Search Results for author: Emre Ugur

Found 9 papers, 3 papers with code

High-level Features for Resource Economy and Fast Learning in Skill Transfer

no code implementations18 Jun 2021 Alper Ahmetoglu, Emre Ugur, Minoru Asada, Erhan Oztop

To be concrete, in our simulation experiments, we either apply principal component analysis (PCA) or slow feature analysis (SFA) on the signals collected from the last hidden layer of a deep network while it performs a source task, and use these features for skill transfer in a new target task.

Decision Making

Object and Relation Centric Representations for Push Effect Prediction

no code implementations3 Feb 2021 Ahmet E. Tekden, Aykut Erdem, Erkut Erdem, Tamim Asfour, Emre Ugur

For this reason, effect prediction and parameter estimation with pushing actions have been heavily investigated in the literature.

DeepSym: Deep Symbol Generation and Rule Learning from Unsupervised Continuous Robot Interaction for Planning

1 code implementation4 Dec 2020 Alper Ahmetoglu, M. Yunus Seker, Justus Piater, Erhan Oztop, Emre Ugur

Our system is verified in a physics-based 3d simulation environment where a robot arm-hand system learned symbols that can be interpreted as 'rollable', 'insertable', 'larger-than' from its push and stack actions; and generated effective plans to achieve goals such as building towers from given cubes, balls, and cups using off-the-shelf probabilistic planners.

Reward Conditioned Neural Movement Primitives for Population Based Variational Policy Optimization

1 code implementation9 Nov 2020 M. Tuluhan Akbulut, Utku Bozdogan, Ahmet Tekden, Emre Ugur

For this, the experience of the robot, which can be bootstrapped from demonstrated trajectories, is used to train a novel Neural Processes-based deep network that samples from its latent space and generates the required trajectories given desired rewards.

Variational Inference

Time Perception: A Review on Psychological, Computational and Robotic Models

no code implementations23 Jul 2020 Hamit Basgol, Inci Ayhan, Emre Ugur

Firstly, we introduce a brief background from the psychology and neuroscience literature, covering the characteristics and models of time perception and related abilities.

Decision Making

ACNMP: Skill Transfer and Task Extrapolation through Learning from Demonstration and Reinforcement Learning via Representation Sharing

no code implementations25 Mar 2020 M. Tuluhan Akbulut, Erhan Oztop, M. Yunus Seker, Honghu Xue, Ahmet E. Tekden, Emre Ugur

To equip robots with dexterous skills, an effective approach is to first transfer the desired skill via Learning from Demonstration (LfD), then let the robot improve it by self-exploration via Reinforcement Learning (RL).

Belief Regulated Dual Propagation Nets for Learning Action Effects on Articulated Multi-Part Objects

1 code implementation9 Sep 2019 Ahmet E. Tekden, Aykut Erdem, Erkut Erdem, Mert Imre, M. Yunus Seker, Emre Ugur

In this paper, we introduce Belief Regulated Dual Propagation Networks (BRDPN), a general purpose learnable physics engine, which enables a robot to predict the effects of its actions in scenes containing groups of articulated multi-part objects.


Generalization in Transfer Learning

no code implementations3 Sep 2019 Suzan Ece Ada, Emre Ugur, H. Levent Akin

Furthermore, we increase the generalization capacity in widely used transfer learning benchmarks by using maximum entropy regularization, different critic methods, and curriculum learning in an adversarial setup.

Continuous Control Curriculum Learning +1

Symbol Emergence in Cognitive Developmental Systems: a Survey

no code implementations26 Jan 2018 Tadahiro Taniguchi, Emre Ugur, Matej Hoffmann, Lorenzo Jamone, Takayuki Nagai, Benjamin Rosman, Toshihiko Matsuka, Naoto Iwahashi, Erhan Oztop, Justus Piater, Florentin Wörgötter

However, the symbol grounding problem was originally posed to connect symbolic AI and sensorimotor information and did not consider many interdisciplinary phenomena in human communication and dynamic symbol systems in our society, which semiotics considered.

Cannot find the paper you are looking for? You can Submit a new open access paper.