Learning a risk-aware policy is essential but rather challenging in unstructured robotic tasks. Safe reinforcement learning methods open up new possibilities to tackle this problem. However, the conservative policy updates make it intractable to achieve sufficient exploration and desirable performance in complex, sample-expensive environments. In this paper, we propose a dual-agent safe reinforcement learning strategy consisting of a baseline and a safe agent. Such a decoupled framework enables high flexibility, data efficiency and risk-awareness for RL-based control. Concretely, the baseline agent is responsible for maximizing rewards under standard RL settings. Thus, it is compatible with off-the-shelf training techniques of unconstrained optimization, exploration and exploitation. On the other hand, the safe agent mimics the baseline agent for policy improvement and learns to fulfill safety constraints via off-policy RL tuning. In contrast to training from scratch, safe policy correction requires significantly fewer interactions to obtain a near-optimal policy. The dual policies can be optimized synchronously via a shared replay buffer, or leveraging the pre-trained model or the non-learning-based controller as a fixed baseline agent. Experimental results show that our approach can learn feasible skills without prior knowledge as well as deriving risk-averse counterparts from pre-trained unsafe policies. The proposed method outperforms the state-of-the-art safe RL algorithms on difficult robot locomotion and manipulation tasks with respect to both safety constraint satisfaction and sample efficiency.

Automation of berthing maneuvers in shipping is a pressing issue as the berthing maneuver is one of the most stressful tasks seafarers undertake. Berthing control problems are often tackled via tracking a predefined trajectory or path. Maintaining a tracking error of zero under an uncertain environment is impossible; the tracking controller is nonetheless required to bring vessels close to desired berths. The tracking controller must prioritize the avoidance of tracking errors that may cause collisions with obstacles. This paper proposes a training method based on reinforcement learning for a trajectory tracking controller that reduces the probability of collisions with static obstacles. Via numerical simulations, we show that the proposed method reduces the probability of collisions during berthing maneuvers. Furthermore, this paper shows the tracking performance in a model experiment.

Reinforcement learning is a machine learning approach based on behavioral psychology. It is focused on learning agents that can acquire knowledge and learn to carry out new tasks by interacting with the environment. However, a problem occurs when reinforcement learning is used in critical contexts where the users of the system need to have more information and reliability for the actions executed by an agent. In this regard, explainable reinforcement learning seeks to provide to an agent in training with methods in order to explain its behavior in such a way that users with no experience in machine learning could understand the agent's behavior. One of these is the memory-based explainable reinforcement learning method that is used to compute probabilities of success for each state-action pair using an episodic memory. In this work, we propose to make use of the memory-based explainable reinforcement learning method in a hierarchical environment composed of sub-tasks that need to be first addressed to solve a more complex task. The end goal is to verify if it is possible to provide to the agent the ability to explain its actions in the global task as well as in the sub-tasks. The results obtained showed that it is possible to use the memory-based method in hierarchical environments with high-level tasks and compute the probabilities of success to be used as a basis for explaining the agent's behavior.

Navigation represents one of the most heavily studied topics in robotics [3]. It is often approached in terms of mapping and planning: constructing a geometric representation of the world from observations, then planning through this model using motion planning algorithms [4-6]. However, such geometric approaches abstract away significant physical and semantic aspects of the navigation problem that in practice leave a range of real-world situations difficult to handle (see Figure 1). These challenges require special handling, resulting in complex systems with many components. Some works have sought to incorporate machine learning techniques to either learn navigational skills from simulation or to learn perception systems for navigation for human-provided labels. In this article, we instead argue that learned navigational models, trained directly on real-world experience rather than human-provided labels or simulators, provide the most promising long-term direction for a general solution to navigation. We refer to such learning approaches as experiential learning, because they learn directly from past experience of performing real-world navigation. As we will discuss in Section 2, such methods relate closely to reinforcement learning.

The rapid adoption of residential solar photovoltaics (PV) has resulted in regular overvoltage events, due to correlated reverse power flows. Currently, PV inverters prevent damage to electronics by curtailing energy production in response to overvoltage. However, this disproportionately affects households at the far end of the feeder, leading to an unfair allocation of the potential value of energy produced. Globally optimizing for fair curtailment requires accurate feeder parameters, which are often unknown. This paper investigates reinforcement learning, which gradually optimizes a fair PV curtailment strategy by interacting with the system. We evaluate six fairness metrics on how well they can be learned compared to an optimal solution oracle. We show that all definitions permit efficient learning, suggesting that reinforcement learning is a promising approach to achieving both safe and fair PV coordination.

