Now showing items 1-15 of 15

  • A competitive strategy for function approximation in Q-learning 

    Agostini, Alejandro Gabriel; Celaya Llover, Enric (2011)
    Conference report
    Open Access
    In 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)
    External research report
    Open Access
    This 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 (2008)
    Conference report
    Open Access
    In 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 (University of Karlsruhe, 2008)
    Conference report
    Open Access
    In 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
    Open Access
    Embodied 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 ...
  • 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)
    Conference report
    Open Access
    Human 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)
    External research report
    Open Access
    In 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
    Open Access
    We 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
    Open Access
    This 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)
    External research report
    Open Access
    In 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 ...
  • Probability density estimation of the Q Function for reinforcement learning 

    Agostini, Alejandro Gabriel; Celaya Llover, Enric (2009)
    External research report
    Open Access
    Performing 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)
    External research report
    Open Access
    In 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)
    Conference report
    Restricted access - publisher's policy
    The 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)
    Conference report
    Open Access
    Recent 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)
    External research report
    Open Access
    In 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.