Reinforcement Learning(RL) has achieved tremendous development in recent years, but still faces significant obstacles in addressing complex real-life problems due to the issues of poor system generalization, low sample efficiency as well as safety and interpretability concerns. The core reason underlying such dilemmas can be attributed to the fact that most of the work has focused on the computational aspect of value functions or policies using a representational model to describe atomic components of rewards, states and actions etc, thus neglecting the rich high-level declarative domain knowledge of facts, relations and rules that can be either provided a priori or acquired through reasoning over time. Recently, there has been a rapidly growing interest in the use of Knowledge Representation and Reasoning(KRR) methods, usually using logical languages, to enable more abstract representation and efficient learning in RL. In this survey, we provide a preliminary overview on these endeavors that leverage the strengths of KRR to help solving various problems in RL, and discuss the challenging open problems and possible directions for future work in this area.

Autonomous agents (robots) face tremendous challenges while interacting with heterogeneous human agents in close proximity. One of these challenges is that the autonomous agent does not have an accurate model tailored to the specific human that the autonomous agent is interacting with, which could sometimes result in inefficient human-robot interaction and suboptimal system dynamics. Developing an online method to enable the autonomous agent to learn information about the human model is therefore an ongoing research goal. Existing approaches position the robot as a passive learner in the environment to observe the physical states and the associated human response. This passive design, however, only allows the robot to obtain information that the human chooses to exhibit, which sometimes doesn't capture the human's full intention. In this work, we present an online optimization-based probing procedure for the autonomous agent to clarify its belief about the human model in an active manner. By optimizing an information radius, the autonomous agent chooses the action that most challenges its current conviction. This procedure allows the autonomous agent to actively probe the human agents to reveal information that's previously unavailable to the autonomous agent. With this gathered information, the autonomous agent can interactively influence the human agent for some designated objectives. Our main contributions include a coherent theoretical framework that unifies the probing and influence procedures and two case studies in autonomous driving that show how active probing can help to create better participant experience during influence, like higher efficiency or less perturbations.

Time series data are ubiquitous nowadays. Whereas most of the literature on the topic deals with real-valued time series, categorical time series have received much less attention. However, the development of data mining techniques for this kind of data has substantially increased in recent years. The R package ctsfeatures offers users a set of useful tools for analyzing categorical time series. In particular, several functions allowing the extraction of well-known statistical features and the construction of illustrative graphs describing underlying temporal patterns are provided in the package. The output of some functions can be employed to perform traditional machine learning tasks including clustering, classification and outlier detection. The package also includes two datasets of biological sequences introduced in the literature for clustering purposes, as well as three interesting synthetic databases. In this work, the main characteristics of the package are described and its use is illustrated through various examples. Practitioners from a wide variety of fields could benefit from the valuable tools provided by ctsfeatures.

Classical policy search algorithms for robotics typically require performing extensive explorations, which are time-consuming and expensive to implement with real physical platforms. To facilitate the efficient learning of robot manipulation skills, in this work, we propose a new approach comprised of three modules: (1) learning of general prior knowledge with random explorations in simulation, including state representations, dynamic models, and the constrained action space of the task; (2) extraction of a state alignment-based reward function from a single demonstration video; (3) real-time optimization of the imitation policy under systematic safety constraints with sampling-based model predictive control. This solution results in an efficient one-shot imitation-from-video strategy that simplifies the learning and execution of robot skills in real applications. Specifically, we learn priors in a scene of a task family and then deploy the policy in a novel scene immediately following a single demonstration, preventing time-consuming and risky explorations in the environment. As we do not make a strong assumption of dynamic consistency between the scenes, learning priors can be conducted in simulation to avoid collecting data in real-world circumstances. We evaluate the effectiveness of our approach in the context of contact-rich fabric manipulation, which is a common scenario in industrial and domestic tasks. Detailed numerical simulations and real-world hardware experiments reveal that our method can achieve rapid skill acquisition for challenging manipulation tasks.

This paper studies temporal planning in probabilistic environments, modeled as labeled Markov decision processes (MDPs), with user preferences over multiple temporal goals. Existing works reflect such preferences as a prioritized list of goals. This paper introduces a new specification language, termed prioritized qualitative choice linear temporal logic on finite traces, which augments linear temporal logic on finite traces with prioritized conjunction and ordered disjunction from prioritized qualitative choice logic. This language allows for succinctly specifying temporal objectives with corresponding preferences accomplishing each temporal task. The finite traces that describe the system's behaviors are ranked based on their dissatisfaction scores with respect to the formula. We propose a systematic translation from the new language to a weighted deterministic finite automaton. Utilizing this computational model, we formulate and solve a problem of computing an optimal policy that minimizes the expected score of dissatisfaction given user preferences. We demonstrate the efficacy and applicability of the logic and the algorithm on several case studies with detailed analyses for each.

