Learning to perceive in the sensor motor approach: Piaget's theory of equilibration interpreted dynamically

Learning to perceive is faced with a classical paradox: if understanding is required for perception, how can we learn to perceive something new, something we do not yet understand? According to the sensorimotor approach, perception involves mastery of regular sensorimotor co-variations that depend on the agent and the environment, also known as the "laws" of sensorimotor contingencies (SMCs). In this sense, perception involves enacting relevant sensorimotor skills in each situation. It is important for this proposal that such skills can be learned and refined with experience and yet up to this date, the sensorimotor approach has had no explicit theory of perceptual learning. The situation is made more complex if we acknowledge the open-ended nature of human learning. In this paper we propose Piaget's theory of equilibration as a potential candidate to fulfill this role. This theory highlights the importance of intrinsic sensorimotor norms, in terms of the closure of sensorimotor schemes. It also explains how the equilibration of a sensorimotor organization faced with novelty or breakdowns proceeds by re-shaping pre-existing structures in coupling with dynamical regularities of the world. This way learning to perceive is guided by the equilibration of emerging forms of skillful coping with the world. We demonstrate the compatibility between Piaget's theory and the sensorimotor approach by providing a dynamical formalization of equilibration to give an explicit micro-genetic account of sensorimotor learning and, by extension, of how we learn to perceive. This allows us to draw important lessons in the form of general principles for open-ended sensorimotor learning, including the need for an intrinsic normative evaluation by the agent itself. We also explore implications of our micro-genetic account at the personal level.

Learning Multirobot Hose Transportation and Deployment by Distributed Round-Robin Q-Learning

Multi-Agent Reinforcement Learning (MARL) algorithms face two main difficulties: the curse of dimensionality, and environment non-stationarity due to the independent learning processes carried out by the agents concurrently. In this paper we formalize and prove the convergence of a Distributed Round Robin Q-learning (D-RR-QL) algorithm for cooperative systems. The computational complexity of this algorithm increases linearly with the number of agents. Moreover, it eliminates environment non sta tionarity by carrying a round-robin scheduling of the action selection and execution. That this learning scheme allows the implementation of Modular State-Action Vetoes (MSAV) in cooperative multi-agent systems, which speeds up learning convergence in over-constrained systems by vetoing state-action pairs which lead to undesired termination states (UTS) in the relevant state-action subspace. Each agent's local state-action value function learning is an independent process, including the MSAV policies. Coordination of locally optimal policies to obtain the global optimal joint policy is achieved by a greedy selection procedure using message passing. We show that D-RR-QL improves over state-of-the-art approaches, such as Distributed Q-Learning, Team Q-Learning and Coordinated Reinforcement Learning in a paradigmatic Linked Multi-Component Robotic System (L-MCRS) control problem: the hose transportation task. L-MCRS are over-constrained systems with many UTS induced by the interaction of the passive linking element and the active mobile robots.

Learning from implementation of community selection in Zambia, Solomon Islands, and Bangladesh AAS hubs

The CGIAR Research Program on Aquatic Agricultural Systems (AAS) is a research in development program which aims to foster innovation to respond to community needs, and through networking and social learning to bring about development outcomes and impact at scale. It aims to reach the poorest and most vulnerable communities that are dependent upon aquatic agricultural systems. AAS uses monitoring and evaluation to track progress along identified impact pathways for accountability and learning. This report presents an evaluation of the recommended method for selecting communities during the participatory planning process, referred to as AAS “hub rollout,” in the first year of program implementation.

Solomon Islands Aquatic Agricultural Systems Program design document

WorldFish is leading the CGIAR Research Program on Aquatic Agricultural Systems together with two other CGIAR Centers; the International Water Management Institute (IWMI) and Bioversity. In 2012 and 2013 the AAS Program rolled out in Solomon Islands, Zambia, Bangladesh, Cambodia and the Philippines. Aquatic Agricultural Systems are places where farming and fishing in freshwater and/or coastal ecosystems contribute significantly to household income and food security. The program goal is to improve the well-being of AAS-dependent people. A hub is a geographic location that provides a focus for learning, innovation and impact through participatory action research. In Solomon Islands AAS works in Malaita Hub (Malaita Province) and Western Hub (Western Province). In each hub we identify a ‘Development Challenge’ that the Program will address to give us focus and motivation.

