In an ablation study, we show the benefits of the two-stage model for single time step prediction and the effectiveness of the mixed-horizon model for long-term prediction tasks.
For multiple modes, we suggest to learn local latent representations of motion trajectories with a density estimation method based on real-valued non-volume preserving (RealNVP) transformations that provides a set of powerful, stably invertible, and learnable transformations.
For this reason, effect prediction and parameter estimation with pushing actions have been heavily investigated in the literature.
In typical MBRL, we cannot expect the data-driven model to generate accurate and reliable policies to the intended robotic tasks during the learning process due to sample scarcity.
The first, Graph Networks (GN) based approach, considers explicitly defined edge attributes and not only does it consistently underperform an auto-encoder baseline that we modified to predict future states, our results indicate how different edge attributes can significantly influence the predictions.
To address this issue, we develop a model-agnostic noise regularization method for CDE that adds random perturbations to the data during training.
Finally, we demonstrate that our approach is able to match the asymptotic performance of model-free methods while requiring significantly less experience.
We release two artificial datasets, Simulated Flying Shapes and Simulated Planar Manipulator that allow to test the learning ability of video processing systems.
We present a novel deep neural network architecture for representing robot experiences in an episodic-like memory which facilitates encoding, recalling, and predicting action experiences.
Combining parameter noise with traditional RL methods allows to combine the best of both worlds.
We evaluate our approach on 2, 846 human whole-body motions and 6, 187 natural language descriptions thereof from the KIT Motion-Language Dataset.
Linking human motion and natural language is of great interest for the generation of semantic representations of human activities as well as for the generation of robot activities based on natural language input.
The result indicate that the new programming model together with the extensions within the application layer, makes them highly adaptable; leading to better quality in the results obtained.