Many games feature a progression of levels that doesn't adapt to the player. This can be problematic because some players may get stuck if the progression is too difficult, while others may find it boring if the progression is too slow to get to more challenging levels. This can be addressed by building levels based on the player's performance and preferences. In this work, we formulate the problem of generating levels for a player as a Markov Decision Process (MDP) and use adaptive dynamic programming (ADP) to solve the MDP before assembling a level. We tested with two case studies and found that using an ADP outperforms two baselines. Furthermore, we experimented with player proxies and switched them in the middle of play, and we show that a simple modification prior to running ADP results in quick adaptation. By using ADP, which searches the entire MDP, we produce a dynamic progression of levels that adapts to the player.
相關內容
Team assembly is a problem that demands trade-offs between multiple fairness criteria and computational optimization. We focus on four criteria: (i) fair distribution of workloads within the team, (ii) fair distribution of skills and expertise regarding project requirements, (iii) fair distribution of protected classes in the team, and (iv) fair distribution of the team cost among protected classes. For this problem, we propose a two-stage algorithmic solution. First, a multi-objective optimization procedure is executed and the Pareto candidates that satisfy the project requirements are selected. Second, N random groups are formed containing combinations of these candidates, and a second round of multi-objective optimization is executed, but this time for selecting the groups that optimize the team-assembly criteria. We also discuss the conflicts between those objectives when trying to understand the impact of fairness constraints in the utility associated with the formed team.
Visual localization is a fundamental task for various applications including autonomous driving and robotics. Prior methods focus on extracting large amounts of often redundant locally reliable features, resulting in limited efficiency and accuracy, especially in large-scale environments under challenging conditions. Instead, we propose to extract globally reliable features by implicitly embedding high-level semantics into both the detection and description processes. Specifically, our semantic-aware detector is able to detect keypoints from reliable regions (e.g. building, traffic lane) and suppress unreliable areas (e.g. sky, car) implicitly instead of relying on explicit semantic labels. This boosts the accuracy of keypoint matching by reducing the number of features sensitive to appearance changes and avoiding the need of additional segmentation networks at test time. Moreover, our descriptors are augmented with semantics and have stronger discriminative ability, providing more inliers at test time. Particularly, experiments on long-term large-scale visual localization Aachen Day-Night and RobotCar-Seasons datasets demonstrate that our model outperforms previous local features and gives competitive accuracy to advanced matchers but is about 2 and 3 times faster when using 2k and 4k keypoints, respectively.
In sim-to-real Reinforcement Learning (RL), a policy is trained in a simulated environment and then deployed on the physical system. The main challenge of sim-to-real RL is to overcome the reality gap - the discrepancies between the real world and its simulated counterpart. Using general geometric representations, such as convex decomposition, triangular mesh, signed distance field can improve simulation fidelity, and thus potentially narrow the reality gap. Common to these approaches is that many contact points are generated for geometrically-complex objects, which slows down simulation and may cause numerical instability. Contact reduction methods address these issues by limiting the number of contact points, but the validity of these methods for sim-to-real RL has not been confirmed. In this paper, we present a contact reduction method with bounded stiffness to improve the simulation accuracy. Our experiments show that the proposed method critically enables training RL policy for a tight-clearance double pin insertion task and successfully deploying the policy on a rigid, position-controlled physical robot.
This thesis studies the domain of collective robotics, and more particularly the optimization problems of multirobot systems in the context of exploration, path planning and coordination. It includes two contributions. The first one is the use of the Butterfly Optimization Algorithm (BOA) to solve the Unknown Area Exploration problem with energy constraints in dynamic environments. This algorithm was never used for solving robotics problems before, as far as we know. We proposed a new version of this algorithm called xBOA based on the crossover operator to improve the diversity of the candidate solutions and speed up the convergence of the algorithm. The second contribution is the development of a new simulation framework for benchmarking dynamic incremental problems in robotics such as exploration tasks. The framework is made in such a manner to be generic to quickly compare different metaheuristics with minimum modifications, and to adapt easily to single and multi-robot scenarios. Also, it provides researchers with tools to automate their experiments and generate visuals, which will allow them to focus on more important tasks such as modeling new algorithms. We conducted a series of experiments that showed promising results and allowed us to validate our approach and model.
Detecting change-points in data is challenging because of the range of possible types of change and types of behaviour of data when there is no change. Statistically efficient methods for detecting a change will depend on both of these features, and it can be difficult for a practitioner to develop an appropriate detection method for their application of interest. We show how to automatically generate new offline detection methods based on training a neural network. Our approach is motivated by many existing tests for the presence of a change-point being representable by a simple neural network, and thus a neural network trained with sufficient data should have performance at least as good as these methods. We present theory that quantifies the error rate for such an approach, and how it depends on the amount of training data. Empirical results show that, even with limited training data, its performance is competitive with the standard CUSUM-based classifier for detecting a change in mean when the noise is independent and Gaussian, and can substantially outperform it in the presence of auto-correlated or heavy-tailed noise. Our method also shows strong results in detecting and localising changes in activity based on accelerometer data.
