Learning to Drive via Apprenticeship Learning and Deep Reinforcement Learning

This paper presents a parameter selection method of notch filters for suppressing mechanical resonances in industrial servo systems using the deep deterministic policy gradient (DDPG) algorithm. Several methods for tuning the notch filter parameters were studied such as the fast-Fourier-transform-based methods, extended-Kalman-filter-based methods and adaptive notch filter methods. However, these methods do not find the Q parameters of notch filters which play an important role in determining the system stability, and do not consider the cases in which multiple notch filters are required. Deep-Q-network-based method was developed to solve these problems, but the notch filter parameter tuning is limited to discrete action spaces. This paper develops a new parameter selection method of notch filters, using the DDPG algorithm. DDPG algorithm, which is a model-free and actor-critic algorithm using deep neural networks, is utilized for its capability to operate over continuous action spaces. Experiments are performed using an actual industrial servo system to demonstrate that the developed parameter selection method successfully finds the notch filter parameters to suppress the resonances of the system.

The research on autonomous driving based on deep reinforcement learning algorithms is a research hotspot. Traditional autonomous driving requires human involvement, and the autonomous driving algorithms based on supervised learning must be trained in advance using human experience. To deal with autonomous driving problems, this paper proposes an improved end-to-end deep deterministic policy gradient (DDPG) algorithm based on the convolutional block attention mechanism, and it is called multi-input attention prioritized deep deterministic policy gradient algorithm (MAPDDPG). Both the actor network and the critic network of the model have the same structure with symmetry. Meanwhile, the attention mechanism is introduced to help the vehicles focus on useful environmental information. The experiments are conducted in the open racing car simulator (TORCS)and the results of five experiment runs on the test tracks are averaged to obtain the final result. Compared with the state-of-the-art algorithm, the maximum reward increases from 62,207 to 116,347, and the average speed increases from 135 km/h to 193 km/h, while the number of success episodes to complete a circle increases from 96 to 147. Also, the variance of the distance from the vehicle to the center of the road is compared, and the result indicates that the variance of the DDPG is 0.6 m while that of the MAPDDPG is only 0.2 m. The above results indicate that the proposed MAPDDPG achieves excellent performance.

Energy efficient task scheduling based on deep reinforcement learning in cloud environment: A specialized review

Anti-rolling devices are widely used in modern shipboard components. In particular, ship anti-rolling control systems are developed to achieve a wide range of ship speeds and efficient anti-rolling capabilities. However, factors that are challenging to solve accurately, such as strong nonlinearities, a complex working environment, and hydrodynamic system parameters, limit the investigation of the rolling motion of ships at sea. Moreover, current anti-rolling control systems still face several challenges, such as poor nonlinear adaptability and manual parameter adjustment. In this regard, this study developed a dynamic model for a ship anti-rolling system. In addition, based on deep reinforcement learning (DRL), an efficient anti-rolling controller was developed using a deep deterministic policy gradient (DDPG) algorithm. Finally, the developed system was applied to a ship anti-rolling device based on the Magnus effect. The advantages of reinforcement learning adaptive control enable controlling an anti-rolling system under various wave angles, ship speeds, and wavelengths. The results revealed that the anti-rolling efficiency of the intelligent ship anti-rolling control method using the DDPG algorithm surpassed 95% and had fast convergence. This study lays the foundation for developing a DRL anti-rolling controller for full-scale ships.

The UAV pursuit-evasion strategy based on Deep Deterministic Policy Gradient (DDPG) algorithm is a current research hotspot. However, this algorithm has the defect of low efficiency in sample exploration. To solve this problem, this paper uses the imitation learning (IL) to improve the DDPG exploration strategy. A kind of quasiproportional guidance control law is designed to generate effective learning samples, which are used as the data of the initial experience pool of DDPG algorithm. The UAV pursuit-evasion strategy based on DDPG and imitation learning (IL-DDPG) is proposed, and the algorithm obtains the data from the experience pool for experience playback learning, which improves the exploration efficiency of the algorithm in the initial stage of training and avoids the problem of too many useless exploration in the training process. The simulation results show that the trained pursuit-UAV can flexibly adjust the flight speed and flight attitude to pursuit the evasion-UAV quickly. It also verifies that the improved DDPG algorithm is more effective than the basic DDPG algorithm to improve the training efficiency.