Phone-level pronunciation scoring and assessment for interactive language learning

This paper investigates a method of automatic pronunciation scoring for use in computer-assisted language learning (CALL) systems. The method utilizes a likelihood-based `Goodness of Pronunciation' (GOP) measure which is extended to include individual thresholds for each phone based on both averaged native confidence scores and on rejection statistics provided by human judges. Further improvements are obtained by incorporating models of the subject's native language and by augmenting the recognition networks to include expected pronunciation errors. The various GOP measures are assessed using a specially recorded database of non-native speakers which has been annotated to mark phone-level pronunciation errors. Since pronunciation assessment is highly subjective, a set of four performance measures has been designed, each of them measuring different aspects of how well computer-derived phone-level scores agree with human scores. These performance measures are used to cross-validate the reference annotations and to assess the basic GOP algorithm and its refinements. The experimental results suggest that a likelihood-based pronunciation scoring metric can achieve usable performance, especially after applying the various enhancements.

Dynamic learning with the EM algorithm for neural networks

In this paper, we derive an EM algorithm for nonlinear state space models. We use it to estimate jointly the neural network weights, the model uncertainty and the noise in the data. In the E-step we apply a forwardbackward Rauch-Tung-Striebel smoother to compute the network weights. For the M-step, we derive expressions to compute the model uncertainty and the measurement noise. We find that the method is intrinsically very powerful, simple and stable.

On-line policy optimisation of spoken dialogue systems via live interaction with human subjects

Statistical dialogue models have required a large number of dialogues to optimise the dialogue policy, relying on the use of a simulated user. This results in a mismatch between training and live conditions, and significant development costs for the simulator thereby mitigating many of the claimed benefits of such models. Recent work on Gaussian process reinforcement learning, has shown that learning can be substantially accelerated. This paper reports on an experiment to learn a policy for a real-world task directly from human interaction using rewards provided by users. It shows that a usable policy can be learnt in just a few hundred dialogues without needing a user simulator and, using a learning strategy that reduces the risk of taking bad actions. The paper also investigates adaptation behaviour when the system continues learning for several thousand dialogues and highlights the need for robustness to noisy rewards. © 2011 IEEE.

Exploring key sustainable development themes through learning activities

Purpose: The paper examines how a number of key themes are introduced in the Masters programme in Engineering for Sustainable Development at Cambridge University through student centred activities. These themes include dealing with complexity, uncertainty, change, other disciplines, people, environmental limits, whole life costs, and trade-offs. Design/methodology/approach: The range of exercises and assignments designed to encourage students to test their own assumptions and abilities to develop competencies in these areas are analysed by mapping the key themes onto the formal activities which all students undertake throughout the core MPhil programme. The paper reviews the range of these activities that are designed to help support the formal delivery of the taught programme. These include residential field courses, role plays, change challenges, games, systems thinking, multi criteria decision making, awareness of literature from other disciplines and consultancy projects. An axial coding approach to the analysis of routine feedback questionnaires drawn from recent years has been used to identify how student’s own awareness develops. Also results of two surveys are presented which tests the students’ perceptions about whether or not the course is providing learning environments to develop awareness and skills in these areas. Findings: Students generally perform well against these tasks with a significant feature being the mutual support they give to each other in their learning. The paper concludes that for students from an engineering background it is an holistic approach to delivering a new way of thinking through a combination of lectures, class activities, assignments, interactions between class members, and access to material elsewhere in the University that enables participants to develop their skills in each of the key themes. Originality /value: The paper provides a reflection on different pedagogical approaches to exploring key sustainable themes and reports students own perceptions of the value of these kinds of activities. Experiences are shared of running a range of diverse learning activities within a professional practice Masters programme.

ℓasso MPC: Smart regulation of over-actuated systems

In this paper, a novel MPC strategy is proposed, and referred to as asso MPC. The new paradigm features an 1-regularised least squares loss function, in which the control error variance competes with the sum of input channels magnitude (or slew rate) over the whole horizon length. This cost choice is motivated by the successful development of LASSO theory in signal processing and machine learning. In the latter fields, sum-of-norms regularisation have shown a strong capability to provide robust and sparse solutions for system identification and feature selection. In this paper, a discrete-time dual-mode asso MPC is formulated, and its stability is proven by application of standard MPC arguments. The controller is then tested for the problem of ship course keeping and roll reduction with rudder and fins, in a directional stochastic sea. Simulations show the asso MPC to inherit positive features from its corresponding regressor: extreme reduction of decision variables' magnitude, namely, actuators' magnitude (or variations), with a finite energy error, being particularly promising for over-actuated systems. © 2012 AACC American Automatic Control Council).