Category Archives: Cognitive Sciences

Semantic and syntactic bootstrapped learning for robots, inspired in similar processes in humans, that use language as a scaffolding mechanism to improve learning in unknown situations

July 21, 2015 11:01 ,

Worgotter, F.; Geib, C.; Tamosiunaite, M.; Aksoy, E.E.; Piater, J.; Hanchen Xiong; Ude, A.; Nemec, B.; Kraft, D.; Kruger, N.; Wachter, M.; Asfour, T., Structural Bootstrapping—A Novel, Generative Mechanism for Faster and More Efficient Acquisition of Action-Knowledge, Autonomous Mental Development, IEEE Transactions on , vol.7, no.2, pp.140,154, June 2015, DOI: 10.1109/TAMD.2015.2427233.

Humans, but also robots, learn to improve their behavior. Without existing knowledge, learning either needs to be explorative and, thus, slow or-to be more efficient-it needs to rely on supervision, which may not always be available. However, once some knowledge base exists an agent can make use of it to improve learning efficiency and speed. This happens for our children at the age of around three when they very quickly begin to assimilate new information by making guided guesses how this fits to their prior knowledge. This is a very efficient generative learning mechanism in the sense that the existing knowledge is generalized into as-yet unexplored, novel domains. So far generative learning has not been employed for robots and robot learning remains to be a slow and tedious process. The goal of the current study is to devise for the first time a general framework for a generative process that will improve learning and which can be applied at all different levels of the robot’s cognitive architecture. To this end, we introduce the concept of structural bootstrapping-borrowed and modified from child language acquisition-to define a probabilistic process that uses existing knowledge together with new observations to supplement our robot’s data-base with missing information about planning-, object-, as well as, action-relevant entities. In a kitchen scenario, we use the example of making batter by pouring and mixing two components and show that the agent can efficiently acquire new knowledge about planning operators, objects as well as required motor pattern for stirring by structural bootstrapping. Some benchmarks are shown, too, that demonstrate how structural bootstrapping improves performance.

Posted in: Developmental robotics, Psycho-physiological bases of engineering , Tagged: , ,

Developmental approach for a robot manipulator that learns in several bootstrapped stages, strongly inspired in infant development

July 21, 2015 10:32 ,

Ugur, E.; Nagai, Y.; Sahin, E.; Oztop, E., Staged Development of Robot Skills: Behavior Formation, Affordance Learning and Imitation with Motionese, Autonomous Mental Development, IEEE Transactions on , vol.7, no.2, pp.119,139, June 2015, DOI: 10.1109/TAMD.2015.2426192.

Inspired by infant development, we propose a three staged developmental framework for an anthropomorphic robot manipulator. In the first stage, the robot is initialized with a basic reach-and- enclose-on-contact movement capability, and discovers a set of behavior primitives by exploring its movement parameter space. In the next stage, the robot exercises the discovered behaviors on different objects, and learns the caused effects; effectively building a library of affordances and associated predictors. Finally, in the third stage, the learned structures and predictors are used to bootstrap complex imitation and action learning with the help of a cooperative tutor. The main contribution of this paper is the realization of an integrated developmental system where the structures emerging from the sensorimotor experience of an interacting real robot are used as the sole building blocks of the subsequent stages that generate increasingly more complex cognitive capabilities. The proposed framework includes a number of common features with infant sensorimotor development. Furthermore, the findings obtained from the self-exploration and motionese guided human-robot interaction experiments allow us to reason about the underlying mechanisms of simple-to-complex sensorimotor skill progression in human infants.

Posted in: Developmental robotics, Psycho-physiological bases of engineering , Tagged: , , , , ,

Finding the common utility of actions in several tasks learnt in the same domain in order to reduce the learning cost of reinforcement learning

July 21, 2015 08:42 ,

Rosman, B.; Ramamoorthy, S., Action Priors for Learning Domain Invariances, Autonomous Mental Development, IEEE Transactions on , vol.7, no.2, pp.107,118, June 2015, DOI: 10.1109/TAMD.2015.2419715.

An agent tasked with solving a number of different decision making problems in similar environments has an opportunity to learn over a longer timescale than each individual task. Through examining solutions to different tasks, it can uncover behavioral invariances in the domain, by identifying actions to be prioritized in local contexts, invariant to task details. This information has the effect of greatly increasing the speed of solving new problems. We formalise this notion as action priors, defined as distributions over the action space, conditioned on environment state, and show how these can be learnt from a set of value functions. We apply action priors in the setting of reinforcement learning, to bias action selection during exploration. Aggressive use of action priors performs context based pruning of the available actions, thus reducing the complexity of lookahead during search. We additionally define action priors over observation features, rather than states, which provides further flexibility and generalizability, with the additional benefit of enabling feature selection. Action priors are demonstrated in experiments in a simulated factory environment and a large random graph domain, and show significant speed ups in learning new tasks. Furthermore, we argue that this mechanism is cognitively plausible, and is compatible with findings from cognitive psychology.