This work proposes a non-singular fast terminal sliding mode control (NFTSMC) strategy based on the Twin Delayed Deep Deterministic Policy Gradient (TD3) algorithm and a nonlinear disturbance observer (NDO) to address the issues of modeling errors, motion disturbances, and transmission friction in robotic manipulators. Firstly, a novel modular serial 5-DOF robotic manipulator configuration is designed, and its kinematic and dynamic models are established. Secondly, a nonlinear disturbance observer is employed to estimate the total disturbance of the system and apply feedforward compensation. Based on boundary layer technology, an improved NFTSMC method is proposed to accelerate the convergence of tracking errors, reduce chattering, and avoid singularity issues inherent in traditional terminal sliding mode control. The stability of the designed control system is proved using Lyapunov stability theory. Subsequently, a deep reinforcement learning (DRL) agent based on the TD3 algorithm is trained to adaptively adjust the control gains of the non-singular fast terminal sliding mode controller. The dynamic information of the robotic manipulator is used as the input to the TD3 agent, which searches for optimal controller parameters within a continuous action space. A composite reward function is designed to ensure the stable and efficient learning of the TD3 agent. Finally, the motion characteristics of three joints for the designed 5-DOF robotic manipulator are analyzed. The results show that compared to the non-singular fast terminal sliding mode control algorithm based on a nonlinear disturbance observer (NDONFT), the non-singular fast terminal sliding mode control algorithm integrating a nonlinear disturbance observer and the Twin Delayed Deep Deterministic Policy Gradient algorithm (TD3NDONFT) reduces the mean absolute error of position tracking for the three joints by 7.14%, 19.94%, and 6.14%, respectively, and reduces the mean absolute error of velocity tracking by 1.78%, 9.10%, and 2.11%, respectively. These results verify the effectiveness of the proposed algorithm in enhancing the trajectory tracking accuracy of the robotic manipulator under unknown time-varying disturbances and demonstrate its strong robustness against sudden disturbances.

Piezoelectric inkjet printing has important applications in high-precision manufacturing, but precise control of droplet quality faces challenges such as the nonlinear coupling between drive waveform parameters and droplet characteristics, as well as environmental disturbances. To address these issues, this paper proposes a closed-loop droplet control method based on a curriculum deep deterministic policy gradient (DDPG) algorithm, with the standard deviation of droplet volume and velocity as the main optimization objectives. To tackle the complex mapping relationships and boost training efficiency, we first built a high-fidelity simulation environment using a four-layer deep residual network trained on real-world industrial ink droplet data. Following that, we designed a dynamic weight-adaptive composite reward mechanism and integrated a curriculum learning strategy with the Deep Deterministic Policy Gradient (DDPG) algorithm. Relying on our self-developed droplet observation platform, we achieve closed-loop control of the standard deviation of droplet volume and velocity. Experimental results show that this method can precisely control the droplet volume within ±0.1 pl of the target value, while keeping the velocity standard deviation below 40 mm/s. The adjustment process is stable without severe oscillations, and the method demonstrates strong robustness against environmental disturbances such as ink supply pressure. This provides an efficient and practical solution for the automated control of droplet quality in piezoelectric inkjet printing.

