Golog and ConGolog are languages defined in the situation calculus for cognitive robotics. Given a Golog program \delta, its semantics is defined by a macro Do(\delta,s,s') that expands to a logical sentence that captures the conditions under which performing \delta in s can terminate in s'. A similarmacro is defined for ConGolog programs. In general, the logical sentences that these macros expand to are second-order, and in the case of ConGolog, may involve quantification over programs. In this paper, we show that by making use of the foundational axioms in the situation calculus, in particular, the second-order closure axiom about the space of situations, these macro expressions can actually be defined using first-order sentences.

Golog and ConGolog are languages defined in the situation calculus for cognitive robotics. Given a Golog program \delta, its semantics is defined by a macro Do(\delta,s,s') that expands to a logical sentence that captures the conditions under which performing \delta in s can terminate in s'. A similarmacro is defined for ConGolog programs. In general, the logical sentences that these macros expand to are second-order, and in the case of ConGolog, may involve quantification over programs. In this paper, we show that by making use of the foundational axioms in the situation calculus, in particular, the second-order closure axiom about the space of situations, these macro expressions can actually be defined using first-order sentences.

Golog and ConGolog are languages defined in the situation calculus for cognitive robotics. Given a Golog program \delta, its semantics is defined by a macro Do(\delta,s,s') that expands to a logical sentence that captures the conditions under which performing \delta in s can terminate in s'. A similarmacro is defined for ConGolog programs. In general, the logical sentences that these macros expand to are second-order, and in the case of ConGolog, may involve quantification over programs. In this paper, we show that by making use of the foundational axioms in the situation calculus, in particular, the second-order closure axiom about the space of situations, these macro expressions can actually be defined using first-order sentences.

Golog and ConGolog are languages defined in the situation calculus for cognitive robotics. Given a Golog program \delta, its semantics is defined by a macro Do(\delta,s,s') that expands to a logical sentence that captures the conditions under which performing \delta in s can terminate in s'. A similarmacro is defined for ConGolog programs. In general, the logical sentences that these macros expand to are second-order, and in the case of ConGolog, may involve quantification over programs. In this paper, we show that by making use of the foundational axioms in the situation calculus, in particular, the second-order closure axiom about the space of situations, these macro expressions can actually be defined using first-order sentences.

Golog and ConGolog are languages defined in the situation calculus for cognitive robotics. Given a Golog program \delta, its semantics is defined by a macro Do(\delta,s,s') that expands to a logical sentence that captures the conditions under which performing \delta in s can terminate in s'. A similarmacro is defined for ConGolog programs. In general, the logical sentences that these macros expand to are second-order, and in the case of ConGolog, may involve quantification over programs. In this paper, we show that by making use of the foundational axioms in the situation calculus, in particular, the second-order closure axiom about the space of situations, these macro expressions can actually be defined using first-order sentences.

Tackling large approximate dynamic programming or reinforcement learning problems requires methods that can exploit regularities, or intrinsic structure, of the problem in hand. Most current methods are geared towards exploiting the regularities of either the value function or the policy. We introduce a general classification-based approximate policy iteration (CAPI) framework, which encompasses a large class of algorithms that can exploit regularities of both the value function and the policy space, depending on what is advantageous. This framework has two main components: a generic value function estimator and a classifier that learns a policy based on the estimated value function. We establish theoretical guarantees for the sample complexity of CAPI-style algorithms, which allow the policy evaluation step to be performed by a wide variety of algorithms (including temporal-difference-style methods), and can handle nonparametric representations of policies. Our bounds on the estimation error of the performance loss are tighter than existing results. We also illustrate this approach empirically on several problems, including a large HIV control task.

The learning with privileged information setting has recently attracted a lot of attention within the machine learning community, as it allows the integration of additional knowledge into the training process of a classifier, even when this comes in the form of a data modality that is not available at test time. Here, we show that privileged information can naturally be treated as noise in the latent function of a Gaussian Process classifier (GPC). That is, in contrast to the standard GPC setting, the latent function is not just a nuisance but a feature: it becomes a natural measure of confidence about the training data by modulating the slope of the GPC sigmoid likelihood function. Extensive experiments on public datasets show that the proposed GPC method using privileged noise, called GPC+, improves over a standard GPC without privileged knowledge, and also over the current state-of-the-art SVM-based method, SVM+. Moreover, we show that advanced neural networks and deep learning methods can be compressed as privileged information.

Nearest neighbor methods are a popular class of nonparametric estimators with several desirable properties, such as adaptivity to different distance scales in different regions of space. Prior work on convergence rates for nearest neighbor classification has not fully reflected these subtle properties. We analyze the behavior of these estimators in metric spaces and provide finite-sample, distribution-dependent rates of convergence under minimal assumptions. As a by-product, we are able to establish the universal consistency of nearest neighbor in a broader range of data spaces than was previously known. We illustrate our upper and lower bounds by introducing smoothness classes that are customized for nearest neighbor classification.

Heuristic functions based on the delete relaxation compute upper and lower bounds on the optimal delete-relaxation heuristic h+, and are of paramount importance in both optimal and satisficing planning. Here we introduce a principled and flexible technique for improving h+, by augmenting delete-relaxed planning tasks with a limited amount of delete information. This is done by introducing special fluents that explicitly represent conjunctions of fluents in the original planning task, rendering h+ the perfect heuristic h* in the limit. Previous work has introduced a method in which the growth of the task is potentially exponential in the number of conjunctions introduced. We formulate an alternative technique relying on conditional effects, limiting the growth of the task to be linear in this number. We show that this method still renders h+ the perfect heuristic h* in the limit. We propose techniques to find an informative set of conjunctions to be introduced in different settings, and analyze and extend existing methods for lower-bounding and upper-bounding h+ in the presence of conditional effects. We evaluate the resulting heuristic functions empirically on a set of IPC benchmarks, and show that they are sometimes much more informative than standard delete-relaxation heuristics.

This paper describes a polynomially-solvable class of temporal planning problems. Polynomiality follows from two assumptions. Firstly, by supposing that each sub-goal fluent can be established by at most one action, we can quickly determine which actions are necessary in any plan. Secondly, the monotonicity of sub-goal fluents allows us to express planning as an instance of STP≠ (Simple Temporal Problem with difference constraints). This class includes temporally-expressive problems requiring the concurrent execution of actions, with potential applications in the chemical, pharmaceutical and construction industries. We also show that any (temporal) planning problem has a monotone relaxation which can lead to the polynomial-time detection of its unsolvability in certain cases. Indeed we show that our relaxation is orthogonal to relaxations based on the ignore-deletes approach used in classical planning since it preserves deletes and can also exploit temporal information.