36 citations · 112 across the 14 of their papers we have counts for
7 papers · 1 filter
Follow the Object: Curriculum Learning for Manipulation Tasks with Imagined Goals
Ozsel Kilinc, Giovanni Montana
Learning robot manipulation through deep reinforcement learning in environments with sparse rewards is a challenging task. In this paper we address this problem by introducing a no…
Reinforcement Learning for Robotic Manipulation using Simulated Locomotion Demonstrations
Ozsel Kilinc, Giovanni Montana
Mastering robotic manipulation skills through reinforcement learning (RL) typically requires the design of shaped reward functions. Recent developments in this area have demonstrat…
Multi-agent Deep Reinforcement Learning with Extremely Noisy Observations
Ozsel Kilinc, Giovanni Montana
Multi-agent reinforcement learning systems aim to provide interacting agents with the ability to collaboratively learn and adapt to the behaviour of other agents. In many real-worl…
Learning Latent Representations in Neural Networks for Clustering through Pseudo Supervision and Graph-based Activity Regularization
Ozsel Kilinc, Ismail Uysal
In this paper, we propose a novel unsupervised clustering approach exploiting the hidden information that is indirectly introduced through a pseudo classification objective. Specif…
GAR: An efficient and scalable Graph-based Activity Regularization for semi-supervised learning
Ozsel Kilinc, Ismail Uysal
In this paper, we propose a novel graph-based approach for semi-supervised learning problems, which considers an adaptive adjacency of the examples throughout the unsupervised port…
Clustering-based Source-aware Assessment of True Robustness for Learning Models
Ozsel Kilinc, Ismail Uysal
We introduce a novel validation framework to measure the true robustness of learning models for real-world applications by creating source-inclusive and source-exclusive partitions…
Auto-clustering Output Layer: Automatic Learning of Latent Annotations in Neural Networks
Ozsel Kilinc, Ismail Uysal
In this paper, we discuss a different type of semi-supervised setting: a coarse level of labeling is available for all observations but the model has to learn a fine level of laten…