This paper introduces a new system to design constructive level generators by searching the space of constructive level generators defined by Marahel language. We use NSGA-II, a multi-objective optimization algorithm, to search for generators for three different problems (Binary, Zelda, and Sokoban). We restrict the representation to a subset of Marahel language to push the evolution to find more efficient generators. The results show that the generated generators were able to achieve good performance on most of the fitness functions over these three problems. However, on Zelda and Sokoban, they tend to depend on the initial state than modifying the map.

The ability to jointly understand the geometry of objects and plan actions for manipulating them is crucial for intelligent agents. We refer to this ability as geometric planning. Recently, many interactive environments have been proposed to evaluate intelligent agents on various skills, however, none of them cater to the needs of geometric planning. We present PackIt, a virtual environment to evaluate and potentially learn the ability to do geometric planning, where an agent needs to take a sequence of actions to pack a set of objects into a box with limited space. We also construct a set of challenging packing tasks using an evolutionary algorithm. Further, we study various baselines for the task that include model-free learning-based and heuristic-based methods, as well as search-based optimization methods that assume access to the model of the environment. Code and data are available at https://github.com/princeton-vl/PackIt.

In this paper, three recently introduced reinforcement learning (RL) methods are used to generate human-interpretable policies for the cart-pole balancing benchmark. The novel RL methods learn human-interpretable policies in the form of compact fuzzy controllers and simple algebraic equations. The representations as well as the achieved control performances are compared with two classical controller design methods and three non-interpretable RL methods. All eight methods utilize the same previously generated data batch and produce their controller offline - without interaction with the real benchmark dynamics. The experiments show that the novel RL methods are able to automatically generate well-performing policies which are at the same time human-interpretable. Furthermore, one of the methods is applied to automatically learn an equation-based policy for a hardware cart-pole demonstrator by using only human-player-generated batch data. The solution generated in the first attempt already represents a successful balancing policy, which demonstrates the methods applicability to real-world problems.

Purpose: This paper presents an algorithm that can elicitate (infer) all or any combination of ELECTRE Tri-B parameters. For example, a decision-maker can maintain the values for indifference, preference, and veto thresholds, and our algorithm can find the criteria weights, reference profiles, and the lambda cutting level. Our approach is inspired by a Machine Learning ensemble technique, the Random Forest, and for that, we named our approach as ELECTRE Tree algorithm. Methodology: First, we generate a set of ELECTRE Tri-B models, where each model solves a random sample of criteria and alternatives. Each sample is made with replacement, having at least two criteria and between 10% to 25% of alternatives. Each model has its parameters optimized by a genetic algorithm that can use an ordered cluster or an assignment example as a reference to the optimization. Finally, after the optimization phase, two procedures can be performed, the first one will merge all models, finding in this way the elicitated parameters, and in the second procedure each alternative is classified (voted) by each separated model, and the majority vote decides the final class. Findings: We have noted that concerning the voting procedure, non-linear decision boundaries are generated, and they can be suitable in analyzing problems with the same nature. In contrast, the merged model generates linear decision boundaries. Originality: The elicitation of ELECTRE Tri-B parameters is made by an ensemble technique that is composed of a set of multicriteria models that are engaged in generating robust solutions.

We present a novel algorithm -- convex natural evolutionary strategies (CoNES) -- for optimizing high-dimensional blackbox functions by leveraging tools from convex optimization and information geometry. CoNES is formulated as an efficiently-solvable convex program that adapts the evolutionary strategies (ES) gradient estimate to promote rapid convergence. The resulting algorithm is invariant to the parameterization of the belief distribution. Our numerical results demonstrate that CoNES vastly outperforms conventional blackbox optimization methods on a suite of functions used for benchmarking blackbox optimizers. Furthermore, CoNES demonstrates the ability to converge faster than conventional blackbox methods on a selection of OpenAI's MuJoCo reinforcement learning tasks for locomotion.

Drone swarms frequently fly outside for a reason: it's difficult for the robotic fliers to navigate in tight spaces without hitting each other. Caltech researchers may have a way for those drones to fly indoors, however. They've developed a machine learning algorithm, Global-to-Local Safe Autonomy Synthesis (GLAS), that lets swarms navigate crowded, unmapped environments. The system works by giving each drone a degree of independence that lets it adapt to a changing environment. Instead of relying on existing maps or the routes of every other drone in the swarm, GLAS has each machine learning how to navigate a given space on its own even as it coordinates with others.

