1 code implementation • 8 Mar 2024 • Lennart Wachowiak, Andrew Coles, Oya Celiktutan, Gerard Canal
We find that GPT-4 strongly outperforms other models, generating answers that correlate strongly with users' answers in two studies $\unicode{x2014}$ the first study dealing with selecting the most appropriate communicative act for a robot in various situations ($r_s$ = 0. 82), and the second with judging the desirability, intentionality, and surprisingness of behavior ($r_s$ = 0. 83).
no code implementations • 4 Mar 2024 • Ruiqi Zhu, Tianhong Dai, Oya Celiktutan
Unlike prior methods that rely on paired data, we propose a novel approach for learning the mapping functions between state and action spaces across domains using unpaired data.
1 code implementation • 6 Jul 2023 • Ruiqi Zhu, Siyuan Li, Tianhong Dai, Chongjie Zhang, Oya Celiktutan
Our method can endow agents with the ability to explore and acquire the required prior behaviours and then connect to the task-specific behaviours in the demonstration to solve sparse-reward tasks without requiring additional demonstration of the prior behaviours.
no code implementations • ICCV 2023 • Edoardo Cetin, Antonio Carta, Oya Celiktutan
Meta-learning holds the potential to provide a general and explicit solution to tackle interference and forgetting in continual learning.
1 code implementation • 24 Nov 2022 • Jian Jiang, Oya Celiktutan
Task incremental learning aims to enable a system to maintain its performance on previously learned tasks while learning new tasks, solving the problem of catastrophic forgetting.
no code implementations • 13 Oct 2022 • Edoardo Cetin, Oya Celiktutan
We model agent behavior as the steady-state distribution of a parameterized reasoning Markov chain (RMC), optimized with a new tractable estimate of the policy gradient.
no code implementations • 30 Sep 2022 • Hanan Salam, Oya Celiktutan, Hatice Gunes, Mohamed Chetouani
An integral part of seamless human-human communication is engagement, the process by which two or more participants establish, maintain, and end their perceived connection.
1 code implementation • 3 Jul 2022 • Edoardo Cetin, Philip J. Ball, Steve Roberts, Oya Celiktutan
Off-policy reinforcement learning (RL) from pixel observations is notoriously unstable.
no code implementations • 8 Nov 2021 • Viktor Schmuck, Oya Celiktutan
Our proposed method, GROup detection With Link prediction (GROWL), demonstrates the effectiveness of a GNN based approach.
1 code implementation • 18 Oct 2021 • Nguyen Tan Viet Tuyen, Oya Celiktutan
Along with verbal communication, successful social interaction is closely coupled with the interplay between nonverbal perception and action mechanisms, such as observation of gaze behaviour and following their attention, coordinating the form and function of hand gestures.
no code implementations • 7 Oct 2021 • Edoardo Cetin, Oya Celiktutan
Off-policy deep reinforcement learning algorithms commonly compensate for overestimation bias during temporal-difference learning by utilizing pessimistic estimates of the expected target returns.
no code implementations • 5 Jun 2021 • Edoardo Cetin, Oya Celiktutan
Within our framework, agents learn effective behavior over a routine space: a new, higher-level action space, where each routine represents a set of 'equivalent' sequences of granular actions with arbitrary length.
no code implementations • 21 Apr 2021 • Jian Jiang, Edoardo Cetin, Oya Celiktutan
However, finding a trade-off between the model performance and the number of samples to save for each class is still an open problem for replay-based incremental learning and is increasingly desirable for real-life applications.
1 code implementation • ICLR 2021 • Edoardo Cetin, Oya Celiktutan
Human beings are able to understand objectives and learn by simply observing others perform a task.
no code implementations • 4 May 2015 • Eric Lombardi, Christian Wolf, Oya Celiktutan, Bülent Sankur
In this paper, we propose a method for activity recognition from videos based on sparse local features and hypergraph matching.