Advice giving has been long explored in artificial intelligence to build robust learning algorithms. We consider advice giving in relational domains where the noise is systematic. The advice is provided as logical statements that are then explicitly considered by the learning algorithm at every update. Our empirical evidence proves that human advice can effectively accelerate learning in noisy structured domains where so far humans have been merely used as labelers or as designers of initial structure of the model.

Bayesian reinforcement learning (BRL) provides a principled framework for optimal exploration-exploitation tradeoff in reinforcement learning. We focus on model based BRL, which involves a compact formulation of the optimal tradeoff from the Bayesian perspective. However, it still remains a computational challenge to compute the Bayes-optimal policy. In this paper, we propose a novel approach to compute tighter value function bounds of the Bayes-optimal value function, which is crucial for improving the performance of many model-based BRL algorithms. We then present how our bounds can be integrated into real-time AO* heuristic search, and provide a theoretical analysis on the impact of improved bounds on the search efficiency. We also provide empirical results on standard BRL domains that demonstrate the effectiveness of our approach.

Two other algorithms require the knowledge Markov Decision Processes (MDPs) offer a general framework of the optimal policy and its expected reward. We show to describe probabilistic planning problems of varying that the expected reward of the optimal policy is a lower complexity. The development of algorithms that act successfully bound for the expected performance of both strategies. in MDPs is important to many AI applications. Our final algorithm switches between the application of Since it is often impossible or intractable to evaluate MDP the optimal policy and the policy with the highest possible algorithms based on a theoretical analysis alone, the International outcome, which can be computed without notable overhead Probabilistic Planning Competition (IPPC) was introduced in the Trial-based Heuristic Tree Search (THTS) framework to allow a comparison based on experimental evaluation. (Keller and Helmert 2013). We show theoretically and empirically The idea is to approximate the quality of an MDP that all algorithms outperform the naïve base approach solver by performing a sequence of runs on a problem instance, that ignores the potential of optimizing evaluation and by using the average of the obtained results as runs in hindsight, and that it pays off to take suboptimal base an approximation of the expected reward.

Several heuristic search algorithms such as A* and breadth-first branch and bound have been developed for learning Bayesian network structures that optimize a scoring function. These algorithms rely on a lower bound function called k-cycle conflict heuristic in guiding the search to explore the most promising search spaces. The heuristic takes as input a partition of the random variables of a data set; the importance of the partition opens up opportunities for further research. This work introduces a new partition method based on information extracted from the potential optimal parent sets (POPS) of the variables. Empirical results show that the new partition can significantly improve the efficiency and scalability of heuristic search-based structure learning algorithms.

We consider the problem of, given a probabilistic model on a set of random variables, how to add a new variable that depends on the other variables, without changing the original distribution. In particular, we consider relational models (such as Markov logic networks (MLNs)), where we cannot directly define conditional probabilities. In relational models, there may be an unbounded number of parents in the grounding, and conditional distributions need to be defined in terms of aggregators. The question we ask is whether and when it is possible to represent conditional probabilities at all in various relational models. Some aggregators have been shown to be representable by MLNs, by adding auxiliary variables; however it was unknown whether they could be defined without auxiliary variables. For other aggregators, it was not known whether they can be represented by MLNs at all. We obtained surprisingly strong negative results on the capability of flexible undirected relational models such as MLNs to represent aggregators without affecting the original model's distribution. We provide a map of what aspects of the models, including the use of auxiliary variables and quantifiers, result in the ability to represent various aggregators. In addition, we provide proof techniques which can be used to facilitate future theoretic results on relational models, and demonstrate them on relational logistic regression (RLR).

Controlling for selection and confounding biases are two of the most challenging problems that appear in data analysis in the empirical sciences as well as in artificial intelligence tasks. The combination of previously studied methods for each of these biases in isolation is not directly applicable to certain non-trivial cases in which selection and confounding biases are simultaneously present. In this paper, we tackle these instances non-parametrically and in full generality. We provide graphical and algorithmic conditions for recoverability of interventional distributions for when selection and confounding biases are both present. Our treatment completely characterizes the class of causal effects that are recoverable in Markovian models, and is suffi- cient for Semi-Markovian models.

The defining characteristic the SDVRP, where vehicle capacity and customer demands of the SDVRP that distinguishes it from the classical are not required to be integer numbers, the number of vehicles vehicle routing problem (VRP) is that each customer is not limited to the minimum possible number, and can be served by more than one vehicle. Obviously, when the customer demands may exceed the vehicle capacity. The the demand of a customer is lager than the vehicle capacity, main contributions are threefold. First, we find a novel way it has to be split and the customer has to be visited more to represent the solutions of the SDVRP, which is the combination than once. As shown by (Dror and Trudeau 1989), when all of a set of vehicle routes and a forest. Second, based customer demands are less than or equal to the vehicle capacity, on this solution representation, we propose three classes of split delivery can also lead to substantial cost savings.

Heuristic search is a state-of-the-art approach to classical planning. Several heuristic families were developed over the years to automatically estimate goal distance information from problem descriptions. Orthogonally to the development of better heuristics, recent years have seen an increasing interest in symmetry-based state space pruning techniques that aim at reducing the search effort. However, little work has dealt with how the heuristics behave under symmetries. We investigate the symmetry properties of existing heuristics and reveal that many of them are invariant under symmetries.

A key challenge in the design of multi-sensor systems is the efficient allocation of scarce resources such as bandwidth, CPU cycles, and energy, leading to the dynamic sensor selection problem in which a subset of the available sensors must be selected at each timestep. While partially observable Markov decision processes (POMDPs) provide a natural decision-theoretic model for this problem, the computational cost of POMDP planning grows exponentially in the number of sensors, making it feasible only for small problems. We propose a new POMDP planning method that uses greedy maximization to greatly improve scalability in the number of sensors. We show that, under certain conditions, the value function of a dynamic sensor selection POMDP is submodular and use this result to bound the error introduced by performing greedy maximization. Experimental results on a real-world dataset from a multi-camera tracking system in a shopping mall show it achieves similar performance to existing methods but incurs only a fraction of the computational cost, leading to much better scalability in the number of cameras.

Planning in large partially observable Markov decision processes (POMDPs) is challenging especially when a long planning horizon is required. A few recent algorithms successfully tackle this case but at the expense of a weaker information-gathering capacity. In this paper, we propose Information Gathering and Reward Exploitation of Subgoals (IGRES), a randomized POMDP planning algorithm that leverages information in the state space to automatically generate "macro-actions" to tackle tasks with long planning horizons, while locally exploring the belief space to allow effective information gathering. Experimental results show that IGRES is an effective multi-purpose POMDP solver, providing state-of-the-art performance for both long horizon planning tasks and information-gathering tasks on benchmark domains. Additional experiments with an ecological adaptive management problem indicate that IGRES is a promising tool for POMDP planning in real-world settings.