Tuning machine learning hyperparameters is a tedious yet crucial task, as the performance of an algorithm can be highly dependent on the choice of hyperparameters. Manual tuning takes time away from important steps of the machine learning pipeline like feature engineering and interpreting results. Grid and random search are hands-off, but require long run times because they waste time evaluating unpromising areas of the search space. Increasingly, hyperparameter tuning is done by automated methods that aim to find optimal hyperparameters in less time using an informed search with no manual effort necessary beyond the initial set-up. Bayesian optimization, a model-based method for finding the minimum of a function, has recently been applied to machine learning hyperparameter tuning, with results suggesting this approach can achieve better performance on the test set while requiring fewer iterations than random search. Moreover, there are now a number of Python libraries that make implementing Bayesian hyperparameter tuning simple for any machine learning model.

The 13th AAAI Conference on Artificial Intelligence and Interactive Digital Entertainment (AIIDE 2017) was held at the Snowbird Ski and Summer Resort in Little Cottonwod Canyon in the Wasatch Range of the Rock Mountains near Salt Lake County, Utah. Along with the main conference presentations, the meeting included two tutorials, three workshops, and invited keynotes. This report summarizes the main conference. It also includes contributions from the organizers of the three workshops.

A self-taught artificial intelligence (AI) system called DeepCube has mastered solving the Rubik's Cube puzzle in just 44 hours without human intervention. The system's inventors have detailed their design in a paper titled'Solving the Rubik's Cube Without Human Knowledge'. "A generally intelligent agent must be able to teach itself how to solve problems in complex domains with minimal human supervision," write the paper's authors. "Indeed, if we're ever going to achieve a general, human-like machine intelligence, we'll have to develop systems that can learn and then apply those learnings to real-world applications." While many AI systems have been taught to play games, mastering the complexity of a Rubik's Cube posed a unique set of challenges.

We present a principled way of extending a classical AI planning formalism with systems of state constraints, which relate - sometimes determine - the values of variables in each state traversed by the plan. This extension occupies an attractive middle ground between expressivity and complexity. It enables modelling a new range of problems, as well as formulating more efficient models of classical planning problems. An example of the former is planning-based control of networked physical systems - power networks, for example - in which a local, discrete control action can have global effects on continuous quantities, such as altering flows across the entire network. At the same time, our extension remains decidable as long as the satisfiability of sets of state constraints is decidable, including in the presence of numeric state variables, and we demonstrate that effective techniques for cost-optimal planning known in the classical setting - in particular, relaxation-based admissible heuristics - can be adapted to the extended formalism. In this paper, we apply our approach to constraints in the form of linear or non-linear equations over numeric state variables, but the approach is independent of the type of state constraints, as long as there exists a procedure that decides their consistency. The planner and the constraint solver interact through a well-defined, narrow interface, in which the solver requires no specialisation to the planning context.

Artificial Intelligence is becoming instrumental in a variety of applications. Games serve as a good breeding ground for trying and testing these algorithms in a sandbox with simpler constraints in comparison to real life. In this project, we aim to develop an AI agent that can solve the classical Japanese game of Sokoban using various algorithms and heuristics and compare their performances through standard metrics. In this progress report, we delve deeper into the ideas furnished in our proposal by (1) pointing out the game mechanics in a straightforward manner (2) describing the states and explaining how it is modeled in our algorithms (3) detailing our algorithms to calculate the best moves for the levels of the game (4) defining proper pruning techniques that are implemented to ameliorate the performance of the algorithm (5) providing results and comparing the developed algorithm using standard metrics of evaluation. We conclude with the next steps we plan to take up to finish this project.

