Erhan Oztop

Suzan Ece Ada, Erhan Oztop, Emre Ugur

Offline Reinforcement Learning (RL) methods leverage previous experiences to learn better policies than the behavior policy used for data collection. However, they face challenges handling distribution shifts due to the lack of online interaction during training. To this end, we propose a novel method named State Reconstruction for Diffusion Policies (SRDP) that incorporates state reconstruction feature learning in the recent class of diffusion policies to address the problem of out-of-distribution (OOD) generalization. Our method promotes learning of generalizable state representation to alleviate the distribution shift caused by OOD states. To illustrate the OOD generalization and faster convergence of SRDP, we design a novel 2D Multimodal Contextual Bandit environment and realize it on a 6-DoF real-world UR10 robot, as well as in simulation, and compare its performance with prior algorithms. In particular, we show the importance of the proposed state reconstruction via ablation studies. In addition, we assess the performance of our model on standard continuous control benchmarks (D4RL), namely the navigation of an 8-DoF ant and forward locomotion of half-cheetah, hopper, and walker2d, achieving state-of-the-art results. Finally, we demonstrate that our method can achieve 167% improvement over the competing baseline on a sparse continuous control navigation task where various regions of the state space are removed from the offline RL dataset, including the region encapsulating the goal.

Hakan Aktas, Yukie Nagai, Minoru Asada et al.

We observe a large variety of robots in terms of their bodies, sensors, and actuators. Given the commonalities in the skill sets, teaching each skill to each different robot independently is inefficient and not scalable when the large variety in the robotic landscape is considered. If we can learn the correspondences between the sensorimotor spaces of different robots, we can expect a skill that is learned in one robot can be more directly and easily transferred to other robots. In this paper, we propose a method to learn correspondences among two or more robots that may have different morphologies. 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. To set up the correspondence among the robots considered, an initial base task is demonstrated to the robots to achieve the same goal. Then, a common latent representation is learned along with the individual robot policies for achieving the goal. After the initial learning stage, the observation of a new task execution by one robot becomes sufficient to generate a latent space representation pertaining to the other robots to achieve the same task. We verified our system in a set of experiments where the correspondence between robots is learned (1) when the robots need to follow the same paths to achieve the same task, (2) when the robots need to follow different trajectories to achieve the same task, and (3) when complexities of the required sensorimotor trajectories are different for the robots. We also provide a proof-of-the-concept realization of correspondence learning between a real manipulator robot and a simulated mobile robot.

Nurullah Eymen Özdemir, Erhan Oztop

Human cognitive development is shaped not only by individual effort but by structured social interaction, where role-based exchanges such as those between a tutor and a learner, enable solutions that neither could achieve alone. Inspired by these developmental principles, we ask the question whether a tutor-student multi-agent system can create a synergistic effect by pushing Large Language Model (LLM) beyond what it can do within existing frameworks. To test the idea, we adopt autonomous coding problem domain where two agents instantiated from the same LLM assigned asymmetric roles: a student agent generates and iteratively refines solutions, while a tutor agent provides structured evaluative feedback without access to ground-truth answers. In our proposed framework (PETITE), we aim to extract better problem-solving performance from one model by structuring its interaction through complementary roles, rather than relying on stronger supervisory models or heterogeneous ensembles. Our model is evaluated on the APPS coding benchmark against state-of-the-art approaches of Self-Consistency, Self-Refine, Multi-Agent Debate, and Multi-Agent Review. The results show that our model achieves similar or higher accuracy while consuming significantly fewer tokens. These results suggest that developmentally grounded role-differentiated interaction structures provide a principled and resource-efficient paradigm for enhancing LLM problem-solving through structured peer-like interactions. Index Terms- Peer Tutoring, Scaffolding, Large Language Models, Multi-Agent Systems, Code Generation

Bosong Ding, Erhan Oztop, Giacomo Spigler et al.

