Recent technology development brings the booming of numerous new Demand-Driven Services (DDS) into urban lives, including ridesharing, on-demand delivery, express systems and warehousing. In DDS, a service loop is an elemental structure, including its service worker, the service providers and corresponding service targets. The service workers should transport either humans or parcels from the providers to the target locations. Various planning tasks within DDS can thus be classified into two individual stages: 1) Dispatching, which is to form service loops from demand/supply distributions, and 2)Routing, which is to decide specific serving orders within the constructed loops. Generating high-quality strategies in both stages is important to develop DDS but faces several challenging. Meanwhile, deep reinforcement learning (DRL) has been developed rapidly in recent years. It is a powerful tool to solve these problems since DRL can learn a parametric model without relying on too many problem-based assumptions and optimize long-term effect by learning sequential decisions. In this survey, we first define DDS, then highlight common applications and important decision/control problems within. For each problem, we comprehensively introduce the existing DRL solutions, and further summarize them in \textit{https://github.com/tsinghua-fib-lab/DDS\_Survey}. We also introduce open simulation environments for development and evaluation of DDS applications. Finally, we analyze remaining challenges and discuss further research opportunities in DRL solutions for DDS.

"High Quality Related Search Query Suggestions" task aims at recommending search queries which are real, accurate, diverse, relevant and engaging. Obtaining large amounts of query-quality human annotations is expensive. Prior work on supervised query suggestion models suffered from selection and exposure bias, and relied on sparse and noisy immediate user-feedback (e.g., clicks), leading to low quality suggestions. Reinforcement Learning techniques employed to reformulate a query using terms from search results, have limited scalability to large-scale industry applications. To recommend high quality related search queries, we train a Deep Reinforcement Learning model to predict the query a user would enter next. The reward signal is composed of long-term session-based user feedback, syntactic relatedness and estimated naturalness of generated query. Over the baseline supervised model, our proposed approach achieves a significant relative improvement in terms of recommendation diversity (3%), down-stream user-engagement (4.2%) and per-sentence word repetitions (82%).

In this work we present a novel approach to hierarchical reinforcement learning for linearly-solvable Markov decision processes. Our approach assumes that the state space is partitioned, and the subtasks consist in moving between the partitions. We represent value functions on several levels of abstraction, and use the compositionality of subtasks to estimate the optimal values of the states in each partition. The policy is implicitly defined on these optimal value estimates, rather than being decomposed among the subtasks. As a consequence, our approach can learn the globally optimal policy, and does not suffer from the non-stationarity of high-level decisions. If several partitions have equivalent dynamics, the subtasks of those partitions can be shared. If the set of boundary states is smaller than the entire state space, our approach can have significantly smaller sample complexity than that of a flat learner, and we validate this empirically in several experiments.

Inspired by double q learning algorithm, the double DQN algorithm was originally proposed in order to address the overestimation issue in the original DQN algorithm. The double DQN has successfully shown both theoretically and empirically the importance of decoupling in terms of action evaluation and selection in computation of targets values; although, all the benefits were acquired with only a simple adaption to DQN algorithm, minimal possible change as it was mentioned by the authors. Nevertheless, there seems a roll-back in the proposed algorithm of Double-DQN since the parameters of policy network are emerged again in the target value function which were initially withdrawn by DQN with the hope of tackling the serious issue of moving targets and the instability caused by it (i.e., by moving targets) in the process of learning. Therefore, in this paper three modifications to the Double-DQN algorithm are proposed with the hope of maintaining the performance in the terms of both stability and overestimation. These modifications are focused on the logic of decoupling the best action selection and evaluation in the target value function and the logic of tackling the moving targets issue. Each of these modifications have their own pros and cons compared to the others. The mentioned pros and cons mainly refer to the execution time required for the corresponding algorithm and the stability provided by the corresponding algorithm. Also, in terms of overestimation, none of the modifications seem to underperform compared to the original Double-DQN if not outperform it. With the intention of evaluating the efficacy of the proposed modifications, multiple empirical experiments along with theoretical experiments were conducted. The results obtained are represented and discussed in this article.

Artificial Intelligence has been developed for decades with the achievement of great progress. Recently, deep learning shows its ability to solve many real world problems, e.g. image classification and detection, natural language processing, playing GO. Theoretically speaking, an artificial neural network can fit any function and reinforcement learning can learn from any delayed reward. But in solving real world tasks, we still need to spend a lot of effort to adjust algorithms to fit task unique features. This paper proposes that the reason of this phenomenon is the sparse feedback feature of the nature, and a single algorithm, no matter how we improve it, can only solve dense feedback tasks or specific sparse feedback tasks. This paper first analyses how sparse feedback affects algorithm perfomance, and then proposes a pattern that explains how to accumulate knowledge to solve sparse feedback problems.