Whole-slide images (WSI) in computational pathology have high resolution with gigapixel size, but are generally with sparse regions of interest, which leads to weak diagnostic relevance and data inefficiency for each area in the slide. Most of the existing methods rely on a multiple instance learning framework that requires densely sampling local patches at high magnification. The limitation is evident in the application stage as the heavy computation for extracting patch-level features is inevitable. In this paper, we develop RLogist, a benchmarking deep reinforcement learning (DRL) method for fast observation strategy on WSIs. Imitating the diagnostic logic of human pathologists, our RL agent learns how to find regions of observation value and obtain representative features across multiple resolution levels, without having to analyze each part of the WSI at the high magnification. We benchmark our method on two whole-slide level classification tasks, including detection of metastases in WSIs of lymph node sections, and subtyping of lung cancer. Experimental results demonstrate that RLogist achieves competitive classification performance compared to typical multiple instance learning algorithms, while having a significantly short observation path. In addition, the observation path given by RLogist provides good decision-making interpretability, and its ability of reading path navigation can potentially be used by pathologists for educational/assistive purposes. Our code is available at: \url{https://github.com/tencent-ailab/RLogist}.

Sampling is ubiquitous in machine learning methodologies. Due to the growth of large datasets and model complexity, we want to learn and adapt the sampling process while training a representation. Towards achieving this grand goal, a variety of sampling techniques have been proposed. However, most of them either use a fixed sampling scheme or adjust the sampling scheme based on simple heuristics. They cannot choose the best sample for model training in different stages. Inspired by "Think, Fast and Slow" (System 1 and System 2) in cognitive science, we propose a reward-guided sampling strategy called Adaptive Sample with Reward (ASR) to tackle this challenge. To the best of our knowledge, this is the first work utilizing reinforcement learning (RL) to address the sampling problem in representation learning. Our approach optimally adjusts the sampling process to achieve optimal performance. We explore geographical relationships among samples by distance-based sampling to maximize overall cumulative reward. We apply ASR to the long-standing sampling problems in similarity-based loss functions. Empirical results in information retrieval and clustering demonstrate ASR's superb performance across different datasets. We also discuss an engrossing phenomenon which we name as "ASR gravity well" in experiments.

Driven by the global decarbonization effort, the rapid integration of renewable energy into the conventional electricity grid presents new challenges and opportunities for the battery energy storage system (BESS) participating in the energy market. Energy arbitrage can be a significant source of revenue for the BESS due to the increasing price volatility in the spot market caused by the mismatch between renewable generation and electricity demand. In addition, the Frequency Control Ancillary Services (FCAS) markets established to stabilize the grid can offer higher returns for the BESS due to their capability to respond within milliseconds. Therefore, it is crucial for the BESS to carefully decide how much capacity to assign to each market to maximize the total profit under uncertain market conditions. This paper formulates the bidding problem of the BESS as a Markov Decision Process, which enables the BESS to participate in both the spot market and the FCAS market to maximize profit. Then, Proximal Policy Optimization, a model-free deep reinforcement learning algorithm, is employed to learn the optimal bidding strategy from the dynamic environment of the energy market under a continuous bidding scale. The proposed model is trained and validated using real-world historical data of the Australian National Electricity Market. The results demonstrate that our developed joint bidding strategy in both markets is significantly profitable compared to individual markets.

Reinforcement learning (RL) is an increasingly popular way to model sequential decision-making problems in artificial intelligence. RL agents learn through trial and error, repeatedly interacting with the world to learn a policy that maximizes a reward signal. RL agents have recently achieved remarkable results when used in conjunction with deep neural networks. Chief among these so-called deep-RL results is the 2015 paper that introduced the Deep Q Network (DQN) agent, which surpassed human-level performance on a large set of Atari games. A core component of DQN is an optimizer that adapts the parameters of the neural network to minimize the DQN objective.

The unit commitment (UC) problem, which determines operating schedules of generation units to meet demand, is a fundamental task in power systems operation. Existing UC methods using mixed-integer programming are not well-suited to highly stochastic systems. Approaches which more rigorously account for uncertainty could yield large reductions in operating costs by reducing spinning reserve requirements; operating power stations at higher efficiencies; and integrating greater volumes of variable renewables. A promising approach to solving the UC problem is reinforcement learning (RL), a methodology for optimal decision-making which has been used to conquer long-standing grand challenges in artificial intelligence. This thesis explores the application of RL to the UC problem and addresses challenges including robustness under uncertainty; generalisability across multiple problem instances; and scaling to larger power systems than previously studied. To tackle these issues, we develop guided tree search, a novel methodology combining model-free RL and model-based planning. The UC problem is formalised as a Markov decision process and we develop an open-source environment based on real data from Great Britain's power system to train RL agents. In problems of up to 100 generators, guided tree search is shown to be competitive with deterministic UC methods, reducing operating costs by up to 1.4\%. An advantage of RL is that the framework can be easily extended to incorporate considerations important to power systems operators such as robustness to generator failure, wind curtailment or carbon prices. When generator outages are considered, guided tree search saves over 2\% in operating costs as compared with methods using conventional $N-x$ reserve criteria.