Exploració per autor "Agostini, Alejandro Gabriel"
Ara es mostren els items 1-20 de 20
-
A cognitive architecture for automatic gardening
Agostini, Alejandro Gabriel; Alenyà Ribas, Guillem; Fischbach, Andreas; Scharr, Hanno; Woergoetter, Florentin; Torras, Carme (2017-06-01)
Article
Accés obertIn large industrial greenhouses, plants are usually treated following well established protocols for watering, nutrients, and shading/light. While this is practical for the automation of the process, it does not tap the ... -
A competitive strategy for function approximation in Q-learning
Agostini, Alejandro Gabriel; Celaya Llover, Enric (2011)
Text en actes de congrés
Accés obertIn this work we propose an approach for generalization in continuous domain Reinforcement Learning that, instead of using a single function approximator, tries many different function approximators in parallel, each one ... -
A general strategy for interactive decision-making in robotic platforms
Agostini, Alejandro Gabriel; Torras, Carme; Wörgötter, Florentin (2011)
Report de recerca
Accés obertThis work presents an intergated strategy for planning and learning suitable to execute tasks with robotic platforms without any previous task specification. The approach rapidly learns planning operators from few action ... -
Action rule induction from cause-effect pairs learned through robot-teacher interaction
Agostini, Alejandro Gabriel; Celaya Llover, Enric; Torras, Carme; Wörgötter, Florentin (University of Karlsruhe, 2008)
Text en actes de congrés
Accés obertIn this work we propose a decision-making system that efficiently learns behaviors in the form of rules using natural human instructions about cause-effect relations in currently observed situations, avoiding complicated ... -
Action rule induction from cause-effect pairs learned through robot-teacher interaction
Agostini, Alejandro Gabriel; Celaya Llover, Enric; Torras, Carme; Wörgötter, Florentin (2008)
Text en actes de congrés
Accés obertIn this work we propose a decision-making system that efficiently learns behaviors in the form of rules using natural human instructions about cause-effect relations in currently observed situations, avoiding complicated ... -
Cognitive agents: a procedural perspective relying on the predictability of object-action-omplexes (OACs)
Wörgötter, Florentin; Agostini, Alejandro Gabriel; Krüger, Norbert; Shylo, Natalya; Porr, Ben (2009)
Article
Accés obertEmbodied cognition suggests that complex cognitive traits can only arise when agents have a body situated in the world. The aspects of embodiment and situatedness are being discussed here from the perspective of linear ... -
Competitive function approximation for reinforcement learning
Agostini, Alejandro Gabriel; Celaya Llover, Enric (2014)
Report de recerca
Accés obertThe application of reinforcement learning to problems with continuous domains requires representing the value function by means of function approximation. We identify two aspects of reinforcement learning that make the ... -
Efficient interactive decision-making framework for robotic applications
Agostini, Alejandro Gabriel; Torras, Carme; Woergoetter, Florentin (2017-06-01)
Article
Accés obertThe inclusion of robots in our society is imminent, such as service robots. Robots are now capable of reliably manipulating objects in our daily lives but only when combined with artificial intelligence (AI) techniques for ... -
Integrating task planning and interactive learning for robots to work in human environments
Agostini, Alejandro Gabriel; Torras, Carme; Wörgötter, Florentin (AAAI Press. Association for the Advancement of Artificial Intelligence, 2011)
Text en actes de congrés
Accés obertHuman environments are challenging for robots, which need to be trainable by lay people and learn new behaviours rapidly without disrupting much the ongoing activity. A system that integrates AI techniques for planning and ... -
Learning rules from cause-effects explanations
Agostini, Alejandro Gabriel; Celaya Llover, Enric; Torras, Carme; Wörgötter, Florentin (2008)
Report de recerca
Accés obertIn this work we propose a learning system to learn on-line an action policy coded in rules using natural human instructions about cause-effect relations in currently observed situations. The instructions only on currently ... -
