亚洲男人的天堂2018av,欧美草比,久久久久久免费视频精选,国色天香在线看免费,久久久久亚洲av成人片仓井空

Flexible, goal-directed behavior is a fundamental aspect of human life. Based on the free energy minimization principle, the theory of active inference formalizes the generation of such behavior from a computational neuroscience perspective. Based on the theory, we introduce an output-probabilistic, temporally predictive, modular artificial neural network architecture, which processes sensorimotor information, infers behavior-relevant aspects of its world, and invokes highly flexible, goal-directed behavior. We show that our architecture, which is trained end-to-end to minimize an approximation of free energy, develops latent states that can be interpreted as affordance maps. That is, the emerging latent states signal which actions lead to which effects dependent on the local context. In combination with active inference, we show that flexible, goal-directed behavior can be invoked, incorporating the emerging affordance maps. As a result, our simulated agent flexibly steers through continuous spaces, avoids collisions with obstacles, and prefers pathways that lead to the goal with high certainty. Additionally, we show that the learned agent is highly suitable for zero-shot generalization across environments: After training the agent in a handful of fixed environments with obstacles and other terrains affecting its behavior, it performs similarly well in procedurally generated environments containing different amounts of obstacles and terrains of various sizes at different locations. To improve and focus model learning further, we plan to invoke active inference-based, information-gain-oriented behavior also while learning the temporally predictive model itself in the near future. Moreover, we intend to foster the development of both deeper event-predictive abstractions and compact, habitual behavioral primitives.

Accurate trajectory tracking control for quadrotors is essential for safe navigation in cluttered environments. However, this is challenging in agile flights due to nonlinear dynamics, complex aerodynamic effects, and actuation constraints. In this article, we empirically compare two state-of-the-art control frameworks: the nonlinear-model-predictive controller (NMPC) and the differential-flatness-based controller (DFBC), by tracking a wide variety of agile trajectories at speeds up to 20 m/s (i.e.,72 km/h). The comparisons are performed in both simulation and real-world environments to systematically evaluate both methods from the aspect of tracking accuracy, robustness, and computational efficiency. We show the superiority of NMPC in tracking dynamically infeasible trajectories, at the cost of higher computation time and risk of numerical convergence issues. For both methods, we also quantitatively study the effect of adding an inner-loop controller using the incremental nonlinear dynamic inversion (INDI) method, and the effect of adding an aerodynamic drag model. Our real-world experiments, performed in one of the world's largest motion capture systems, demonstrate more than 78% tracking error reduction of both NMPC and DFBC, indicating the necessity of using an inner-loop controller and aerodynamic drag model for agile trajectory tracking.

Information cross-validation can be a powerful tool to detect manipulated, dubious GNSS data. A promising approach is to leverage time obtained over networks a mobile device can connect to, and detect discrepancies between the GNSS-provided time and the network time. The challenge lies in having reliably both accurate and trustworthy network time as the basis for the GNSS attack detection. Here, we provide a concrete proposal that leverages, together with the network time servers, the nearly ubiquitous IEEE 802.11 (Wi-Fi) infrastructure. Our framework supports application-layer, secure and robust real time broadcasting by Wi-Fi Access Points (APs), based on hash chains and infrequent digital signatures verification to minimize computational and communication overhead, allowing mobile nodes to efficiently obtain authenticated and rich time information as they roam. We pair this method with Network Time Security (NTS), for enhanced resilience through multiple sources, available, ideally, simultaneously. We analyze the performance of our scheme in a dedicated setup, gauging the overhead for authenticated time data (Wi-Fi timestamped beacons and NTS). The results show that it is possible to provide security for the external to GNSS time sources, with minimal overhead for authentication and integrity, even when the GNSS-equipped nodes are mobile, and thus have short interactions with the Wi-Fi infrastructure and possibly intermittent Internet connectivity, as well as limited resources.

In this paper, a safe and learning-based control framework for model predictive control (MPC) is proposed to optimize nonlinear systems with a non-differentiable objective function under uncertain environmental disturbances. The control framework integrates a learning-based MPC with an auxiliary controller in a way of minimal intervention. The learning-based MPC augments the prior nominal model with incremental Gaussian Processes to learn the uncertain disturbances. The cross-entropy method (CEM) is utilized as the sampling-based optimizer for the MPC with a non-differentiable objective function. A minimal intervention controller is devised with a control Lyapunov function and a control barrier function to guide the sampling process and endow the system with high probabilistic safety. The proposed algorithm shows a safe and adaptive control performance on a simulated quadrotor in the tasks of trajectory tracking and obstacle avoidance under uncertain wind disturbances.

This report proposes a combined optimal control and perception framework for Micro Aerial Vehicle (MAV) autonomous navigation in novel indoor enclosed environments, relying exclusively on on-board sensor data. We use privileged information from a simulator to generate optimal waypoints in 3D space that our perception system learns to imitate. The trained learning based perception module in turn is able to generate similar obstacle avoiding waypoints from sensor data (RGB + IMU) alone. We demonstrate the efficacy of the framework across novel scenes in the iGibson simulation environment.