Objects, in particular tools, provide several action possibilities to the agents that can act on them, which are generally associated with the term of affordances. A tool is typically designed for a specific purpose, such as driving a nail in the case of a hammer, which we call as the primary affordance. A tool can also be used beyond its primary purpose, in which case we can associate this auxiliary use with the term secondary affordance. Previous work on affordance perception and learning has been mostly focused on primary affordances. Here, we address the less explored problem of learning the secondary tool affordances of human partners. To do this, we use the iCub robot to observe human partners with three cameras while they perform actions on twenty objects using four different tools. In our experiments, human partners utilize tools to perform actions that do not correspond to their primary affordances. For example, the iCub robot observes a human partner using a ruler for pushing, pulling, and moving objects instead of measuring their lengths. In this setting, we constructed a dataset by taking images of objects before and after each action is executed. We then model learning secondary affordances by training three neural networks (ResNet-18, ResNet-50, and ResNet-101) each on three tasks, using raw images showing the `initial' and `final' position of objects as input: (1) predicting the tool used to move an object, (2) predicting the tool used with an additional categorical input that encoded the action performed, and (3) joint prediction of both tool used and action performed. Our results indicate that deep learning architectures enable the iCub robot to predict secondary tool affordances, thereby paving the road for human-robot collaborative object manipulation involving complex affordances.

Suzan Ece Ada, Georg Martius, Emre Ugur et al.

Offline Reinforcement Learning (RL) provides a promising avenue for training policies from pre-collected datasets when gathering additional interaction data is infeasible. However, existing offline RL methods often assume stationarity or only consider synthetic perturbations at test time, assumptions that often fail in real-world scenarios characterized by abrupt, time-varying offsets. These offsets can lead to partial observability, causing agents to misperceive their true state and degrade performance. To overcome this challenge, we introduce Forecasting in Non-stationary Offline RL (FORL), a framework that unifies (i) conditional diffusion-based candidate state generation, trained without presupposing any specific pattern of future non-stationarity, and (ii) zero-shot time-series foundation models. FORL targets environments prone to unexpected, potentially non-Markovian offsets, requiring robust agent performance from the onset of each episode. Empirical evaluations on offline RL benchmarks, augmented with real-world time-series data to simulate realistic non-stationarity, demonstrate that FORL consistently improves performance compared to competitive baselines. By integrating zero-shot forecasting with the agent's experience, we aim to bridge the gap between offline RL and the complexities of real-world, non-stationary environments.

Suzan Ece Ada, Hanne Say, Emre Ugur et al.

Human brain and behavior provide a rich venue that can inspire novel control and learning methods for robotics. 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). The proposed ERP-BPNN model (1) learns in a human-like interleaved manner by (2) autonomous task switching based on a novel intrinsic motivation signal and, in contrast to existing methods, (3) allows bidirectional skill transfer among tasks. ERP-BPNN is a general architecture applicable to several multi-task learning settings; in this paper, we present the details of its neural architecture and show its ability to enable effective learning and skill transfer among morphologically different robots in a reaching task. The developed Bidirectional Progressive Neural Network (BPNN) architecture enables bidirectional skill transfer without requiring incremental training and seamlessly integrates with online task arbitration. The task arbitration mechanism developed is based on soft Episodic Return progress (ERP), a novel intrinsic motivation (IM) signal. To evaluate our method, we use quantifiable robotics metrics such as 'expected distance to goal' and 'path straightness' in addition to the usual reward-based measure of episodic return common in reinforcement learning. With simulation experiments, we show that ERP-BPNN achieves faster cumulative convergence and improves performance in all metrics considered among morphologically different robots compared to the baselines.

Negin Amirshirzad, Mehmet Arda Eren, Erhan Oztop

In this paper, we propose a novel lightweight learning from demonstration (LfD) model based on reservoir computing that can learn and generate multiple movement trajectories with prediction intervals, which we call as Context-based Echo State Network with prediction confidence (CESN+). CESN+ can generate movement trajectories that may go beyond the initial LfD training based on a desired set of conditions while providing confidence on its generated output. To assess the abilities of CESN+, we first evaluate its performance against Conditional Neural Movement Primitives (CNMP), a comparable framework that uses a conditional neural process to generate movement primitives. Our findings indicate that CESN+ not only outperforms CNMP but is also faster to train and demonstrates impressive performance in generating trajectories for extrapolation cases. In human-robot shared control applications, the confidence of the machine generated trajectory is a key indicator of how to arbitrate control sharing. To show the usability of the CESN+ for human-robot adaptive shared control, we have designed a proof-of-concept human-robot shared control task and tested its efficacy in adapting the sharing weight between the human and the robot by comparing it to a fixed-weight control scheme. The simulation experiments show that with CESN+ based adaptive sharing the total human load in shared control can be significantly reduced. Overall, the developed CESN+ model is a strong lightweight LfD system with desirable properties such fast training and ability to extrapolate to the new task parameters while producing robust prediction intervals for its output.