Recently, sequence learning methods have been applied to the problem of off-policy Reinforcement Learning, including the seminal work on Decision Transformers, which employs transformers for this task. Since transformers are parameter-heavy, cannot benefit from history longer than a fixed window size, and are not computed using recurrence, we set out to investigate the suitability of the S4 family of models, which are based on state-space layers and have been shown to outperform transformers, especially in modeling long-range dependencies. In this work we present two main algorithms: (i) an off-policy training procedure that works with trajectories, while still maintaining the training efficiency of the S4 model. (ii) An on-policy training procedure that is trained in a recurrent manner, benefits from long-range dependencies, and is based on a novel stable actor-critic mechanism. Our results indicate that our method outperforms multiple variants of decision transformers, as well as the other baseline methods on most tasks, while reducing the latency, number of parameters, and training time by several orders of magnitude, making our approach more suitable for real-world RL.
In many industrial applications, obtaining labeled observations is not straightforward as it often requires the intervention of human experts or the use of expensive testing equipment. In these circumstances, active learning can be highly beneficial in suggesting the most informative data points to be used when fitting a model. Reducing the number of observations needed for model development alleviates both the computational burden required for training and the operational expenses related to labeling. Online active learning, in particular, is useful in high-volume production processes where the decision about the acquisition of the label for a data point needs to be taken within an extremely short time frame. However, despite the recent efforts to develop online active learning strategies, the behavior of these methods in the presence of outliers has not been thoroughly examined. In this work, we investigate the performance of online active linear regression in contaminated data streams. Our study shows that the currently available query strategies are prone to sample outliers, whose inclusion in the training set eventually degrades the predictive performance of the models. To address this issue, we propose a solution that bounds the search area of a conditional D-optimal algorithm and uses a robust estimator. Our approach strikes a balance between exploring unseen regions of the input space and protecting against outliers. Through numerical simulations, we show that the proposed method is effective in improving the performance of online active learning in the presence of outliers, thus expanding the potential applications of this powerful tool.
Neural networks are notorious for being overconfident predictors, posing a significant challenge to their safe deployment in real-world applications. While feature normalization has garnered considerable attention within the deep learning literature, current train-time regularization methods for Out-of-Distribution(OOD) detection are yet to fully exploit this potential. Indeed, the naive incorporation of feature normalization within neural networks does not guarantee substantial improvement in OOD detection performance. In this work, we introduce T2FNorm, a novel approach to transforming features to hyperspherical space during training, while employing non-transformed space for OOD-scoring purposes. This method yields a surprising enhancement in OOD detection capabilities without compromising model accuracy in in-distribution(ID). Our investigation demonstrates that the proposed technique substantially diminishes the norm of the features of all samples, more so in the case of out-of-distribution samples, thereby addressing the prevalent concern of overconfidence in neural networks. The proposed method also significantly improves various post-hoc OOD detection methods.
Decision-making algorithms are being used in important decisions, such as who should be enrolled in health care programs and be hired. Even though these systems are currently deployed in high-stakes scenarios, many of them cannot explain their decisions. This limitation has prompted the Explainable Artificial Intelligence (XAI) initiative, which aims to make algorithms explainable to comply with legal requirements, promote trust, and maintain accountability. This paper questions whether and to what extent explainability can help solve the responsibility issues posed by autonomous AI systems. We suggest that XAI systems that provide post-hoc explanations could be seen as blameworthy agents, obscuring the responsibility of developers in the decision-making process. Furthermore, we argue that XAI could result in incorrect attributions of responsibility to vulnerable stakeholders, such as those who are subjected to algorithmic decisions (i.e., patients), due to a misguided perception that they have control over explainable algorithms. This conflict between explainability and accountability can be exacerbated if designers choose to use algorithms and patients as moral and legal scapegoats. We conclude with a set of recommendations for how to approach this tension in the socio-technical process of algorithmic decision-making and a defense of hard regulation to prevent designers from escaping responsibility.
Benefit from the quick development of deep learning techniques, salient object detection has achieved remarkable progresses recently. However, there still exists following two major challenges that hinder its application in embedded devices, low resolution output and heavy model weight. To this end, this paper presents an accurate yet compact deep network for efficient salient object detection. More specifically, given a coarse saliency prediction in the deepest layer, we first employ residual learning to learn side-output residual features for saliency refinement, which can be achieved with very limited convolutional parameters while keep accuracy. Secondly, we further propose reverse attention to guide such side-output residual learning in a top-down manner. By erasing the current predicted salient regions from side-output features, the network can eventually explore the missing object parts and details which results in high resolution and accuracy. Experiments on six benchmark datasets demonstrate that the proposed approach compares favorably against state-of-the-art methods, and with advantages in terms of simplicity, efficiency (45 FPS) and model size (81 MB).
小貼士
登錄享
注冊地址： 北京市海淀區羊坊店路18號2幢3層301-191