Robot navigation with deep reinforcement learning (RL) achieves higher performance and performs well under complex environment. Meanwhile, the interpretation of the decision-making of deep RL models becomes a critical problem for more safety and reliability of autonomous robots. In this paper, we propose a visual explanation method based on an attention branch for deep RL models. We connect attention branch with pre-trained deep RL model and the attention branch is trained by using the selected action by the trained deep RL model as a correct label in a supervised learning manner. Because the attention branch is trained to output the same result as the deep RL model, the obtained attention maps are corresponding to the agent action with higher interpretability. Experimental results with robot navigation task show that the proposed method can generate interpretable attention maps for a visual explanation.

Addressing the need for explainable Machine Learning has emerged as one of the most important research directions in modern Artificial Intelligence (AI). While the current dominant paradigm in the field is based on black-box models, typically in the form of (deep) neural networks, these models lack direct interpretability for human users, i.e., their outcomes (and, even more so, their inner working) are opaque and hard to understand. This is hindering the adoption of AI in safety-critical applications, where high interests are at stake. In these applications, explainable by design models, such as decision trees, may be more suitable, as they provide interpretability. Recent works have proposed the hybridization of decision trees and Reinforcement Learning, to combine the advantages of the two approaches. So far, however, these works have focused on the optimization of those hybrid models. Here, we apply MAP-Elites for diversifying hybrid models over a feature space that captures both the model complexity and its behavioral variability. We apply our method on two well-known control problems from the OpenAI Gym library, on which we discuss the "illumination" patterns projected by MAP-Elites, comparing its results against existing similar approaches.

A multi-robot system (MRS) is a group of coordinated robots designed to cooperate with each other and accomplish given tasks. Due to the uncertainties in operating environments, the system may encounter emergencies, such as unobserved obstacles, moving vehicles, and extreme weather. Animal groups such as bee colonies initiate collective emergency reaction behaviors such as bypassing obstacles and avoiding predators, similar to muscle-conditioned reflex which organizes local muscles to avoid hazards in the first response without delaying passage through the brain. Inspired by this, we develop a similar collective conditioned reflex mechanism for multi-robot systems to respond to emergencies. In this study, Collective Conditioned Reflex (CCR), a bio-inspired emergency reaction mechanism, is developed based on animal collective behavior analysis and multi-agent reinforcement learning (MARL). The algorithm uses a physical model to determine if the robots are experiencing an emergency; then, rewards for robots involved in the emergency are augmented with corresponding heuristic rewards, which evaluate emergency magnitudes and consequences and decide local robots' participation. CCR is validated on three typical emergency scenarios: \textit{turbulence, strong wind, and hidden obstacle}. Simulation results demonstrate that CCR improves robot teams' emergency reaction capability with faster reaction speed and safer trajectory adjustment compared with baseline methods.

Your learning system is often called an agent, in most modern literature. This term includes more than just the neural network estimator in recent algorithms. The agent interacts with an environment to solve a task. We'll go into further details later into what constitutes the environment, as it can become problematic. The environment relies on two main components: its transition and reward functions.

Closed-loop printing enhanced by machine learning. Using fluids for 3D printing may seem paradoxical at first glance, but not all fluids are watery. Many useful materials are more viscous, from inks to hydrogels, and thus qualify for printing. Yet their potential has been relatively unexplored due to the limited control over their behaviour. Now, researchers of the Bickel group at the Institute of Science and Technology Austria (ISTA) are employing machine learning in virtual environments to achieve better results in real-world experiments.

GANs generate new designs from an existing dataset utilizing a generator and a discriminator which are usually Deep Generative design has been growing across the Neural Networks (DNNs). The objective function of GANs design community as a viable method for design should be differentiable to utilize gradient-based optimization space exploration. Thermal design is more complex while reward of a deep RL can be defined based on the than mechanical or aerodynamic design because design requirements (Chen & Ahmed, 2021b). of the additional convection-diffusion equation and its pertinent boundary interaction. We Shape and Topology Optimization (TO) play a major role in present a generative thermal design using cooperative Generative models in engineering design (Chen & Ahmed, multi-agent deep reinforcement learning 2021a). Engineering design often require Finite Element and continuous geometric representation of the Analysis (FEA) or Computational Fluid Dynamics (CFD) fluid and solid domain. The proposed framework to assess the performance of the output design (Hoyer et al., consists of a pre-trained neural network surrogate 2019). These numerical approaches are computationally model as an environment to predict heat transfer expensive and require human expertise (Regenwetter et al., and pressure drop of the generated geometries.

Deep reinforcement learning is a promising approach to learning policies in uncontrolled environments that do not require domain knowledge. Unfortunately, due to sample inefficiency, deep RL applications have primarily focused on simulated environments. In this work, we demonstrate that the recent advancements in machine learning algorithms and libraries combined with a carefully tuned robot controller lead to learning quadruped locomotion in only 20 minutes in the real world. We evaluate our approach on several indoor and outdoor terrains which are known to be challenging for classical model-based controllers. We observe the robot to be able to learn walking gait consistently on all of these terrains. Finally, we evaluate our design decisions in a simulated environment.

We propose a data-driven method for controlling the frequency and convergence rate of black-box nonlinear dynamical systems based on the Koopman operator theory. With the proposed method, a policy network is trained such that the eigenvalues of a Koopman operator of controlled dynamics are close to the target eigenvalues. The policy network consists of a neural network to find a Koopman invariant subspace, and a pole placement module to adjust the eigenvalues of the Koopman operator. Since the policy network is differentiable, we can train it in an end-to-end fashion using reinforcement learning. We demonstrate that the proposed method achieves better performance than model-free reinforcement learning and model-based control with system identification.

Wireless sensor networks consist of randomly distributed sensor nodes for monitoring targets or areas of interest. Maintaining the network for continuous surveillance is a challenge due to the limited battery capacity in each sensor. Wireless power transfer technology is emerging as a reliable solution for energizing the sensors by deploying a mobile charger (MC) to recharge the sensor. However, designing an optimal charging path for the MC is challenging because of uncertainties arising in the networks. The energy consumption rate of the sensors may fluctuate significantly due to unpredictable changes in the network topology, such as node failures. These changes also lead to shifts in the importance of each sensor, which are often assumed to be the same in existing works. We address these challenges in this paper by proposing a novel adaptive charging scheme using a deep reinforcement learning (DRL) approach. Specifically, we endow the MC with a charging policy that determines the next sensor to charge conditioning on the current state of the network. We then use a deep neural network to parametrize this charging policy, which will be trained by reinforcement learning techniques. Our model can adapt to spontaneous changes in the network topology. The empirical results show that the proposed algorithm outperforms the existing on-demand algorithms by a significant margin.

The rapid adoption of electric vehicles (EVs) calls for the widespread installation of EV charging stations. To maximize the profitability of charging stations, intelligent controllers that provide both charging and electric grid services are in great need. However, it is challenging to determine the optimal charging schedule due to the uncertain arrival time and charging demands of EVs. In this paper, we propose a novel centralized allocation and decentralized execution (CADE) reinforcement learning (RL) framework to maximize the charging station's profit. In the centralized allocation process, EVs are allocated to either the waiting or charging spots. In the decentralized execution process, each charger makes its own charging/discharging decision while learning the action-value functions from a shared replay memory. This CADE framework significantly improves the scalability and sample efficiency of the RL algorithm. Numerical results show that the proposed CADE framework is both computationally efficient and scalable, and significantly outperforms the baseline model predictive control (MPC). We also provide an in-depth analysis of the learned action-value function to explain the inner working of the reinforcement learning agent.