Hanne Say, Suzan Ece Ada, Emre Ugur et al.

As humans learn new skills and apply their existing knowledge while maintaining previously learned information, "continual learning" in machine learning aims to incorporate new data while retaining and utilizing past knowledge. However, existing machine learning methods often does not mimic human learning where tasks are intermixed due to individual preferences and environmental conditions. Humans typically switch between tasks instead of completely mastering one task before proceeding to the next. To explore how human-like task switching can enhance learning efficiency, we propose a multi task learning architecture that alternates tasks based on task-agnostic measures such as "learning progress" and "neural computational energy expenditure". To evaluate the efficacy of our method, we run several systematic experiments by using a set of effect-prediction tasks executed by a simulated manipulator robot. The experiments show that our approach surpasses random interleaved and sequential task learning in terms of average learning accuracy. Moreover, by including energy expenditure in the task switching logic, our approach can still perform favorably while reducing neural energy expenditure.

A. Enes Doruk, Erhan Oztop, Hasan F. Ates

Unsupervised Domain Adaptation (UDA) aims to utilize labeled data from a source domain to solve tasks in an unlabeled target domain, often hindered by significant domain gaps. Traditional CNN-based methods struggle to fully capture complex domain relationships, motivating the shift to vision transformers like the Swin Transformer, which excel in modeling both local and global dependencies. In this work, we propose a novel UDA approach leveraging the Swin Transformer with three key modules. A Graph Domain Discriminator enhances domain alignment by capturing inter-pixel correlations through graph convolutions and entropy-based attention differentiation. An Adaptive Double Attention module combines Windows and Shifted Windows attention with dynamic reweighting to align long-range and local features effectively. Finally, a Cross-Feature Transform modifies Swin Transformer blocks to improve generalization across domains. Extensive benchmarks confirm the state-of-the-art performance of our versatile method, which requires no task-specific alignment modules, establishing its adaptability to diverse applications.

Mehmet Arda Eren, Erhan Oztop

In self-supervised robotic learning, agents acquire data through active interaction with their environment, incurring costs such as energy use, human oversight, and experimental time. To mitigate these, sample-efficient exploration is essential. While intrinsic motivation (IM) methods like learning progress (LP) are widely used in robotics, and active learning (AL) is well established for classification in machine learning, few frameworks address continuous, high-dimensional regression tasks typical of world model learning. We propose MUSEL (Model Uncertainty for Sample-Efficient Learning), a novel AL framework tailored for regression tasks in robotics, such as action-effect prediction. MUSEL introduces a model uncertainty metric that combines total predictive uncertainty, learning progress, and input diversity to guide data acquisition. We validate our approach using a Stochastic Variational Deep Kernel Learning (SVDKL) model in two robotic tabletop tasks. Experimental results demonstrate that MUSEL improves both learning accuracy and sample efficiency, validating its effectiveness in learning action effects and selecting informative samples.

Zahra Koulaeizadeh, Erhan Oztop

A random recurrent neural network, called a reservoir, can be used to learn robot movements conditioned on context inputs that encode task goals. The Learning is achieved by mapping the random dynamics of the reservoir modulated by context to desired trajectories via linear regression. This makes the reservoir computing (RC) approach computationally efficient as no iterative gradient descent learning is needed. In this work, we propose a novel RC-based Learning from Demonstration (LfD) framework that not only learns to generate the demonstrated movements but also allows online modulation of the reservoir dynamics to generate movement trajectories that are not covered by the initial demonstration set. This is made possible by using a Reinforcement Learning (RL) module that learns a policy to output context as its actions based on the robot state. Considering that the context dimension is typically low, learning with the RL module is very efficient. We show the validity of the proposed model with systematic experiments on a 2 degrees-of-freedom (DOF) simulated robot that is taught to reach targets, encoded as context, with and without obstacle avoidance constraint. The initial data set includes a set of reaching demonstrations which are learned by the reservoir system. To enable reaching out-of-distribution targets, the RL module is engaged in learning a policy to generate dynamic contexts so that the generated trajectory achieves the desired goal without any learning in the reservoir system. Overall, the proposed model uses an initial learned motor primitive set to efficiently generate diverse motor behaviors guided by the designed reward function. Thus the model can be used as a flexible and effective LfD system where the action repertoire can be extended without new data collection.