Dial-a-ride problem (DARP) deals with the transportation of users between pickup and drop-off locations associated with specified time windows. This paper proposes a novel algorithm called multi-atomic annealing (MATA) to solve static dial-a-ride problem. Two new local search operators (burn and reform), a new construction heuristic and two request sequencing mechanisms (Sorted List and Random List) are developed. Computational experiments conducted on various standard DARP test instances prove that MATA is an expeditious meta-heuristic in contrast to other existing methods. In all experiments, MATA demonstrates the capability to obtain high quality solutions, faster convergence, and quicker attainment of a first feasible solution. It is observed that MATA attains a first feasible solution 29.8 to 65.1% faster, and obtains a final solution that is 3.9 to 5.2% better, when compared to other algorithms within 60 sec.

Given a classifier ensemble and a set of examples to be classified, many examples may be confidently and accurately classified after only a subset of the base models in the ensemble are evaluated. This can reduce both mean latency and CPU while maintaining the high accuracy of the original ensemble. To achieve such gains, we propose jointly optimizing a fixed evaluation order of the base models and early-stopping thresholds. Our proposed objective is a combinatorial optimization problem, but we provide a greedy algorithm that achieves a 4-approximation of the optimal solution for certain cases. For those cases, this is also the best achievable polynomial time approximation bound unless $P = NP$. Experiments on benchmark and real-world problems show that the proposed Quit When You Can (QWYC) algorithm can speed-up average evaluation time by $2$x--$4$x, and is around $1.5$x faster than prior work. QWYC's joint optimization of ordering and thresholds also performed better in experiments than various fixed orderings, including gradient boosted trees' ordering.

Multiplayer Online Battle Arena (MOBA) games have received increasing popularity recently. In a match of such games, players compete in two teams of five, each controlling an in-game avatars, known as heroes, selected from a roster of more than 100. The selection of heroes, also known as pick or draft, takes place before the match starts and alternates between the two teams until each player has selected one hero. Heroes are designed with different strengths and weaknesses to promote team cooperation in a game. Intuitively, heroes in a strong team should complement each other's strengths and suppressing those of opponents. Hero drafting is therefore a challenging problem due to the complex hero-to-hero relationships to consider. In this paper, we propose a novel hero recommendation system that suggests heroes to add to an existing team while maximizing the team's prospect for victory. To that end, we model the drafting between two teams as a combinatorial game and use Monte Carlo Tree Search (MCTS) for estimating the values of hero combinations. Our empirical evaluation shows that hero teams drafted by our recommendation algorithm have significantly higher win rate against teams constructed by other baseline and state-of-the-art strategies.

The most data-efficient algorithms for reinforcement learning in robotics are model-based policy search algorithms, which alternate between learning a dynamical model of the robot and optimizing a policy to maximize the expected return given the model and its uncertainties. However, the current algorithms lack an effective exploration strategy to deal with sparse or misleading reward scenarios: if they do not experience any state with a positive reward during the initial random exploration, it is very unlikely to solve the problem. Here, we propose a novel model-based policy search algorithm, Multi-DEX, that leverages a learned dynamical model to efficiently explore the task space and solve tasks with sparse rewards in a few episodes. To achieve this, we frame the policy search problem as a multi-objective, model-based policy optimization problem with three objectives: (1) generate maximally novel state trajectories, (2) maximize the expected return and (3) keep the system in state-space regions for which the model is as accurate as possible. We then optimize these objectives using a Pareto-based multi-objective optimization algorithm. The experiments show that Multi-DEX is able to solve sparse reward scenarios (with a simulated robotic arm) in much lower interaction time than VIME, TRPO, GEP-PG, CMA-ES and Black-DROPS.

Deck building is a crucial component in playing Collectible Card Games (CCGs). The goal of deck building is to choose a fixed-sized subset of cards from a large card pool, so that they work well together in-game against specific opponents. Existing methods either lack flexibility to adapt to different opponents or require large computational resources, still making them unsuitable for any real-time or large-scale application. We propose a new deck recommendation system, named Q-DeckRec, which learns a deck search policy during a training phase and uses it to solve deck building problem instances. Our experimental results demonstrate Q-DeckRec requires less computational resources to build winning-effective decks after a training phase compared to several baseline methods.