Posted in: Psycho-physiological bases of engineering, Reinforcement learning theory , Tagged: , , ,

Example of application of bayesian network learning and inference to robotics, and a brief but useful related work on learning by imitation

July 17, 2015 12:31 ,

Dan Song; Ek, C.H.; Huebner, K.; Kragic, D., Task-Based Robot Grasp Planning Using Probabilistic Inference, Robotics, IEEE Transactions on , vol.31, no.3, pp.546,561, June 2015, DOI: 10.1109/TRO.2015.2409912.

Grasping and manipulating everyday objects in a goal-directed manner is an important ability of a service robot. The robot needs to reason about task requirements and ground these in the sensorimotor information. Grasping and interaction with objects are challenging in real-world scenarios, where sensorimotor uncertainty is prevalent. This paper presents a probabilistic framework for the representation and modeling of robot-grasping tasks. The framework consists of Gaussian mixture models for generic data discretization, and discrete Bayesian networks for encoding the probabilistic relations among various task-relevant variables, including object and action features as well as task constraints. We evaluate the framework using a grasp database generated in a simulated environment including a human and two robot hand models. The generative modeling approach allows the prediction of grasping tasks given uncertain sensory data, as well as object and grasp selection in a task-oriented manner. Furthermore, the graphical model framework provides insights into dependencies between variables and features relevant for object grasping.

Posted in: Learning from Demonstration , Tagged: , , , , ,

Neural support for the cognitive map: place cells and grid cells

May 29, 2015 16:44 ,

Kate J. Jeffery, Distorting the metric fabric of the cognitive map, Trends in Cognitive Sciences, Volume 19, Issue 6, June 2015, Pages 300-301, ISSN 1364-6613, DOI: 10.1016/j.tics.2015.04.001..

Grid cells are neurons whose regularly spaced firing fields form apparently symmetric arrays, or grids, that are thought to collectively provide an environment-independent metric framework for the brain’s cognitive map of space. However, two recent studies show that grids are naturally distorted, revealing greater local environment-specific effects than previously recognized.

Posted in: Psycho-physiological bases of engineering , Tagged:

Reinforcement learning when a human is the one providing the rewards to the algorithm

May 19, 2015 11:46 ,

W. Bradley Knox, Peter Stone, Framing reinforcement learning from human reward: Reward positivity, temporal discounting, episodicity, and performance, Artificial Intelligence, Volume 225, August 2015, Pages 24-50, ISSN 0004-3702, DOI: 10.1016/j.artint.2015.03.009.

Several studies have demonstrated that reward from a human trainer can be a powerful feedback signal for control-learning algorithms. However, the space of algorithms for learning from such human reward has hitherto not been explored systematically. Using model-based reinforcement learning from human reward, this article investigates the problem of learning from human reward through six experiments, focusing on the relationships between reward positivity, which is how generally positive a trainer’s reward values are; temporal discounting, the extent to which future reward is discounted in value; episodicity, whether task learning occurs in discrete learning episodes instead of one continuing session; and task performance, the agent’s performance on the task the trainer intends to teach. This investigation is motivated by the observation that an agent can pursue different learning objectives, leading to different resulting behaviors. We search for learning objectives that lead the agent to behave as the trainer intends.
We identify and empirically support a “positive circuits” problem with low discounting (i.e., high discount factors) for episodic, goal-based tasks that arises from an observed bias among humans towards giving positive reward, resulting in an endorsement of myopic learning for such domains. We then show that converting simple episodic tasks to be non-episodic (i.e., continuing) reduces and in some cases resolves issues present in episodic tasks with generally positive reward and—relatedly—enables highly successful learning with non-myopic valuation in multiple user studies. The primary learning algorithm introduced in this article, which we call “vi-tamer”, is the first algorithm to successfully learn non-myopically from reward generated by a human trainer; we also empirically show that such non-myopic valuation facilitates higher-level understanding of the task. Anticipating the complexity of real-world problems, we perform further studies—one with a failure state added—that compare (1) learning when states are updated asynchronously with local bias—i.e., states quickly reachable from the agent’s current state are updated more often than other states—to (2) learning with the fully synchronous sweeps across each state in the vi-tamer algorithm. With these locally biased updates, we find that the general positivity of human reward creates problems even for continuing tasks, revealing a distinct research challenge for future work.

Posted in: Psycho-physiological bases of engineering, Reinforcement learning in AI , Tagged: ,

Heuristic, real-time search with weighted heuristic function

May 19, 2015 11:40 ,

Nicolás Rivera, Jorge A. Baier, Carlos Hernández, Incorporating weights into real-time heuristic search, Artificial Intelligence, Volume 225, August 2015, Pages 1-23, ISSN 0004-3702, DOI: 10.1016/j.artint.2015.03.008.