Learning generalizable manipulation skills is central for robots to achieve task automation in environments with endless scene and object variations. However, existing robot learning environments are limited in both scale and diversity of 3D assets (especially of articulated objects), making it difficult to train and evaluate the generalization ability of agents over novel objects. In this work, we focus on object-level generalization and propose SAPIEN Manipulation Skill Benchmark (abbreviated as ManiSkill), a large-scale learning-from-demonstrations benchmark for articulated object manipulation with 3D visual input (point cloud and RGB-D image). ManiSkill supports object-level variations by utilizing a rich and diverse set of articulated objects, and each task is carefully designed for learning manipulations on a single category of objects. We equip ManiSkill with a large number of high-quality demonstrations to facilitate learning-from-demonstrations approaches and perform evaluations on baseline algorithms. We believe that ManiSkill can encourage the robot learning community to explore more on learning generalizable object manipulation skills.

The game of monopoly is an adversarial multi-agent domain where there is no fixed goal other than to be the last player solvent, There are useful subgoals like monopolizing sets of properties, and developing them. There is also a lot of randomness from dice rolls, card-draws, and adversaries' strategies. This unpredictability is made worse when unknown novelties are added during gameplay. Given these challenges, Monopoly was one of the test beds chosen for the DARPA-SAILON program which aims to create agents that can detect and accommodate novelties. To handle the game complexities, we developed an agent that eschews complete plans, and adapts it's policy online as the game evolves. In the most recent independent evaluation in the SAILON program, our agent was the best performing agent on most measures. We herein present our approach and results.

Dr. Amy Compton-Phillips is the chief clinical officer and executive vice president for Providence St. Humanity is getting a peek into the future with a new bipedal robot named "Cassie," which ran a 5K recently in 53 minutes and only took two tumbles along the way. Agility Robotics, a company launched at Oregon State University, developed Cassie through a $1 million grant from the Defense Advanced Research Projects Agency. Four-legged robots have a big advantage over bipedal robots when it comes to stability and maneuverability, but researchers at OSU are using a "deep reinforcement learning algorithm" to make Cassie's ostrich-like legs run smoothly. "Deep reinforcement learning is a powerful method in AI that opens up skills like running, skipping and walking up and down stairs," Yesh Godse, an undergraduate in the lab, explained in a statement. Jonathan Hurst, a robotics professor at OSU, said that robots like Cassie will deliver packages and even help people in their homes.

We train embodied neural networks to plan and navigate unseen complex 3D environments, emphasising real-world deployment. Rather than requiring prior knowledge of the agent or environment, the planner learns to model the state transitions and rewards. To avoid the potentially hazardous trial-and-error of reinforcement learning, we focus on differentiable planners such as Value Iteration Networks (VIN), which are trained offline from safe expert demonstrations. Although they work well in small simulations, we address two major limitations that hinder their deployment. First, we observed that current differentiable planners struggle to plan long-term in environments with a high branching complexity. While they should ideally learn to assign low rewards to obstacles to avoid collisions, we posit that the constraints imposed on the network are not strong enough to guarantee the network to learn sufficiently large penalties for every possible collision. We thus impose a structural constraint on the value iteration, which explicitly learns to model any impossible actions. Secondly, we extend the model to work with a limited perspective camera under translation and rotation, which is crucial for real robot deployment. Many VIN-like planners assume a 360 degrees or overhead view without rotation. In contrast, our method uses a memory-efficient lattice map to aggregate CNN embeddings of partial observations, and models the rotational dynamics explicitly using a 3D state-space grid (translation and rotation). Our proposals significantly improve semantic navigation and exploration on several 2D and 3D environments, succeeding in settings that are otherwise challenging for this class of methods. As far as we know, we are the first to successfully perform differentiable planning on the difficult Active Vision Dataset, consisting of real images captured from a robot.

Proxemics is a branch of non-verbal communication concerned with studying the spatial behavior of people and animals. This behavior is an essential part of the communication process due to delimit the acceptable distance to interact with another being. With increasing research on human-agent interaction, new alternatives are needed that allow optimal communication, avoiding agents feeling uncomfortable. Several works consider proxemic behavior with cognitive agents, where human-robot interaction techniques and machine learning are implemented. However, environments consider fixed personal space and that the agent previously knows it. In this work, we aim to study how agents behave in environments based on proxemic behavior, and propose a modified gridworld to that aim. This environment considers an issuer with proxemic behavior that provides a disagreement signal to the agent. Our results show that the learning agent can identify the proxemic space when the issuer gives feedback about agent performance.