Deep reinforcement learning (DRL) is an emerging methodology that is transforming the way many complicated transportation decision-making problems are tackled. Researchers have been increasingly turning to this powerful learning-based methodology to solve challenging problems across transportation fields. While many promising applications have been reported in the literature, there remains a lack of comprehensive synthesis of the many DRL algorithms and their uses and adaptations. The objective of this paper is to fill this gap by conducting a comprehensive, synthesized review of DRL applications in transportation. We start by offering an overview of the DRL mathematical background, popular and promising DRL algorithms, and some highly effective DRL extensions. Building on this overview, a systematic investigation of about 150 DRL studies that have appeared in the transportation literature, divided into seven different categories, is performed. Building on this review, we continue to examine the applicability, strengths, shortcomings, and common and application-specific issues of DRL techniques with regard to their applications in transportation. In the end, we recommend directions for future research and present available resources for actually implementing DRL.

Self-supervised learning and data augmentation have significantly reduced the performance gap between state and image-based reinforcement learning agents in continuous control tasks. However, it is still unclear whether current techniques can face a variety of visual conditions required by real-world environments. We propose a challenging benchmark that tests agents' visual generalization by adding graphical variety to existing continuous control domains. Our empirical analysis shows that current methods struggle to generalize across a diverse set of visual changes, and we examine the specific factors of variation that make these tasks difficult. We find that data augmentation techniques outperform self-supervised learning approaches and that more significant image transformations provide better visual generalization \footnote{The benchmark and our augmented actor-critic implementation are open-sourced @ https://github.com/jakegrigsby/dmc_remastered)

Real-time control of pumps can be an infeasible task in water distribution systems (WDSs) because the calculation to find the optimal pump speeds is resource-intensive. The computational need cannot be lowered even with the capabilities of smart water networks when conventional optimization techniques are used. Deep reinforcement learning (DRL) is presented here as a controller of pumps in two WDSs. An agent based on a dueling deep q-network is trained to maintain the pump speeds based on instantaneous nodal pressure data. General optimization techniques (e.g., Nelder-Mead method, differential evolution) serve as baselines. The total efficiency achieved by the DRL agent compared to the best performing baseline is above 0.98, whereas the speedup is around 2x compared to that. The main contribution of the presented approach is that the agent can run the pumps in real-time because it depends only on measurement data. If the WDS is replaced with a hydraulic simulation, the agent still outperforms conventional techniques in search speed.

Deploying Reinforcement Learning (RL) agents to solve real-world applications often requires satisfying complex system constraints. Often the constraint thresholds are incorrectly set due to the complex nature of a system or the inability to verify the thresholds offline (e.g, no simulator or reasonable offline evaluation procedure exists). This results in solutions where a task cannot be solved without violating the constraints. However, in many real-world cases, constraint violations are undesirable yet they are not catastrophic, motivating the need for soft-constrained RL approaches. We present two soft-constrained RL approaches that utilize meta-gradients to find a good trade-off between expected return and minimizing constraint violations. We demonstrate the effectiveness of these approaches by showing that they consistently outperform the baselines across four different Mujoco domains.

In this meetup, we will learn how AI, in particular, Reinforcement Learning learns to play games. We will provide an overview of Monte Carlo methods, including prediction & control. Then see how we can use this to play the game of Black Jack with no user input. Have your Laptops ready as this meetup is hands-on.

In this meetup, we will learn how AI, in particular, Reinforcement Learning learns to play games. We will provide an overview of Monte Carlo methods, including prediction and control. Then see how we can use this to play the game of Black Jack with no user input. Have your Laptops ready as this meetup is hands-on.

A team of researchers from the University of Southern California's Valero Lab built a relatively simple robotic limb that accomplished something simply amazing: The 3-tendon, 2-joint robotic leg taught itself how to move. The team was led by Professor Francisco Valero-Cuevas and doctoral student Ali Marjaninejad. Their research was featured on the cover of the March issue of Nature Machine Intelligence. The robotic limb is not programmed for a specific task. It learns autonomously first by modeling its own dynamic properties and then using a form of artificial intelligence (AI) known as reinforcement learning. Instead of weeks upon weeks of coding, the robotic leg is able to teach itself to move in just minutes.

Although Q-learning is one of the most successful algorithms for finding the best action-value function (and thus the optimal policy) in reinforcement learning, its implementation often suffers from large overestimation of Q-function values incurred by random sampling. The double Q-learning algorithm proposed in~\citet{hasselt2010double} overcomes such an overestimation issue by randomly switching the update between two Q-estimators, and has thus gained significant popularity in practice. However, the theoretical understanding of double Q-learning is rather limited. So far only the asymptotic convergence has been established, which does not characterize how fast the algorithm converges. In this paper, we provide the first non-asymptotic (i.e., finite-time) analysis for double Q-learning. We show that both synchronous and asynchronous double Q-learning are guaranteed to converge to an $\epsilon$-accurate neighborhood of the global optimum by taking $\tilde{\Omega}\left(\left( \frac{1}{(1-\gamma)^6\epsilon^2}\right)^{\frac{1}{\omega}} +\left(\frac{1}{1-\gamma}\right)^{\frac{1}{1-\omega}}\right)$ iterations, where $\omega\in(0,1)$ is the decay parameter of the learning rate, and $\gamma$ is the discount factor. Our analysis develops novel techniques to derive finite-time bounds on the difference between two inter-connected stochastic processes, which is new to the literature of stochastic approximation.

Reinforcement learning (RL) [5] studies the problem of how to make sequential decisions to learn and act in unknown environments (which is usually modeled by a Markov Decision Process (MDP)) and maximize the collected rewards. There are mainly two types of algorithms to approach the RL problems: model-based algorithms and model-free algorithms. Model-based RL algorithms keep explicit description of the learned model and make decisions based on this model. In contrast, modelfree algorithms only maintain a group of value functions instead of the complete model of the system dynamics. Due to their space-and time-efficiency, model-free RL algorithms have been getting popular in a wide range of practical tasks (e.g., DQN [16], TRPO [18], and A3C [15]). In RL theory, model-free algorithms are explicitly defined to be the ones whose space complexity is always sublinear relative to the space required to store the MDP parameters [12]. For tabular MDPs (i.e., MDPs with finite number of states and actions, usually denoted by S and A respectively), this requires that the space complexity to be opS

We propose AttendLight, an end-to-end Reinforcement Learning (RL) algorithm for the problem of traffic signal control. Previous approaches for this problem have the shortcoming that they require training for each new intersection with a different structure or traffic flow distribution. AttendLight solves this issue by training a single, universal model for intersections with any number of roads, lanes, phases (possible signals), and traffic flow. To this end, we propose a deep RL model which incorporates two attention models. The first attention model is introduced to handle different numbers of roads-lanes; and the second attention model is intended for enabling decision-making with any number of phases in an intersection. As a result, our proposed model works for any intersection configuration, as long as a similar configuration is represented in the training set. Experiments were conducted with both synthetic and real-world standard benchmark data-sets. The results we show cover intersections with three or four approaching roads; one-directional/bi-directional roads with one, two, and three lanes; different number of phases; and different traffic flows. We consider two regimes: (i) single-environment training, single-deployment, and (ii) multi-environment training, multi-deployment. AttendLight outperforms both classical and other RL-based approaches on all cases in both regimes.