Multiplying the heuristic function by a weight greater than one is a well-known technique in heuristic search. When this technique is applied to A* with an admissible heuristic it yields substantial runtime savings, at the expense of sacrificing solution optimality. Its applicability to real-time heuristic search, a search approach that builds upon heuristic search, however, has only been explored by a few studies. In this article we present two new approaches to using weights in real-time heuristic search, applicable to a wide range of algorithms. The first one, weighted lookahead, is a variant of an existing approach by Shimbo and Ishida, and utilizes the weight while the algorithm performs lookahead search. The second one, weighted update, incorporates the weight to the edges of the search graph during the learning phase. We implemented both techniques within LSS-LRTA* and evaluated them in path-planning benchmarks. We show that weighted lookahead outperforms an existing approach by Shimbo and Ishida but that it does not improve over existing approaches that do not use weights. Weighted update, on the other hand, yields performance improvements of up to one order of magnitude both in solution cost and total search time. To illustrate further the generality of weighted update, we incorporate the technique in two other well-known real-time heuristic search algorithms: LRTA*-LS and daLSS-LRTA*, and we empirically show significant improvements for LRTA*-LS and modest but still important improvements for daLSS-LRTA*. We analyze the properties of weighted update in depth, showing, among other things, that it guarantees termination. Convergence behavior of LSS-LRTA*, modified to use weighted update, is also analyzed. In such a setting, we prove solutions are w-optimal, and provide additional bounds on solution quality that in practice are tighter than w-optimality.

Posted in: Artificial Intelligence, Real-Time Systems , Tagged: ,

Reinforcement learning applied to select which parts of a Neural Turing Machine are to be updated with backpropagation during learning

May 12, 2015 18:21 ,

Wojciech Zaremba, Ilya Sutskever, Reinforcement Learning Neural Turing Machines, arXiv.org, arXiv:1505.00521.

The expressive power of a machine learning model is closely related to the number of sequential computational steps it can learn. For example, Deep Neural Networks have been more successful than shallow networks because they can perform a greater number of sequential computational steps (each highly parallel). The Neural Turing Machine (NTM) is a model that can compactly express an even greater number of sequential computational steps, so it is even more powerful than a DNN. Its memory addressing operations are designed to be differentiable; thus the NTM can be trained with backpropagation.
While differentiable memory is relatively easy to implement and train, it necessitates accessing the entire memory content at each computational step. This makes it difficult to implement a fast NTM. In this work, we use the Reinforce algorithm to learn where to access the memory, while using backpropagation to learn what to write to the memory. We call this model the RL-NTM. Reinforce allows our model to access a constant number of memory cells at each computational step, so its implementation can be faster. The RL-NTM is the first model that can, in principle, learn programs of unbounded running time. We successfully trained the RL-NTM to solve a number of algorithmic tasks that are simpler than the ones solvable by the fully differentiable NTM.
As the RL-NTM is a fairly intricate model, we needed a method for verifying the correctness of our implementation. To do so, we developed a simple technique for numerically checking arbitrary implementations of models that use Reinforce, which may be of independent interest.

Posted in: Cognitive sciences , Tagged: , ,

A bayesian framework to explain magnitude estimation in the human mind

May 4, 2015 12:03 ,

Frederike H. Petzschner, Stefan Glasauer, Klaas E. Stephan, A Bayesian perspective on magnitude estimation, Trends in Cognitive Sciences, Volume 19, Issue 5, May 2015, Pages 285-293, ISSN 1364-6613, DOI: 10.1016/j.tics.2015.03.002.

Our representation of the physical world requires judgments of magnitudes, such as loudness, distance, or time. Interestingly, magnitude estimates are often not veridical but subject to characteristic biases. These biases are strikingly similar across different sensory modalities, suggesting common processing mechanisms that are shared by different sensory systems. However, the search for universal neurobiological principles of magnitude judgments requires guidance by formal theories. Here, we discuss a unifying Bayesian framework for understanding biases in magnitude estimation. This Bayesian perspective enables a re-interpretation of a range of established psychophysical findings, reconciles seemingly incompatible classical views on magnitude estimation, and can guide future investigations of magnitude estimation and its neurobiological mechanisms in health and in psychiatric diseases, such as schizophrenia.

Posted in: Psycho-physiological bases of engineering , Tagged:

Reinforcement learning to explain emotions

May 4, 2015 11:59 ,

Joost Broekensa, Elmer Jacobsa & Catholijn M. Jonker, A reinforcement learning model of joy, distress, hope and fear, Connection Science, DOI: 10.1080/09540091.2015.1031081.

In this paper we computationally study the relation between adaptive behaviour and emotion. Using the reinforcement learning framework, we propose that learned state utility, V(s), models fear (negative) and hope (positive) based on the fact that both signals are about anticipation of loss or gain. Further, we propose that joy/distress is a signal similar to the error signal. We present agent-based simulation experiments that show that this model replicates psychological and behavioural dynamics of emotion. This work distinguishes itself by assessing the dynamics of emotion in an adaptive agent framework – coupling it to the literature on habituation, development, extinction and hope theory. Our results support the idea that the function of emotion is to provide a complex feedback signal for an organism to adapt its behaviour. Our work is relevant for understanding the relation between emotion and adaptation in animals, as well as for human–robot interaction, in particular how emotional signals can be used to communicate between adaptive agents and humans.

Posted in: Psycho-physiological bases of engineering , Tagged: ,