A key factor in the modern success of deep learning is the astonishing expressive power of neural networks. However, this comes at the cost of complex, black-boxed models that are unable to extrapolate beyond the domain of the training dataset, conflicting with goals of expressing physical laws or building human-readable programs. In this paper, we introduce OccamNet, a neural network model that can find interpretable, compact and sparse solutions for fitting data, \`{a} la Occam's razor. Our model defines a probability distribution over a non-differentiable function space, and we introduce an optimization method that samples functions and updates the weights based on cross-entropy matching in an evolutionary strategy: we train by biasing the probability mass towards better fitting solutions. We demonstrate that we can fit a variety of algorithms, ranging from simple analytic functions through recursive programs to even simple image classification. Our method takes minimal memory footprint, does not require AI accelerators for efficient training, fits complicated functions in minutes of training on a single CPU, and demonstrates significant performance gains when scaled on GPU. Our implementation, demonstrations and instructions for reproducing the experiments are available at https://github.com/AllanSCosta/occam-net.

I just heard from those clever chaps and chapesses at Algolux, who tell me they are using an evolutionary algorithm approach in their Atlas Camera Optimization Suite, which -- they say -- is the industry's first set of machine-learning tools and workflows that can automatically optimize camera architectures intended for computer vision applications. As we will see, this is exciting on many levels, not the least that it prompted me to start cogitating, ruminating, and musing on the possibilities that might ensue from combining evolutionary algorithms (EAs) and genetic algorithms (GAs) with artificial intelligence (AI). But before we plunge headfirst into the fray with gusto and abandon (and aplomb, of course), let's remind ourselves that not everyone may be as familiar with things like genetic algorithms as you and yours truly, so let's take a slight diversion to bring everyone up to speed. Personally, I find the entire concept of genetic algorithms to be tremendously exciting. John Henry Holland (1929 – 2015) was an American scientist and Professor of psychology and Professor of electrical engineering and computer science at the University of Michigan, Ann Arbor.

As modern neural networks have grown to billions of parameters, meeting tight latency budgets has become increasingly challenging. Approaches like compression, sparsification and network pruning have proven effective to tackle this problem - but they rely on modifications of the underlying network. In this paper, we look at a complimentary approach of optimizing how tensors are mapped to on-chip memory in an inference accelerator while leaving the network parameters untouched. Since different memory components trade off capacity for bandwidth differently, a sub-optimal mapping can result in high latency. We introduce evolutionary graph reinforcement learning (EGRL) - a method combining graph neural networks, reinforcement learning (RL) and evolutionary search - that aims to find the optimal mapping to minimize latency. Furthermore, a set of fast, stateless policies guide the evolutionary search to improve sample-efficiency. We train and validate our approach directly on the Intel NNP-I chip for inference using a batch size of 1. EGRL outperforms policy-gradient, evolutionary search and dynamic programming baselines on BERT, ResNet-101 and ResNet-50. We achieve 28-78% speed-up compared to the native NNP-I compiler on all three workloads.

Nonlinear equations systems (NESs) are widely used in real-world problems while they are also difficult to solve due to their characteristics of nonlinearity and multiple roots. Evolutionary algorithm (EA) is one of the methods for solving NESs, given their global search capability and an ability to locate multiple roots of a NES simultaneously within one run. Currently, the majority of research on using EAs to solve NESs focuses on transformation techniques and improving the performance of the used EAs. By contrast, the problem domain knowledge of NESs is particularly investigated in this study, using which we propose to incorporate the variable reduction strategy (VRS) into EAs to solve NESs. VRS makes full use of the systems of expressing a NES and uses some variables (i.e., core variable) to represent other variables (i.e., reduced variables) through the variable relationships existing in the equation systems. It enables to reduce partial variables and equations and shrink the decision space, thereby reducing the complexity of the problem and improving the search efficiency of the EAs. To test the effectiveness of VRS in dealing with NESs, this paper integrates VRS into two existing state-of-the-art EA methods (i.e., MONES and DRJADE), respectively. Experimental results show that, with the assistance of VRS, the EA methods can significantly produce better results than the original methods and other compared methods.