Structure-based drug design (SBDD) aims to discover drug candidates by finding molecules (ligands) that bind tightly to a disease-related protein (targets), which is the primary approach to computer-aided drug discovery. Recently, applying deep generative models for three-dimensional (3D) molecular design conditioned on protein pockets to solve SBDD has attracted much attention, but their formulation as probabilistic modeling often leads to unsatisfactory optimization performance. On the other hand, traditional combinatorial optimization methods such as genetic algorithms (GA) have demonstrated state-of-the-art performance in various molecular optimization tasks. However, they do not utilize protein target structure to inform design steps but rely on a random-walk-like exploration, which leads to unstable performance and no knowledge transfer between different tasks despite the similar binding physics. To achieve a more stable and efficient SBDD, we propose Reinforced Genetic Algorithm (RGA) that uses neural models to prioritize the profitable design steps and suppress random-walk behavior. The neural models take the 3D structure of the targets and ligands as inputs and are pre-trained using native complex structures to utilize the knowledge of the shared binding physics from different targets and then fine-tuned during optimization. We conduct thorough empirical studies on optimizing binding affinity to various disease targets and show that RGA outperforms the baselines in terms of docking scores and is more robust to random initializations. The ablation study also indicates that the training on different targets helps improve performance by leveraging the shared underlying physics of the binding processes. The code is available at https://github.com/futianfan/reinforced-genetic-algorithm.

With rapid development of blockchain technology as well as integration of various application areas, performance evaluation, performance optimization, and dynamic decision in blockchain systems are playing an increasingly important role in developing new blockchain technology. This paper provides a recent systematic overview of this class of research, and especially, developing mathematical modeling and basic theory of blockchain systems. Important examples include (a) performance evaluation: Markov processes, queuing theory, Markov reward processes, random walks, fluid and diffusion approximations, and martingale theory; (b) performance optimization: Linear programming, nonlinear programming, integer programming, and multi-objective programming; (c) optimal control and dynamic decision: Markov decision processes, and stochastic optimal control; and (d) artificial intelligence: Machine learning, deep reinforcement learning, and federated learning. So far, a little research has focused on these research lines. We believe that the basic theory with mathematical methods, algorithms and simulations of blockchain systems discussed in this paper will strongly support future development and continuous innovation of blockchain technology.

This work provides a Deep Reinforcement Learning approach to solving a periodic review inventory control system with stochastic vendor lead times, lost sales, correlated demand, and price matching. While this dynamic program has historically been considered intractable, our results show that several policy learning approaches are competitive with or outperform classical methods. In order to train these algorithms, we develop novel techniques to convert historical data into a simulator. On the theoretical side, we present learnability results on a subclass of inventory control problems, where we provide a provable reduction of the reinforcement learning problem to that of supervised learning. On the algorithmic side, we present a model-based reinforcement learning procedure (Direct Backprop) to solve the periodic review inventory control problem by constructing a differentiable simulator. Under a variety of metrics Direct Backprop outperforms model-free RL and newsvendor baselines, in both simulations and real-world deployments.

Safe and efficient co-planning of multiple robots in pedestrian participation environments is promising for applications. In this work, a novel multi-robot social-aware efficient cooperative planner that on the basis of off-policy multi-agent reinforcement learning (MARL) under partial dimension-varying observation and imperfect perception conditions is proposed. We adopt temporal-spatial graph (TSG)-based social encoder to better extract the importance of social relation between each robot and the pedestrians in its field of view (FOV). Also, we introduce K-step lookahead reward setting in multi-robot RL framework to avoid aggressive, intrusive, short-sighted, and unnatural motion decisions generated by robots. Moreover, we improve the traditional centralized critic network with multi-head global attention module to better aggregates local observation information among different robots to guide the process of individual policy update. Finally, multi-group experimental results verify the effectiveness of the proposed cooperative motion planner.

Neural algorithmic reasoning studies the problem of learning algorithms with neural networks, especially with graph architectures. A recent proposal, XLVIN, reaps the benefits of using a graph neural network that simulates the value iteration algorithm in deep reinforcement learning agents. It allows model-free planning without access to privileged information about the environment, which is usually unavailable. However, XLVIN only supports discrete action spaces, and is hence nontrivially applicable to most tasks of real-world interest. We expand XLVIN to continuous action spaces by discretization, and evaluate several selective expansion policies to deal with the large planning graphs. Our proposal, CNAP, demonstrates how neural algorithmic reasoning can make a measurable impact in higher-dimensional continuous control settings, such as MuJoCo, bringing gains in low-data settings and outperforming model-free baselines.

