Normalizing flows for probabilistic modeling and inference
Normalizing flows provide a general mechanism for defining expressive probability
distributions, only requiring the specification of a (usually simple) base distribution and a …
distributions, only requiring the specification of a (usually simple) base distribution and a …
Goal-conditioned imitation learning
Y Ding, C Florensa, P Abbeel… - Advances in neural …, 2019 - proceedings.neurips.cc
Abstract Designing rewards for Reinforcement Learning (RL) is challenging because it
needs to convey the desired task, be efficient to optimize, and be easy to compute. The latter …
needs to convey the desired task, be efficient to optimize, and be easy to compute. The latter …
Coarse-to-fine imitation learning: Robot manipulation from a single demonstration
E Johns - 2021 IEEE international conference on robotics and …, 2021 - ieeexplore.ieee.org
We introduce a simple new method for visual imitation learning, which allows a novel robot
manipulation task to be learned from a single human demonstration, without requiring any …
manipulation task to be learned from a single human demonstration, without requiring any …
Deep generative models for offline policy learning: Tutorial, survey, and perspectives on future directions
Deep generative models (DGMs) have demonstrated great success across various domains,
particularly in generating texts, images, and videos using models trained from offline data …
particularly in generating texts, images, and videos using models trained from offline data …
Variational imitation learning with diverse-quality demonstrations
Learning from demonstrations can be challenging when the quality of demonstrations is
diverse, and even more so when the quality is unknown and there is no additional …
diverse, and even more so when the quality is unknown and there is no additional …
Intrinsic reward driven imitation learning via generative model
Imitation learning in a high-dimensional environment is challenging. Most inverse
reinforcement learning (IRL) methods fail to outperform the demonstrator in such a high …
reinforcement learning (IRL) methods fail to outperform the demonstrator in such a high …
A coupled flow approach to imitation learning
In reinforcement learning and imitation learning, an object of central importance is the state
distribution induced by the policy. It plays a crucial role in the policy gradient theorem, and …
distribution induced by the policy. It plays a crucial role in the policy gradient theorem, and …
Neural density estimation and likelihood-free inference
G Papamakarios - arXiv preprint arXiv:1910.13233, 2019 - arxiv.org
I consider two problems in machine learning and statistics: the problem of estimating the
joint probability density of a collection of random variables, known as density estimation, and …
joint probability density of a collection of random variables, known as density estimation, and …
Goal-aware generative adversarial imitation learning from imperfect demonstration for robotic cloth manipulation
Y Tsurumine, T Matsubara - Robotics and Autonomous Systems, 2022 - Elsevier
Abstract Generative Adversarial Imitation Learning (GAIL) can learn policies without
explicitly defining the reward function from demonstrations. GAIL has the potential to learn …
explicitly defining the reward function from demonstrations. GAIL has the potential to learn …
Forethought and hindsight in credit assignment
We address the problem of credit assignment in reinforcement learning and explore
fundamental questions regarding the way in which an agent can best use additional …
fundamental questions regarding the way in which an agent can best use additional …