MOBA games, e.g., Dota2 and Honor of Kings, have been actively used as the testbed for the recent AI research on games, and various AI systems have been developed at the human level so far. However, these AI systems mainly focus on how to compete with humans, less on exploring how to collaborate with humans. To this end, this paper makes the first attempt to investigate human-agent collaboration in MOBA games. In this paper, we propose to enable humans and agents to collaborate through explicit communication by designing an efficient and interpretable Meta-Command Communication-based framework, dubbed MCC, for accomplishing effective human-agent collaboration in MOBA games. The MCC framework consists of two pivotal modules: 1) an interpretable communication protocol, i.e., the Meta-Command, to bridge the communication gap between humans and agents; 2) a meta-command value estimator, i.e., the Meta-Command Selector, to select a valuable meta-command for each agent to achieve effective human-agent collaboration. Experimental results in Honor of Kings demonstrate that MCC agents can collaborate reasonably well with human teammates and even generalize to collaborate with different levels and numbers of human teammates. Videos are available at https://sites.google.com/view/mcc-demo.

Motion prediction is a key factor towards the full deployment of autonomous vehicles. It is fundamental in order to assure safety while navigating through highly interactive complex scenarios. In this work, the framework IAMP (Interaction- Aware Motion Prediction), producing multi-modal probabilistic outputs from the integration of a Dynamic Bayesian Network and Markov Chains, is extended with a learning-based approach. The integration of a machine learning model tackles the limitations of the ruled-based mechanism since it can better adapt to different driving styles and driving situations. The method here introduced generates context-dependent acceleration distributions used in a Markov-chain-based motion prediction. This hybrid approach results in better evaluation metrics when compared with the baseline in the four

In this work, we propose the Informed Batch Belief Trees (IBBT) algorithm for motion planning under motion and sensing uncertainties. The original stochastic motion planning problem is divided into a deterministic motion planning problem and a graph search problem. We solve the deterministic planning problem using sampling-based methods such as PRM or RRG to construct a graph of nominal trajectories. Then, an informed cost-to-go heuristic for the original problem is computed based on the nominal trajectory graph. Finally, we grow a belief tree by searching over the graph using the proposed heuristic. IBBT interleaves between batch state sampling, nominal trajectory graph construction, heuristic computing, and search over the graph to find belief space motion plans. IBBT is an anytime, incremental algorithm. With an increasing number of batches of samples added to the graph, the algorithm finds motion plans that converge to the optimal one. IBBT is efficient by reusing results between sequential iterations. The belief tree searching is an ordered search guided by an informed heuristic. We test IBBT in different planning environments. Our numerical investigation confirms that IBBT finds non-trivial motion plans and is faster compared with previous similar methods.

DNA sequencing allows for the determination of the genetic code of an organism, and therefore is an indispensable tool that has applications in Medicine, Life Sciences, Evolutionary Biology, Food Sciences and Technology, and Agriculture. In this paper, we present several novel methods of performing classical-to-quantum data encoding inspired by various mathematical fields, and we demonstrate these ideas within Bioinformatics. In particular, we introduce algorithms that draw inspiration from diverse fields such as Electrical and Electronic Engineering, Information Theory, Differential Geometry, and Neural Network architectures. We provide a complete overview of the existing data encoding schemes and show how to use them in Genomics. The algorithms provided utilise lossless compression, wavelet-based encoding, and information entropy. Moreover, we propose a contemporary method for testing encoded DNA sequences using Quantum Boltzmann Machines. To evaluate the effectiveness of our algorithms, we discuss a potential dataset that serves as a sandbox environment for testing against real-world scenarios. Our research contributes to developing classical-to-quantum data encoding methods in the science of Bioinformatics by introducing innovative algorithms that utilise diverse fields and advanced techniques. Our findings offer insights into the potential of Quantum Computing in Bioinformatics and have implications for future research in this area.

Although deep reinforcement learning (DRL) has many success stories, the large-scale deployment of policies learned through these advanced techniques in safety-critical scenarios is hindered by their lack of formal guarantees. Variational Markov Decision Processes (VAE-MDPs) are discrete latent space models that provide a reliable framework for distilling formally verifiable controllers from any RL policy. While the related guarantees address relevant practical aspects such as the satisfaction of performance and safety properties, the VAE approach suffers from several learning flaws (posterior collapse, slow learning speed, poor dynamics estimates), primarily due to the absence of abstraction and representation guarantees to support latent optimization. We introduce the Wasserstein auto-encoded MDP (WAE-MDP), a latent space model that fixes those issues by minimizing a penalized form of the optimal transport between the behaviors of the agent executing the original policy and the distilled policy, for which the formal guarantees apply. Our approach yields bisimulation guarantees while learning the distilled policy, allowing concrete optimization of the abstraction and representation model quality. Our experiments show that, besides distilling policies up to 10 times faster, the latent model quality is indeed better in general. Moreover, we present experiments from a simple time-to-failure verification algorithm on the latent space. The fact that our approach enables such simple verification techniques highlights its applicability.