Spatio-temporal graph transformer networks for pedestrian trajectory prediction
Understanding crowd motion dynamics is critical to real-world applications, eg, surveillance
systems and autonomous driving. This is challenging because it requires effectively …
systems and autonomous driving. This is challenging because it requires effectively …
Visual language integration: A survey and open challenges
SM Park, YG Kim - Computer Science Review, 2023 - Elsevier
With the recent development of deep learning technology comes the wide use of artificial
intelligence (AI) models in various domains. AI shows good performance for definite …
intelligence (AI) models in various domains. AI shows good performance for definite …
Differentiable particle filtering via entropy-regularized optimal transport
A Corenflos, J Thornton… - International …, 2021 - proceedings.mlr.press
Particle Filtering (PF) methods are an established class of procedures for performing
inference in non-linear state-space models. Resampling is a key ingredient of PF necessary …
inference in non-linear state-space models. Resampling is a key ingredient of PF necessary …
Differentiable slam-net: Learning particle slam for visual navigation
Simultaneous localization and mapping (SLAM) remains challenging for a number of
downstream applications, such as visual robot navigation, because of rapid turns …
downstream applications, such as visual robot navigation, because of rapid turns …
An overview of differentiable particle filters for data-adaptive sequential Bayesian inference
By approximating posterior distributions with weighted samples, particle filters (PFs) provide
an efficient mechanism for solving non-linear sequential state estimation problems. While …
an efficient mechanism for solving non-linear sequential state estimation problems. While …
Dreaming: Model-based reinforcement learning by latent imagination without reconstruction
M Okada, T Taniguchi - 2021 ieee international conference on …, 2021 - ieeexplore.ieee.org
In the present paper, we propose a decoder-free extension of Dreamer, a leading model-
based reinforcement learning (MBRL) method from pixels. Dreamer is a sample-and cost …
based reinforcement learning (MBRL) method from pixels. Dreamer is a sample-and cost …
Learning latent dynamics for autonomous shape control of deformable object
In recent years, the methods of loading and transporting rigid objects have become more
and more perfect. However, in the process of transportation, the shape control of deformable …
and more perfect. However, in the process of transportation, the shape control of deformable …
Deep transformer q-networks for partially observable reinforcement learning
Real-world reinforcement learning tasks often involve some form of partial observability
where the observations only give a partial or noisy view of the true state of the world. Such …
where the observations only give a partial or noisy view of the true state of the world. Such …
Recurrent off-policy baselines for memory-based continuous control
Z Yang, H Nguyen - arXiv preprint arXiv:2110.12628, 2021 - arxiv.org
When the environment is partially observable (PO), a deep reinforcement learning (RL)
agent must learn a suitable temporal representation of the entire history in addition to a …
agent must learn a suitable temporal representation of the entire history in addition to a …
Recurrent model-free rl is a strong baseline for many pomdps
Many problems in RL, such as meta RL, robust RL, and generalization in RL can be cast as
POMDPs. In theory, simply augmenting model-free RL with memory, such as recurrent …
POMDPs. In theory, simply augmenting model-free RL with memory, such as recurrent …