no code implementations • 24 Apr 2024 • Hakan Aktas, Yukie Nagai, Minoru Asada, Erhan Oztop, Emre Ugur
As a theoretical lens, affordances bridge the gap between effect and action, providing a nuanced understanding of the connections between agents' actions on entities and the effect of these actions.
no code implementations • 6 Mar 2024 • Suzan Ece Ada, Hanne Say, Emre Ugur, Erhan Oztop
In an attempt to exemplify such a development by inspiring how humans acquire knowledge and transfer skills among tasks, we introduce a novel multi-task reinforcement learning framework named Episodic Return Progress with Bidirectional Progressive Neural Networks (ERP-BPNN).
no code implementations • 20 Oct 2023 • Hakan Aktas, Yukie Nagai, Minoru Asada, Erhan Oztop, Emre Ugur
To be specific, besides robots with similar morphologies with different degrees of freedom, we show that a fixed-based manipulator robot with joint control and a differential drive mobile robot can be addressed within the proposed framework.
no code implementations • 2 Sep 2023 • Alper Ahmetoglu, Batuhan Celik, Erhan Oztop, Emre Ugur
We compare the performance of our proposed architecture with state-of-the-art symbol discovery methods in a simulated tabletop environment where the robot needs to discover symbols related to the relative positions of objects to predict the observed effect successfully.
no code implementations • 10 Jul 2023 • Suzan Ece Ada, Erhan Oztop, Emre Ugur
In contrast to behavior cloning, which assumes the data is collected from expert demonstrations, offline RL can work with non-expert data and multimodal behavior policies.
no code implementations • 18 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.
1 code implementation • 4 Dec 2020 • Alper Ahmetoglu, M. Yunus Seker, Justus Piater, Erhan Oztop, Emre Ugur
We propose a novel general method that finds action-grounded, discrete object and effect categories and builds probabilistic rules over them for non-trivial action planning.
no code implementations • 6 Jul 2020 • Erhan Oztop, Minoru Asada
In this report, we show that all n-variable Boolean function can be represented as polynomial threshold functions (PTF) with at most $0. 75 \times 2^n$ non-zero integer coefficients and give an upper bound on the absolute value of these coefficients.
no code implementations • 25 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).
no code implementations • 26 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.
no code implementations • 5 Apr 2015 • Can Eren Sezener, Erhan Oztop
In this paper we present several heuristic algorithms, including a Genetic Algorithm (GA), for obtaining polynomial threshold function (PTF) representations of Boolean functions (BFs) with small number of monomials.