Offline reinforcement learning enables learning from a fixed dataset, without further interactions with the environment. The lack of environmental interactions makes the policy training vulnerable to state-action pairs far from the training dataset and prone to missing rewarding actions. For training more effective agents, we propose a framework that supports learning a flexible yet well-regularized fully-implicit policy. We further propose a simple modification to the classical policy-matching methods for regularizing with respect to the dual form of the Jensen--Shannon divergence and the integral probability metrics. We theoretically show the correctness of the policy-matching approach, and the correctness and a good finite-sample property of our modification. An effective instantiation of our framework through the GAN structure is provided, together with techniques to explicitly smooth the state-action mapping for robust generalization beyond the static dataset. Extensive experiments and ablation study on the D4RL dataset validate our framework and the effectiveness of our algorithmic designs.

In this paper, we design a new smart softwaredefined radio access network (RAN) architecture with important properties like flexibility and traffic awareness for sixth generation (6G) wireless networks. In particular, we consider a hierarchical resource allocation framework for the proposed smart soft-RAN model, where the software-defined network (SDN) controller is the first and foremost layer of the framework. This unit dynamically monitors the network to select a network operation type on the basis of distributed or centralized resource allocation architectures to perform decision-making intelligently. In this paper, our aim is to make the network more scalable and more flexible in terms of achievable data rate, overhead, and complexity indicators. To this end, we introduce a new metric, throughput overhead complexity (TOC), for the proposed machine learning-based algorithm, which makes a trade-off between these performance indicators. In particular, the decision making based on TOC is solved via deep reinforcement learning (DRL), which determines an appropriate resource allocation policy. Furthermore, for the selected algorithm, we employ the soft actor-critic method, which is more accurate, scalable, and robust than other learning methods. Simulation results demonstrate that the proposed smart network achieves better performance in terms of TOC compared to fixed centralized or distributed resource management schemes that lack dynamism. Moreover, our proposed algorithm outperforms conventional learning methods employed in other state-of-the-art network designs.

Fault-tolerant flight control faces challenges, as developing a model-based controller for each unexpected failure is unrealistic, and online learning methods can handle limited system complexity due to their low sample efficiency. In this research, a model-free coupled-dynamics flight controller for a jet aircraft able to withstand multiple failure types is proposed. An offline trained cascaded Soft Actor-Critic Deep Reinforcement Learning controller is successful on highly coupled maneuvers, including a coordinated 40 degree bank climbing turn with a normalized Mean Absolute Error of 2.64%. The controller is robust to six failure cases, including the rudder jammed at -15 deg, the aileron effectiveness reduced by 70%, a structural failure, icing and a backward c.g. shift as the response is stable and the climbing turn is completed successfully. Robustness to biased sensor noise, atmospheric disturbances, and to varying initial flight conditions and reference signal shapes is also demonstrated.

Despite deep reinforcement learning has recently achieved great successes, however in multiagent environments, a number of challenges still remain. Multiagent reinforcement learning (MARL) is commonly considered to suffer from the problem of non-stationary environments and exponentially increasing policy space. It would be even more challenging to learn effective policies in circumstances where the rewards are sparse and delayed over long trajectories. In this paper, we study Hierarchical Deep Multiagent Reinforcement Learning (hierarchical deep MARL) in cooperative multiagent problems with sparse and delayed rewards, where efficient multiagent learning methods are desperately needed. We decompose the original MARL problem into hierarchies and investigate how effective policies can be learned hierarchically in synchronous/asynchronous hierarchical MARL frameworks. Several hierarchical deep MARL architectures, i.e., Ind-hDQN, hCom and hQmix, are introduced for different learning paradigms. Moreover, to alleviate the issues of sparse experiences in high-level learning and non-stationarity in multiagent settings, we propose a new experience replay mechanism, named as Augmented Concurrent Experience Replay (ACER). We empirically demonstrate the effects and efficiency of our approaches in several classic Multiagent Trash Collection tasks, as well as in an extremely challenging team sports game, i.e., Fever Basketball Defense.

Autonomous urban driving navigation with complex multi-agent dynamics is under-explored due to the difficulty of learning an optimal driving policy. The traditional modular pipeline heavily relies on hand-designed rules and the pre-processing perception system while the supervised learning-based models are limited by the accessibility of extensive human experience. We present a general and principled Controllable Imitative Reinforcement Learning (CIRL) approach which successfully makes the driving agent achieve higher success rates based on only vision inputs in a high-fidelity car simulator. To alleviate the low exploration efficiency for large continuous action space that often prohibits the use of classical RL on challenging real tasks, our CIRL explores over a reasonably constrained action space guided by encoded experiences that imitate human demonstrations, building upon Deep Deterministic Policy Gradient (DDPG). Moreover, we propose to specialize adaptive policies and steering-angle reward designs for different control signals (i.e. follow, straight, turn right, turn left) based on the shared representations to improve the model capability in tackling with diverse cases. Extensive experiments on CARLA driving benchmark demonstrate that CIRL substantially outperforms all previous methods in terms of the percentage of successfully completed episodes on a variety of goal-directed driving tasks. We also show its superior generalization capability in unseen environments. To our knowledge, this is the first successful case of the learned driving policy through reinforcement learning in the high-fidelity simulator, which performs better-than supervised imitation learning.