An intrinsic reward for affordance exploration

Hart, Stephen

doi:10.1109/devlrn.2009.5175542

Cited by 12 publications

(15 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Q-value iteration [32,33] is implemented to establish a value function where at any time, the highest value corresponds to regions of interest in the parameter-space with high uncertainty. The intrinsic reward function uses the difference in the variance of experiences achieved from the same state under the same action as originally proposed in [7]. For use with the ATG representation, the intrinsic reward takes a slightly different form,…”

Section: E Affordance Modeling and Intrinsic Rewardmentioning

confidence: 99%

“…Hierarchical approaches have been developed employing intrinsic motivation to learn new skills autonomously [5,6]. A number of intrinsic motivators have been proposed [4,7] with approaches in contrast with previous work that relied on hand-built representations tailored to a particular task [8][9][10]. Our view is that autonomous exploration and intrinsically motivated discovery should prove more robust and transferable than hand built knowledge representations.…”

Section: Introductionmentioning

confidence: 99%

“…For instance, an example of multiple intrinsic reward functions have been proposed to learn the transition dynamics of a particular task [25]. Others have looked into domain-independent intrinsic rewards, like novelty or certainty, for learning adaptive, non-stationary policies based on data gathered from experience [7,29]. In particular, model exploration programs have been presented [7], but methods reported to date lack multimodal sensor integration and do not produce knowledge structures that are easily transferrable to other tasks.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Intrinsically motivated multimodal structure learning

Wong

Grupen

2016

2016 Joint IEEE International Conference on Development and Learning and Epigenetic Robotics (ICDL-EpiRob)

View full text Add to dashboard Cite

Abstract-We present a long-term intrinsically motivated structure learning method for modeling transition dynamics during controlled interactions between a robot and semipermanent structures in the world. In particular, we discuss how partially-observable state is represented using distributions over a Markovian state and build models of objects that predict how state distributions change in response to interactions with such objects. These structures serve as the basis for a number of possible future tasks defined as Markov Decision Processes (MDPs). The approach is an example of a structure learning technique applied to a multimodal affordance representation that yields a population of forward models for use in planning. We evaluate the approach using experiments on a bimanual mobile manipulator (uBot-6) that show the performance of model acquisition as the number of transition actions increases.

show abstract

Section: E Affordance Modeling and Intrinsic Rewardmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Intrinsically motivated multimodal structure learning

Wong

Grupen

2016

2016 Joint IEEE International Conference on Development and Learning and Epigenetic Robotics (ICDL-EpiRob)

View full text Add to dashboard Cite

show abstract

“…Others have focused on coupling visual-based object representations with exploratory behaviors [14], [15]. Natale et al [9] have demonstrated that a robot can recognize objects with the help of a self-organizing map using proprioceptive data extracted from the robot's hand as it grasped an object.…”

Section: Related Workmentioning

confidence: 99%

Object category recognition by a humanoid robot using behavior-grounded relational learning

Sinapov

Stoytchev

2011

2011 IEEE International Conference on Robotics and Automation

View full text Add to dashboard Cite

Abstract-The ability to form and recognize object categories is fundamental to human intelligence. This paper proposes a behavior-grounded relational classification model that allows a robot to recognize the categories of household objects. In the proposed approach, the robot initially explores the objects by applying five exploratory behaviors (lift, shake, drop, crush and push) on them while recording the proprioceptive and auditory sensory feedback produced by each interaction. The sensorimotor data is used to estimate multiple measures of similarity between the objects, each corresponding to a specific coupling between an exploratory behavior and a sensory modality. A graph-based recognition model is trained by extracting features from the estimated similarity relations, allowing the robot to recognize the category memberships of a novel object based on the object's similarity to the set of familiar objects. The framework was evaluated on an upper-torso humanoid robot with two large sets of household objects. The results show that the robot's model is able to recognize complex object categories (e.g., metal objects, empty bottles, etc.) significantly better than chance.

show abstract

“…This vocabulary need not be static and can continue to develop [107]. Nor do they need to be trajectories, but can be models or feedback control laws learned through experience or tutoring [108]- [111]. These motor-memory responses with automatic responses can prevent planning-execution delays associated with stuttering [112].…”

Section: Sensorimotor Controlmentioning

confidence: 99%

Biomimetic learning, not learning biomimetics: A survey of developmental learning

Jennings

Ordóñez

2010

Proceedings of the IEEE 2010 National Aerospace &Amp; Electronics Conference

View full text Add to dashboard Cite

Rather than try to learn skills directly, developmental learning seeks to create a general purpose system inspired by the human developmental process. The premise is that intelligent behavior can only be achieved through the course of experience, and attempts to circumvent this approach will lead to a plateau limiting performance. There are many facets of this approach and some of the common examples are categorization, sensorimotor control and social learning. These are relatively simple tasks for people, yet challenging for an autonomous robot. A survey of research in this recent field is presented. The concepts and the tools used are described so that other disciplines may have a understanding of this field and use the paradigm in their applications.

show abstract

An intrinsic reward for affordance exploration

Cited by 12 publications

References 9 publications

Intrinsically motivated multimodal structure learning

Intrinsically motivated multimodal structure learning

Object category recognition by a humanoid robot using behavior-grounded relational learning

Biomimetic learning, not learning biomimetics: A survey of developmental learning

Contact Info

Product

Resources

About