Compositionality is a critical aspect of scalable system design. Reinforcement learning (RL) has recently shown substantial success in task learning, but has only recently begun to truly leverage composition. In this paper, we focus on Boolean composition of learned tasks as opposed to functional or sequential composition. Existing Boolean composition for RL focuses on reaching a satisfying absorbing state in environments with discrete action spaces, but does not support composable safety (i.e., avoidance) constraints. We advance the state of the art in Boolean composition of learned tasks with three contributions: i) introduce two distinct notions of safety in this framework; ii) show how to enforce either safety semantics, prove correctness (under some assumptions), and analyze the trade-offs between the two safety notions; and iii) extend Boolean composition from discrete action spaces to continuous action spaces. We demonstrate these techniques using modified versions of value iteration in a grid world, Deep Q-Network (DQN) in a grid world with image observations, and Twin Delayed DDPG (TD3) in a continuous-observation and continuous-action Bullet physics environment. We believe that these contributions advance the theory of safe reinforcement learning by allowing zero-shot composition of policies satisfying safety properties.

Feature transformation aims to reconstruct an effective representation space by mathematically refining the existing features. It serves as a pivotal approach to combat the curse of dimensionality, enhance model generalization, mitigate data sparsity, and extend the applicability of classical models. Existing research predominantly focuses on domain knowledge-based feature engineering or learning latent representations. However, these methods, while insightful, lack full automation and fail to yield a traceable and optimal representation space. An indispensable question arises: Can we concurrently address these limitations when reconstructing a feature space for a machine-learning task? Our initial work took a pioneering step towards this challenge by introducing a novel self-optimizing framework. This framework leverages the power of three cascading reinforced agents to automatically select candidate features and operations for generating improved feature transformation combinations. Despite the impressive strides made, there was room for enhancing its effectiveness and generalization capability. In this extended journal version, we advance our initial work from two distinct yet interconnected perspectives: 1) We propose a refinement of the original framework, which integrates a graph-based state representation method to capture the feature interactions more effectively and develop different Q-learning strategies to alleviate Q-value overestimation further. 2) We utilize a new optimization technique (actor-critic) to train the entire self-optimizing framework in order to accelerate the model convergence and improve the feature transformation performance. Finally, to validate the improved effectiveness and generalization capability of our framework, we perform extensive experiments and conduct comprehensive analyses.

The notion of robotic manipulation [1, 2] easily invokes the image of a biomimetic robot arm or hand trying to grasp tabletop objects and then rearrange them into desired configurations inferred by exteroceptive sensors such as RGBD cameras. To facilitate this manipulation pipeline, the robot learning community has made tremendous efforts in either how to determine steadier grasping poses in demanding scenarios [3, 4, 5, 6, 7] or how to understand the exteroceptive inputs in a more robust and generalizable way [8, 9, 10, 11, 12, 13]. Acknowledging these progresses, this paper attempts to bypass the challenges in the prevailing pipeline by advocating ArrayBot, a reinforcement learning driven system for distributed manipulation [14], where the objects are manipulated through a great number of actuators with only proprioceptive tactile sensing [15, 16, 17, 18]. Conceptually, the hardware of ArrayBot is a 16 16 array of vertically sliding pillars, each of which can be independently actuated, leading to a 16 16 action space. Functionally, the actuators beneath a tabletop object can support its weight and at the same time cooperate to lift, tilt, and even translate it through proper motion policies.

This paper addresses a novel multi-agent deep reinforcement learning (MADRL)-based positioning algorithm for multiple unmanned aerial vehicles (UAVs) collaboration (i.e., UAVs work as mobile base stations). The primary objective of the proposed algorithm is to establish dependable mobile access networks for cellular vehicle-to-everything (C-V2X) communication, thereby facilitating the realization of high-quality intelligent transportation systems (ITS). The reliable mobile access services can be achieved in following two ways, i.e., i) energy-efficient UAV operation and ii) reliable wireless communication services. For energy-efficient UAV operation, the reward of our proposed MADRL algorithm contains the features for UAV energy consumption models in order to realize efficient operations. Furthermore, for reliable wireless communication services, the quality of service (QoS) requirements of individual users are considered as a part of rewards and 60GHz mmWave radio is used for mobile access. This paper considers the 60GHz mmWave access for utilizing the benefits of i) ultra-wide-bandwidth for multi-Gbps high-speed communications and ii) high-directional communications for spatial reuse that is obviously good for densely deployed users. Lastly, the comprehensive and data-intensive performance evaluation of the proposed MADRL-based algorithm for multi-UAV positioning is conducted in this paper. The results of these evaluations demonstrate that the proposed algorithm outperforms other existing algorithms.

Software testing activities scrutinize the artifacts and the behavior of a software product to find possible defects and ensure that the product meets its expected requirements. Recently, Deep Reinforcement Learning (DRL) has been successfully employed in complex testing tasks such as game testing, regression testing, and test case prioritization to automate the process and provide continuous adaptation. Practitioners can employ DRL by implementing from scratch a DRL algorithm or using a DRL framework. DRL frameworks offer well-maintained implemented state-of-the-art DRL algorithms to facilitate and speed up the development of DRL applications. Developers have widely used these frameworks to solve problems in various domains including software testing. However, to the best of our knowledge, there is no study that empirically evaluates the effectiveness and performance of implemented algorithms in DRL frameworks. Moreover, some guidelines are lacking from the literature that would help practitioners choose one DRL framework over another. In this paper, we empirically investigate the applications of carefully selected DRL algorithms on two important software testing tasks: test case prioritization in the context of Continuous Integration (CI) and game testing. For the game testing task, we conduct experiments on a simple game and use DRL algorithms to explore the game to detect bugs. Results show that some of the selected DRL frameworks such as Tensorforce outperform recent approaches in the literature. To prioritize test cases, we run experiments on a CI environment where DRL algorithms from different frameworks are used to rank the test cases. Our results show that the performance difference between implemented algorithms in some cases is considerable, motivating further investigation.

