26 June 2018 in International Journal of Computational Intelligence and Applications
Most learning algorithms require the practitioner to manually set the values of many hyperparameters before the learning process can begin. However, with modern algorithms, the evaluation of a given hyperparameter setting can take a considerable amount of time and the search space is often very high-dimensional. We suggest using a lower-dimensional representation of the original data to quickly identify promising areas in the hyperparameter space. This information can then be used to initialize the optimization algorithm for the original, higher-dimensional data. We compare this approach with the standard procedure of optimizing the hyperparameters only on the original input. We perform experiments with various state-of-the-art hyperparameter optimization algorithms such as random search, the tree of parzen estimators (TPEs), sequential model-based algorithm configuration (SMAC), and a genetic algorithm (GA). Our experiments indicate that it is possible to speed up the optimization process by using lower-dimensional data representations at the beginning, while increasing the dimensionality of the input later in the optimization process. This is independent of the underlying optimization procedure, making the approach promising for many existing hyperparameter optimization algorithms.
22 April 2016 in IEEE Transactions on Cognitive and Developmental Systems
In the future, robots will be used more extensively as assistants in home scenarios and must be able to acquire expertise from trainers by learning through crossmodal interaction. One promising approach is interactive reinforcement learning (IRL) where an external trainer advises an apprentice on actions to speed up the learning process. In this paper we present an IRL approach for the domestic task of cleaning a table and compare three different learning methods using simulated robots: 1) reinforcement learning (RL); 2) RL with contextual affordances to avoid failed states; and 3) the previously trained robot serving as a trainer to a second apprentice robot. We then demonstrate that the use of IRL leads to different performance with various levels of interaction and consistency of feedback. Our results show that the simulated robot completes the task with RL, although working slowly and with a low rate of success. With RL and contextual affordances fewer actions are needed and can reach higher rates of success. For good performance with IRL it is essential to consider the level of consistency of feedback since inconsistencies can cause considerable delay in the learning process. In general, we demonstrate that interactive feedback provides an advantage for the robot in most of the learning cases.
22 October 2020 in International Journal of Social Robotics
Recent studies have revealed the key importance of modelling personality in robots to improve interaction quality by empowering them with social-intelligence capabilities. Most research relies on verbal and non-verbal features related to personality traits that are highly context-dependent. Hence, analysing how humans behave in a given context is crucial to evaluate which of those social cues are effective. For this purpose, we designed an assistive memory game, in which participants were asked to play the game obtaining support from an introvert or extroverted helper, whether from a human or robot. In this context, we aim to (i) explore whether selective verbal and non-verbal social cues related to personality can be modelled in a robot, (ii) evaluate the efficiency of a statistical decision-making algorithm employed by the robot to provide adaptive assistance, and (iii) assess the validity of the similarity attraction principle. Specifically, we conducted two user studies. In the human–human study (N=31), we explored the effects of helper’s personality on participants’ performance and extracted distinctive verbal and non-verbal social cues from the human helper. In the human–robot study (N=24), we modelled the extracted social cues in the robot and evaluated its effectiveness on participants’ performance. Our findings showed that participants were able to distinguish between robots’ personalities, and not between the level of autonomy of the robot (Wizard-of-Oz vs fully autonomous). Finally, we found that participants achieved better performance with a robot helper that had a similar personality to them, or a human helper that had a different personality.