Hakan Aktas, Yukie Nagai, Minoru Asada et al.

Affordances represent the inherent effect and action possibilities that objects offer to the agents within a given context. From a theoretical viewpoint, affordances bridge the gap between effect and action, providing a functional understanding of the connections between the actions of an agent and its environment in terms of the effects it can cause. In this study, we propose a deep neural network model that unifies objects, actions, and effects into a single latent vector in a common latent space that we call the affordance space. Using the affordance space, our system can generate effect trajectories when action and object are given and can generate action trajectories when effect trajectories and objects are given. Our model does not learn the behavior of individual objects acted upon by a single agent. Still, rather, it forms a `shared affordance representation' spanning multiple agents and objects, which we call Affordance Equivalence. Affordance Equivalence facilitates not only action generalization over objects but also Cross Embodiment transfer linking actions of different robots. In addition to the simulation experiments that demonstrate the proposed model's range of capabilities, we also showcase that our model can be used for direct imitation in real-world settings.

Alper Ahmetoglu, Batuhan Celik, Erhan Oztop et al.

In this paper, we propose and realize a new deep learning architecture for discovering symbolic representations for objects and their relations based on the self-supervised continuous interaction of a manipulator robot with multiple objects on a tabletop environment. The key feature of the model is that it can handle a changing number number of objects naturally and map the object-object relations into symbolic domain explicitly. In the model, we employ a self-attention layer that computes discrete attention weights from object features, which are treated as relational symbols between objects. These relational symbols are then used to aggregate the learned object symbols and predict the effects of executed actions on each object. The result is a pipeline that allows the formation of object symbols and relational symbols from a dataset of object features, actions, and effects in an end-to-end manner. 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. Our experiments show that the proposed architecture performs better than other baselines in effect prediction while forming not only object symbols but also relational symbols. Furthermore, we analyze the learned symbols and relational patterns between objects to learn about how the model interprets the environment. Our analysis shows that the learned symbols relate to the relative positions of objects, object types, and their horizontal alignment on the table, which reflect the regularities in the environment.

Alper Ahmetoglu, Emre Ugur, Minoru Asada et al.

Abstraction is an important aspect of intelligence which enables agents to construct robust representations for effective decision making. In the last decade, deep networks are proven to be effective due to their ability to form increasingly complex abstractions. However, these abstractions are distributed over many neurons, making the re-use of a learned skill costly. Previous work either enforced formation of abstractions creating a designer bias, or used a large number of neural units without investigating how to obtain high-level features that may more effectively capture the source task. For avoiding designer bias and unsparing resource use, we propose to exploit neural response dynamics to form compact representations to use in skill transfer. For this, we consider two competing methods based on (1) maximum information compression principle and (2) the notion that abstract events tend to generate slowly changing signals, and apply them to the neural signals generated during task execution. 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. We compare the generalization performance of these alternatives with the baselines of skill transfer with full layer output and no-transfer settings. Our results show that SFA units are the most successful for skill transfer. SFA as well as PCA, incur less resources compared to usual skill transfer, whereby many units formed show a localized response reflecting end-effector-obstacle-goal relations. Finally, SFA units with lowest eigenvalues resembles symbolic representations that highly correlate with high-level features such as joint angles which might be thought of precursors for fully symbolic systems.

Alper Ahmetoglu, M. Yunus Seker, Justus Piater et al.

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. Our robot interacts with objects using an initial action repertoire that is assumed to be acquired earlier and observes the effects it can create in the environment. To form action-grounded object, effect, and relational categories, we employ a binary bottleneck layer in a predictive, deep encoder-decoder network that takes the image of the scene and the action applied as input, and generates the resulting effects in the scene in pixel coordinates. After learning, the binary latent vector represents action-driven object categories based on the interaction experience of the robot. To distill the knowledge represented by the neural network into rules useful for symbolic reasoning, a decision tree is trained to reproduce its decoder function. Probabilistic rules are extracted from the decision paths of the tree and are represented in the Probabilistic Planning Domain Definition Language (PPDDL), allowing off-the-shelf planners to operate on the knowledge extracted from the sensorimotor experience of the robot. The deployment of the proposed approach for a simulated robotic manipulator enabled the discovery of discrete representations of object properties such as `rollable' and `insertable'. In turn, the use of these representations as symbols allowed the generation of effective plans for achieving goals, such as building towers of the desired height, demonstrating the effectiveness of the approach for multi-step object manipulation. Finally, we demonstrate that the system is not only restricted to the robotics domain by assessing its applicability to the MNIST 8-puzzle domain in which learned symbols allow for the generation of plans that move the empty tile into any given position.

