In this paper, we consider same-day delivery with a heterogeneous fleet of vehicles and drones. Customers make delivery requests over the course of the day and the dispatcher dynamically dispatches vehicles and drones to deliver the goods to customers before their delivery deadline. Vehicles can deliver multiple packages in one route but travel relatively slowly due to the urban traffic. Drones travel faster, but they have limited capacity and require charging or battery swaps. To exploit the different strengths of the fleets, we propose a deep Q-learning approach. Our method learns the value of assigning a new customer to either drones or vehicles as well as the option to not offer service at all. To aid feature selection, we present an analytical analysis that demonstrates the role that different types of information have on the value function and decision making. In a systematic computational analysis, we show the superiority of our policy compared to benchmark policies and the effectiveness of our deep Q-learning approach.

In recent years, the interest in leveraging quantum effects for enhancing machine learning tasks has significantly increased. Many algorithms speeding up supervised and unsupervised learning were established. The first framework in which ways to exploit quantum resources specifically for the broader context of reinforcement learning were found is projective simulation. Projective simulation presents an agent-based reinforcement learning approach designed in a manner which may support quantum walk-based speed-ups. Although classical variants of projective simulation have been benchmarked against common reinforcement learning algorithms, very few formal theoretical analyses have been provided for its performance in standard learning scenarios. In this paper, we provide a detailed formal discussion of the properties of this model. Specifically, we prove that one version of the projective simulation model, understood as a reinforcement learning approach, converges to optimal behavior in a large class of Markov decision processes. This proof shows that a physically-inspired approach to reinforcement learning can guarantee to converge.

The paper describes an implementation of deep reinforcement learning through self-supervised learning within the proof assistant HOL4. A close interaction between the machine learning modules and the HOL4 library is achieved by the choice of tree neural networks (TNNs) as machine learning models and the internal use of HOL4 terms to represent tree structures of TNNs. Recursive improvement is possible when a given task is expressed as a search problem. In this case, a Monte Carlo Tree Search (MCTS) algorithm guided by a TNN can be used to explore the search space and produce better examples for training the next TNN. As an illustration, tasks over propositional and arithmetical terms, representative of fundamental theorem proving techniques, are specified and learned: truth estimation, end-to-end computation, term rewriting and term synthesis.

Robust MDPs are a promising framework for computing robust policies in reinforcement learning. Ambiguity sets, which represent the plausible errors in transition probabilities, determine the trade-off between robustness and average-case performance. The standard practice of defining ambiguity sets using the $L_1$ norm leads, unfortunately, to loose and impractical guarantees. This paper describes new methods for optimizing the shape of ambiguity sets beyond the $L_1$ norm. We derive new high-confidence sampling bounds for weighted $L_1$ and weighted $L_\infty$ ambiguity sets and describe how to compute near-optimal weights from rough value function estimates. Experimental results on a diverse set of benchmarks show that optimized ambiguity sets provide significantly tighter robustness guarantees.

Till now we have been through many reinforcement learning examples, from on-policy to off-policy, discrete state space to continuous state space. All these examples vary in some way, but you might have noticed that they have at least one shared trait -- Episodic, that is all of which have a clear starting point and ending point, and whenever an agent reaches the goal, it starts over again and again until reaching certain number of loops. In this article, we will extend the idea to non-episodic task, that is task which has no clear ending point and the agent goes on forever in the environment setting. The main concept that will be applied to non-episodic task is average reward. The average reward setting also applies to continuing problems, problems for which the interaction between agent and environment goes on and on forever without termination or start states.

We consider a novel application of inverse reinforcement learning which involves modeling, learning and predicting the commenting behavior of YouTube viewers. Each group of users is modeled as a rationally inattentive Bayesian agent. Our methodology integrates three key components. First, to identify distinct commenting patterns, we use deep embedded clustering to estimate framing information (essential extrinsic features) that clusters users into distinct groups. Second, we present an inverse reinforcement learning algorithm that uses Bayesian revealed preferences to test for rationality: does there exist a utility function that rationalizes the given data, and if yes, can it be used to predict future behavior? Finally, we impose behavioral economics constraints stemming from rational inattention to characterize the attention span of groups of users.The test imposes a R{\'e}nyi mutual information cost constraint which impacts how the agent can select attention strategies to maximize their expected utility. After a careful analysis of a massive YouTube dataset, our surprising result is that in most YouTube user groups, the commenting behavior is consistent with optimizing a Bayesian utility with rationally inattentive constraints. The paper also highlights how the rational inattention model can accurately predict future commenting behavior. The massive YouTube dataset and analysis used in this paper are available on GitHub and completely reproducible.

Reinforcement learning is a promising approach to learning control policies for performing complex multi-agent robotics tasks. However, a policy learned in simulation often fails to guarantee even simple safety properties such as obstacle avoidance. To ensure safety, we propose multi-agent model predictive shielding (MAMPS), an algorithm that provably guarantees safety for an arbitrary learned policy. In particular, it operates by using the learned policy as often as possible, but instead uses a backup policy in cases where it cannot guarantee the safety of the learned policy. Using a multi-agent simulation environment, we show how MAMPS can achieve good performance while ensuring safety.

Collision avoidance algorithms are essential for safe and efficient robot operation among pedestrians. This work proposes using deep reinforcement (RL) learning as a framework to model the complex interactions and cooperation with nearby, decision-making agents (e.g., pedestrians, other robots). Existing RL-based works assume homogeneity of agent policies, use specific motion models over short timescales, or lack a mechanism to consider measurements taken with a large number (possibly varying) of nearby agents. Therefore, this work develops an algorithm that learns collision avoidance among a variety of types of non-communicating, dynamic agents without assuming they follow any particular behavior rules. It extends our previous work by introducing a strategy using Long Short-Term Memory (LSTM) that enables the algorithm to use observations of an arbitrary number of other agents, instead of a small, fixed number of neighbors. The proposed algorithm is shown to outperform a classical collision avoidance algorithm, another deep RL-based algorithm, and scales with the number of agents better (fewer collisions, shorter time to goal) than our previously published learning-based approach. Analysis of the LSTM provides insights into how observations of nearby agents affect the hidden state and quantifies the performance impact of various agent ordering heuristics. The learned policy generalizes to several applications beyond the training scenarios: formation control (arrangement into letters), an implementation on a fleet of four multirotors, and an implementation on a fully autonomous robotic vehicle capable of traveling at human walking speed among pedestrians.

Yet many of the applications we've seen are single-event driven. Some examples: Is the image shown that of a cat? Given a word, translate it into English. Execute a given command, such as "Turn on the Light." Deep learning techniques have been responsible for many AI applications like these, but fundamentally, deep learning is task-oriented.