Reinforcement Learning -- How can you become an expert? Reinforcement Learning -- How can you become an expert? You will never believe how Machine can learn like humans! You will never believe how Machine can learn like humans!

Robotic manipulation of cloth is a challenging task due to the high dimensionality of the configuration space and the complexity of dynamics affected by various material properties. The effect of complex dynamics is even more pronounced in dynamic folding, for example, when a square piece of fabric is folded in two by a single manipulator. To account for the complexity and uncertainties, feedback of the cloth state using e.g. vision is typically needed. However, construction of visual feedback policies for dynamic cloth folding is an open problem. In this paper, we present a solution that learns policies in simulation using Reinforcement Learning (RL) and transfers the learned policies directly to the real world. In addition, to learn a single policy that manipulates multiple materials, we randomize the material properties in simulation. We evaluate the contributions of visual feedback and material randomization in real-world experiments. The experimental results demonstrate that the proposed solution can fold successfully different fabric types using dynamic manipulation in the real world. Code, data, and videos are available at https://sites.google.com/view/dynamic-cloth-folding

In recent years, the dramatic progress in machine learning has begun to impact many areas of science and technology significantly. In the present perspective article, we explore how quantum technologies are benefiting from this revolution. We showcase in illustrative examples how scientists in the past few years have started to use machine learning and more broadly methods of artificial intelligence to analyze quantum measurements, estimate the parameters of quantum devices, discover new quantum experimental setups, protocols, and feedback strategies, and generally improve aspects of quantum computing, quantum communication, and quantum simulation. We highlight open challenges and future possibilities and conclude with some speculative visions for the next decade.

Federated learning (FL) is a trending training paradigm to utilize decentralized training data. FL allows clients to update model parameters locally for several epochs, then share them to a global model for aggregation. This training paradigm with multi-local step updating before aggregation exposes unique vulnerabilities to adversarial attacks. Adversarial training is a popular and effective method to improve the robustness of networks against adversaries. In this work, we formulate a general form of federated adversarial learning (FAL) that is adapted from adversarial learning in the centralized setting. On the client side of FL training, FAL has an inner loop to generate adversarial samples for adversarial training and an outer loop to update local model parameters. On the server side, FAL aggregates local model updates and broadcast the aggregated model. We design a global robust training loss and formulate FAL training as a min-max optimization problem. Unlike the convergence analysis in classical centralized training that relies on the gradient direction, it is significantly harder to analyze the convergence in FAL for three reasons: 1) the complexity of min-max optimization, 2) model not updating in the gradient direction due to the multi-local updates on the client-side before aggregation and 3) inter-client heterogeneity. We address these challenges by using appropriate gradient approximation and coupling techniques and present the convergence analysis in the over-parameterized regime. Our main result theoretically shows that the minimum loss under our algorithm can converge to $\epsilon$ small with chosen learning rate and communication rounds. It is noteworthy that our analysis is feasible for non-IID clients.

Reinforcement learning (RL) provides a naturalistic framing for learning through trial and error, which is appealing both because of its simplicity and effectiveness and because of its resemblance to how humans and animals acquire skills through experience. However, real-world embodied learning, such as that performed by humans and animals, is situated in a continual, non-episodic world, whereas common benchmark tasks in RL are episodic, with the environment resetting between trials to provide the agent with multiple attempts. This discrepancy presents a major challenge when attempting to take RL algorithms developed for episodic simulated environments and run them on real-world platforms, such as robots. In this paper, we aim to address this discrepancy by laying out a framework for Autonomous Reinforcement Learning (ARL): reinforcement learning where the agent not only learns through its own experience, but also contends with lack of human supervision to reset between trials. We introduce a simulated benchmark EARL around this framework, containing a set of diverse and challenging simulated tasks reflective of the hurdles introduced to learning when only a minimal reliance on extrinsic intervention can be assumed. We show that standard approaches to episodic RL and existing approaches struggle as interventions are minimized, underscoring the need for developing new algorithms for reinforcement learning with a greater focus on autonomy.

Researchers from Santa Clara University, New Jersey Institute of Technology and the University of Hong Kong have been able to successfully teach microrobots how to swim via deep reinforcement learning, marking a substantial leap in the progression of microswimming capability. There has been tremendous interest in developing artificial microswimmers that can navigate the world similarly to naturally-occurring swimming microorganisms, like bacteria. Such microswimmers provide promise for a vast array of future biomedical applications, such as targeted drug delivery and microsurgery. Yet, most artificial microswimmers to date can only perform relatively simple maneuvers with fixed locomotory gaits. In the researchers' study published in Communications Physics, they reasoned microswimmers could learn--and adapt to changing conditions--through AI.

The difference was due to adding a new dimension of driving skills. In addition to Race Car Control, the essential physics for car dynamics, racing lines and precision maneuvers and Racing Tactics, the split-second decision-making for passing and overtaking, training was provided in the Racing Etiquette deemed essential for fair play. To achieve this not only did the team have to find ways to encode the written and unwritten rules of racing into a complex reward function they also had to choose training examples for reinforcement learning that provided the correct balance of aggression and timidity.

Traffic signal control is a challenging real-world problem aiming to minimize overall travel time by coordinating vehicle movements at road intersections. Existing traffic signal control systems in use still rely heavily on oversimplified information and rule-based methods. Specifically, the periodicity of green/red light alternations can be considered as a prior for better planning of each agent in policy optimization. To better learn such adaptive and predictive priors, traditional RL-based methods can only return a fixed length from predefined action pool with only local agents. If there is no cooperation between these agents, some agents often make conflicts to other agents and thus decrease the whole throughput. This paper proposes a cooperative, multi-objective architecture with age-decaying weights to better estimate multiple reward terms for traffic signal control optimization, which termed COoperative Multi-Objective Multi-Agent Deep Deterministic Policy Gradient (COMMA-DDPG). Two types of agents running to maximize rewards of different goals - one for local traffic optimization at each intersection and the other for global traffic waiting time optimization. The global agent is used to guide the local agents as a means for aiding faster learning but not used in the inference phase. We also provide an analysis of solution existence together with convergence proof for the proposed RL optimization. Evaluation is performed using real-world traffic data collected using traffic cameras from an Asian country. Our method can effectively reduce the total delayed time by 60\%. Results demonstrate its superiority when compared to SoTA methods.

When talking about how to train agent to play games, some reinforcement learning applications use hand-crafted features to train model. However, the performance will be influenced heavily by the feature chosen. If we can directly use the whole image of the game as input, then this problem can be solved. In paper referenced, it shows a convolutional neural network which can do well with only raw video data in environment. Its basic idea is using Bellman equation to iterative update, so that we can get better knowledge about Q value.

In this paper, we consider a wireless network of smart sensors (agents) that monitor a dynamical process and send measurements to a base station that performs global monitoring and decision-making. Smart sensors are equipped with both sensing and computation, and can either send raw measurements or process them prior to transmission. Constrained agent resources raise a fundamental latency-accuracy trade-off. On the one hand, raw measurements are inaccurate but fast to produce. On the other hand, data processing on resource-constrained platforms generates accurate measurements at the cost of non-negligible computation latency. Further, if processed data are also compressed, latency caused by wireless communication might be higher for raw measurements. Hence, it is challenging to decide when and where sensors in the network should transmit raw measurements or leverage time-consuming local processing. To tackle this design problem, we propose a Reinforcement Learning approach to learn an efficient policy that dynamically decides when measurements are to be processed at each sensor. Effectiveness of our proposed approach is validated through a numerical simulation with case study on smart sensing motivated by the Internet of Drones.