Melisa Sener, Yukie Nagai, Erhan Oztop et al.

One effective approach for equipping artificial agents with sensorimotor skills is to use self-exploration. To do this efficiently is critical, as time and data collection are costly. In this study, we propose an exploration mechanism that blends action, object, and action outcome representations into a latent space, where local regions are formed to host forward model learning. The agent uses intrinsic motivation to select the forward model with the highest learning progress to adopt at a given exploration step. This parallels how infants learn, as high learning progress indicates that the learning problem is neither too easy nor too difficult in the selected region. The proposed approach is validated with a simulated robot in a table-top environment. The simulation scene comprises a robot and various objects, where the robot interacts with one of them each time using a set of parameterized actions and learns the outcomes of these interactions. With the proposed approach, the robot organizes its curriculum of learning as in existing intrinsic motivation approaches and outperforms them in learning speed. Moreover, the learning regime demonstrates features that partially match infant development; in particular, the proposed system learns to predict the outcomes of different skills in a staged manner.

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. To our knowledge this provides the best known bound on both the PTF density (number of monomials) and weight (sum of the coefficient magnitudes) of general Boolean functions. The special case of Bent functions is also analyzed and shown that any n-variable Bent function can be represented with integer coefficients less than $2^n$ while also obeying the aforementioned density bound. Finally, sparse Boolean functions, which are almost constant except for $m << 2^n$ number of variable assignments, are shown to have small weight PTFs with density at most $m+2^{n-1}$.

M. Tuluhan Akbulut, Erhan Oztop, M. Yunus Seker et al.

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). In this paper, we propose a novel LfD+RL framework, namely Adaptive Conditional Neural Movement Primitives (ACNMP), that allows efficient policy improvement in novel environments and effective skill transfer between different agents. This is achieved through exploiting the latent representation learned by the underlying Conditional Neural Process (CNP) model, and simultaneous training of the model with supervised learning (SL) for acquiring the demonstrated trajectories and via RL for new trajectory discovery. Through simulation experiments, we show that (i) ACNMP enables the system to extrapolate to situations where pure LfD fails; (ii) Simultaneous training of the system through SL and RL preserves the shape of demonstrations while adapting to novel situations due to the shared representations used by both learners; (iii) ACNMP enables order-of-magnitude sample-efficient RL in extrapolation of reaching tasks compared to the existing approaches; (iv) ACNMPs can be used to implement skill transfer between robots having different morphology, with competitive learning speeds and importantly with less number of assumptions compared to the state-of-the-art approaches. Finally, we show the real-world suitability of ACNMPs through real robot experiments that involve obstacle avoidance, pick and place and pouring actions.

Tadahiro Taniguchi, Emre Ugur, Matej Hoffmann et al.

Humans use signs, e.g., sentences in a spoken language, for communication and thought. Hence, symbol systems like language are crucial for our communication with other agents and adaptation to our real-world environment. The symbol systems we use in our human society adaptively and dynamically change over time. In the context of artificial intelligence (AI) and cognitive systems, the symbol grounding problem has been regarded as one of the central problems related to {\it symbols}. 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. In this paper, we focus on the symbol emergence problem, addressing not only cognitive dynamics but also the dynamics of symbol systems in society, rather than the symbol grounding problem. We first introduce the notion of a symbol in semiotics from the humanities, to leave the very narrow idea of symbols in symbolic AI. Furthermore, over the years, it became more and more clear that symbol emergence has to be regarded as a multifaceted problem. Therefore, secondly, we review the history of the symbol emergence problem in different fields, including both biological and artificial systems, showing their mutual relations. We summarize the discussion and provide an integrative viewpoint and comprehensive overview of symbol emergence in cognitive systems. Additionally, we describe the challenges facing the creation of cognitive systems that can be part of symbol emergence systems.

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. We compare these among each other and against the algorithm of Oztop via computational experiments. The results indicate that our heuristic algorithms find more parsimonious representations compared to the those of non-heuristic and GA-based algorithms.