
imitation: Clean Imitation Learning Implementations
, 2022 imitation provides open-source implementations of imitation and reward learning algorithms in PyTorch. We include three inverse reinforcement learning (IRL) algorithms, three imitation learning algorithms and a preference comparison algorithm. The implementations have been benchmarked against previous results, and automated tests cover 98% of the code.
Gleave, Adam +9 more
openaire +2 more sources