Idle vehicle relocation is crucial for addressing demand-supply imbalance that frequently arises in the ride-hailing system. Current mainstream methodologies - optimization and reinforcement learning - suffer from obvious computational drawbacks. Optimization models need to be solved in real-time and often trade off model fidelity (hence quality of solutions) for computational efficiency. Reinforcement learning is expensive to train and often struggles to achieve coordination among a large fleet. This paper designs a hybrid approach that leverages the strengths of the two while overcoming their drawbacks. Specifically, it trains an optimization proxy, i.e., a machine-learning model that approximates an optimization model, and then refines the proxy with reinforcement learning. This Reinforcement Learning from Optimization Proxy (RLOP) approach is computationally efficient to train and deploy, and achieves better results than RL or optimization alone. Numerical experiments on the New York City dataset show that the RLOP approach reduces both the relocation costs and computation time significantly compared to the optimization model, while pure reinforcement learning fails to converge due to computational complexity.

Recent advancements in reinforcement learning algorithms have opened doors for researchers to operate and optimize building energy management systems autonomously. However, the lack of an easily configurable building dynamical model and energy management task simulation and evaluation platform has arguably slowed the progress in developing advanced and dedicated reinforcement learning (RL) and control algorithms for building operation tasks. Here we propose "BEAR", a physics-principled Building Environment for Control And Reinforcement Learning. The platform allows researchers to benchmark both model-based and model-free controllers using a broad collection of standard building models in Python without co-simulation using external building simulators. In this paper, we discuss the design of this platform and compare it with other existing building simulation frameworks. We demonstrate the compatibility and performance of BEAR with different controllers, including both model predictive control (MPC) and several state-of-the-art RL methods with two case studies.

Energy consumption in buildings, both residential and commercial, accounts for approximately 40% of all energy usage in the U.S., and similar numbers are being reported from countries around the world. This significant amount of energy is used to maintain a comfortable, secure, and productive environment for the occupants. So, it is crucial that the energy consumption in buildings must be optimized, all the while maintaining satisfactory levels of occupant comfort, health, and safety. Recently, Machine Learning has been proven to be an invaluable tool in deriving important insights from data and optimizing various systems. In this work, we review the ways in which machine learning has been leveraged to make buildings smart and energy-efficient. For the convenience of readers, we provide a brief introduction of several machine learning paradigms and the components and functioning of each smart building system we cover. Finally, we discuss challenges faced while implementing machine learning algorithms in smart buildings and provide future avenues for research at the intersection of smart buildings and machine learning.

Recently, methods such as Decision Transformer that reduce reinforcement learning to a prediction task and solve it via supervised learning (RvS) have become popular due to their simplicity, robustness to hyperparameters, and strong overall performance on offline RL tasks. However, simply conditioning a probabilistic model on a desired return and taking the predicted action can fail dramatically in stochastic environments since trajectories that result in a return may have only achieved that return due to luck. In this work, we describe the limitations of RvS approaches in stochastic environments and propose a solution. Rather than simply conditioning on the return of a single trajectory as is standard practice, our proposed method, ESPER, learns to cluster trajectories and conditions on average cluster returns, which are independent from environment stochasticity. Doing so allows ESPER to achieve strong alignment between target return and expected performance in real environments. We demonstrate this in several challenging stochastic offline-RL tasks including the challenging puzzle game 2048, and Connect Four playing against a stochastic opponent. In all tested domains, ESPER achieves significantly better alignment between the target return and achieved return than simply conditioning on returns. ESPER also achieves higher maximum performance than even the value-based baselines.

Existing offline reinforcement learning (RL) algorithms typically assume that training data is either: 1) generated by a known policy, or 2) of entirely unknown origin. We consider multi-demonstrator offline RL, a middle ground where we know which demonstrators generated each dataset, but make no assumptions about the underlying policies of the demonstrators. This is the most natural setting when collecting data from multiple human operators, yet remains unexplored. Since different demonstrators induce different data distributions, we show that this can be naturally framed as a domain generalization problem, with each demonstrator corresponding to a different domain. Specifically, we propose Domain-Invariant Model-based Offline RL (DIMORL), where we apply Risk Extrapolation (REx) (Krueger et al., 2020) to the process of learning dynamics and rewards models. Our results show that models trained with REx exhibit improved domain generalization performance when compared with the natural baseline of pooling all demonstrators' data. We observe that the resulting models frequently enable the learning of superior policies in the offline model-based RL setting, can improve the stability of the policy learning process, and potentially enable increased exploration.