In recent years, the intelligence of various parts of the home has become one of the essential features of any modern home. One of these parts is the intelligence lighting system that personalizes the light for each person. This paper proposes an intelligent system based on machine learning that personalizes lighting in the instant future location of a recognized user, inferred by trajectory prediction. Our proposed system consists of the following modules: (I) human detection to detect and localize the person in each given video frame, (II) face recognition to identify the detected person, (III) human tracking to track the person in the sequence of video frames and (IV) trajectory prediction to forecast the future location of the user in the environment using Inverse Reinforcement Learning. The proposed method provides a unique profile for each person, including specifications, face images, and custom lighting settings. This profile is used in the lighting adjustment process. Unlike other methods that consider constant lighting for every person, our system can apply each 'person's desired lighting in terms of color and light intensity without direct user intervention. Therefore, the lighting is adjusted with higher speed and better efficiency. In addition, the predicted trajectory path makes the proposed system apply the desired lighting, creating more pleasant and comfortable conditions for the home residents. In the experimental results, the system applied the desired lighting in an average time of 1.4 seconds from the moment of entry, as well as a performance of 22.1mAp in human detection, 95.12% accuracy in face recognition, 93.3% MDP in human tracking, and 10.80 MinADE20, 18.55 MinFDE20, 15.8 MinADE5 and 30.50 MinFDE5 in trajectory prediction.

Demand flexibility plays a vital role in maintaining grid balance, reducing peak demand, and saving customers' energy bills. Given their highly shiftable load and significant contribution to a building's energy consumption, Heating, Ventilation, and Air Conditioning (HVAC) systems can provide valuable demand flexibility to the power systems by adjusting their energy consumption in response to electricity price and power system needs. To exploit this flexibility in both operation time and power, it is imperative to accurately model and aggregate the load flexibility of a large population of HVAC systems as well as designing effective control algorithms. In this paper, we tackle the curse of dimensionality issue in modeling and control by utilizing the concept of laxity to quantify the emergency level of each HVAC operation request. We further propose a two-level approach to address energy optimization for a large population of HVAC systems. The lower level involves an aggregator to aggregate HVAC load laxity information and use least-laxity-first (LLF) rule to allocate real-time power for individual HVAC systems based on the controller's total power. Due to the complex and uncertain nature of HVAC systems, we leverage a reinforcement learning (RL)-based controller to schedule the total power based on the aggregated laxity information and electricity price. We evaluate the temperature control and energy cost saving performance of a large-scale group of HVAC systems in both single-zone and multi-zone scenarios, under varying climate and electricity market conditions. The experiment results indicate that proposed approach outperforms the centralized methods in the majority of test scenarios, and performs comparably to model-based method in some scenarios.

The two-time scale nature of SAC, which is an actor-critic algorithm, is characterised by the fact that the critic estimate has not converged for the actor at any given time, but since the critic learns faster than the actor, it ensures eventual consistency between the two. Various strategies have been introduced in literature to learn better gradient estimates to help achieve better convergence. Since gradient estimates depend upon the critic, we posit that improving the critic can provide a better gradient estimate for the actor at each time. Utilizing this, we propose Soft Actor Retrospective Critic (SARC), where we augment the SAC critic loss with another loss term - retrospective loss - leading to faster critic convergence and consequently, better policy gradient estimates for the actor. An existing implementation of SAC can be easily adapted to SARC with minimal modifications. Through extensive experimentation and analysis, we show that SARC provides consistent improvement over SAC on benchmark environments.

We develop several provably efficient model-free reinforcement learning (RL) algorithms for infinite-horizon average-reward Markov Decision Processes (MDPs). We consider both online setting and the setting with access to a simulator. In the online setting, we propose model-free RL algorithms based on reference-advantage decomposition. Our algorithm achieves $\widetilde{O}(S^5A^2\mathrm{sp}(h^*)\sqrt{T})$ regret after $T$ steps, where $S\times A$ is the size of state-action space, and $\mathrm{sp}(h^*)$ the span of the optimal bias function. Our results are the first to achieve optimal dependence in $T$ for weakly communicating MDPs. In the simulator setting, we propose a model-free RL algorithm that finds an $\epsilon$-optimal policy using $\widetilde{O} \left(\frac{SA\mathrm{sp}^2(h^*)}{\epsilon^2}+\frac{S^2A\mathrm{sp}(h^*)}{\epsilon} \right)$ samples, whereas the minimax lower bound is $\Omega\left(\frac{SA\mathrm{sp}(h^*)}{\epsilon^2}\right)$. Our results are based on two new techniques that are unique in the average-reward setting: 1) better discounted approximation by value-difference estimation; 2) efficient construction of confidence region for the optimal bias function with space complexity $O(SA)$.

Geometric regularity, which leverages data symmetry, has been successfully incorporated into deep learning architectures such as CNNs, RNNs, GNNs, and Transformers. While this concept has been widely applied in robotics to address the curse of dimensionality when learning from high-dimensional data, the inherent reflectional and rotational symmetry of robot structures has not been adequately explored. Drawing inspiration from cooperative multi-agent reinforcement learning, we introduce novel network structures for deep learning algorithms that explicitly capture this geometric regularity. Moreover, we investigate the relationship between the geometric prior and the concept of Parameter Sharing in multi-agent reinforcement learning. Through experiments conducted on various challenging continuous control tasks, we demonstrate the significant potential of the proposed geometric regularity in enhancing robot learning capabilities.