Learning weakly correlated cause-effects for gardening with a cognitive system
Agostini, Alejandro Gabriel; Torras, Carme; Worgotter, Florentin (2014)
Article
Accés obertWe propose a cognitive system that combines artificial intelligence techniques for planning and learning to execute tasks involving delayed and variable correlations between the actions executed and their expected effects. ... -
Object-action complexes: grounded abstractions of sensory-motor processes
Krüger, Norbert; Geib, Cristopher; Piater, Justus; Petrick, Ronald; Steedman, Mark; Wörgötter, Florentin; Ude, Ales; Asfour, Tamim; Kraft, Dirk; Omrcen, Damir; Agostini, Alejandro Gabriel; Dillmann, Rudiger (2011)
Article
Accés obertThis paper formalises Object-Action Complexes (OACs) as a basis for symbolic representations of sensorimotor experience and behaviours. OACs are designed to capture the interaction between objects and associated actions in ... -
On-line learning of macro planning operators using probabilistic estimations of cause-effects
Agostini, Alejandro Gabriel; Wörgötter, Florentin; Celaya Llover, Enric; Torras, Carme (2008)
Report de recerca
Accés obertIn this work we propose an on-line learning method for learning action rules for planning. The system uses a probabilistic approach of a constructive induction method that combines a beam search with an example-based search ... -
Online EM with weight-based forgetting
Celaya Llover, Enric; Agostini, Alejandro Gabriel (2015)
Article
Accés obertIn the on-line version of the EM algorithm introduced by Sato and Ishii (2000), a time-dependent discount factor is introduced for forgetting the effect of the old posterior values obtained with an earlier, inaccurate ... -
Online reinforcement learning using a probability density estimation
Agostini, Alejandro Gabriel; Celaya Llover, Enric (The MIT Press. Massachusetts Institute of Technology, 2017-01-01)
Article
Accés obertFunction approximation in online, incremental, reinforcement learning needs to deal with two fundamental problems: biased sampling and nonstationarity. In this kind of task, biased sampling occurs because samples are ... -
Probability density estimation of the Q Function for reinforcement learning
Agostini, Alejandro Gabriel; Celaya Llover, Enric (2009)
Report de recerca
Accés obertPerforming Q-Learning in continuous state-action spaces is a problem still unsolved for many complex applications. The Q function may be rather complex and can not be expected to fit into a predefined parametric model. In ... -
Quick learning of cause-effects relevant for robot action
Agostini, Alejandro Gabriel; Wörgötter, Florentin; Torras, Carme (2010)
Report de recerca
Accés obertIn this work we propose a new paradigm for the rapid learning of cause-effect relations relevant for task execution. Learning occurs automatically from action experiences by means of a novel constructive learning approach ... -
Reinforcement learning for robot control using probability density estimations
Agostini, Alejandro Gabriel; Celaya Llover, Enric (INSTICC Press. Institute for Systems and Technologies of Information, Control and Communication, 2010)
Text en actes de congrés
Accés restringit per política de l'editorialThe successful application of Reinforcement Learning (RL) techniques to robot control is limited by the fact that, in most robotic tasks, the state and action spaces are continuous, multidimensional, and in essence, too ... -
Reinforcement learning with a Gaussian mixture model
Agostini, Alejandro Gabriel; Celaya Llover, Enric (2010)
Text en actes de congrés
Accés obertRecent approaches to Reinforcement Learning (RL) with function approximation include Neural Fitted Q Iteration and the use of Gaussian Processes. They belong to the class of fitted value iteration algorithms, which use a ... -
Stochastic approximations of average values using proportions of samples
Agostini, Alejandro Gabriel; Celaya Llover, Enric (2011)
Report de recerca
Accés obertIn this work we explain how the stochastic approximation of the average of a random variable is carried out when the observations used in the updates consist in proportion of samples rather than complete samples.