In a debris mitigation mission, a crucial phase of the proximity operation for a space manipulator is chasing a capture point on a noncooperative target satellite. Knowing the uncertain position and velocity of the target, a learning-based online trajectory planner offers a robust solution to the chasing problem. This paper uses the concept of transfer learning to develop an online trajectory generator for the task of capturing a moving target with an uncertain space manipulator. We divide this complex task into multiple sub-tasks and order them based on their difficulty level. We employ the Deep Deterministic Policy Gradient (DDPG) algorithm to learn each sub-task individually. The DDPG is a deep reinforcement learning approach that provides the ability to work with continuous states and actions by approximating the action-value function and the policy with neural networks. We propose a novel method to transfer the knowledge gained in an easier sub-task to a more difficult one in the form of expert policy and transition memories. State and action representation has a crucial impact on learning performance, which is comprehensively studied in this paper for the task of capturing a moving target. Considering the learning performance, we show the existence of an optimal state repre-sentation, which is not necessarily the minimal representation of the system. We compare different action representations of a manipulator, i.e., joint space and workspace velocities, and demonstrate the superiority of the workspace actions. Finally, the developed transfer learning approach is implemented on a planar space manipulator with an onboard 2-link arm to generate trajectories that can capture a target randomly moving with the maximum speed of the manipulator's end effector. To show the efficacy of the approach, its results are compared with the case where the agent learns the task from scratch.

Deep Reinforcement Learning (DRL) is a powerful approach for generating control strategies for a variety of complex systems, representing an emerging paradigm in control applications. An important feature of Deep RL is that it does not explicitly model the process, but instead it relies on optimization-driven techniques to devise effective control policies. Despite its remarkable success in simulated environments, RL holds great potential in real-world applications. This article explores the complex challenges involved in implementing Deep Reinforcement Learning (DRL) algorithms on a cable-driven parallel robot. A key contribution of this work as specific advancement is the integration of a Proportional-Integral-Derivative (PID) controller within the RL framework, establishing a unique approach to CDPR control that leverages adaptive learning capabilities. A Reinforcement Learning (RL) agent for reference tracking is trained using the novel application of the adaptive-featured Twin Delayed Deep Deterministic (TD3) policy gradient algorithm, tailored to enhance CDPR adaptability and precision in dynamic environments. The first step is to test the performance of the trained agent on point-to-point robotic application tasks. As a result of such tasks, it is possible to evaluate the level of adaptability and performance of the RL agent. Multiple experiments are conducted to assess the versatility of the RL agent involving linear and circular scenarios. This research significantly advances the field by demonstrating the applicability of RL for complex robotic structures like CDPRs, showcasing promising results that underline the robustness and adaptability of the proposed approach. As a result of the TD3 adaptive learning process, the trained agent is able to perform the designated action in order to determine which policy stands out as the most rewarding.

The design and implementation of a deep reinforcement learning and quantum finance theory-inspired portfolio investment management system

Objective As the core issue of ship navigation safety, ship collision avoidance always depends on the captain's personal status and judgment, which has certain potential safety hazards. In order to coordinate all ships (cruise ships, cargo ships, etc.) in key waters and predict their paths, it is necessary to establish an anti-collision early warning mechanism. Methods Using the deep deterministic policy gradient (DDPG) algorithm and the ship domain model, the electronic chart is used to simulate the ship's navigation path, and the improved strategy of DDPG algorithm based on the key learning of failure region and the improved parameters of ship domain model according to the characteristics of cruise ships are proposed, Improve the accuracy of route prediction and anti-collision. Results Using the improved DDPG algorithm and the improved ship domain model, compared with the previous algorithm, the accuracy of ship collision avoidance is improved from 84.9% to 89.7%, and the average error between the simulated route and the real route is reduced from 25.2 m to 21.4 m. Conclusion Through the ship collision avoidance path planning based on the improved DDPG algorithm and the improved ship domain model, the ship route supervision function in water area can be realized, and when the predicted route intersects with other ships, the dispatcher will be alerted to realize the anti-collision early warning mechanism.

An improved Deep Deterministic Policy Gradient (DDPG) algorithm, integrating self-attention mechanisms, adversarial training, and prioritized experience replay, is proposed to address the limitations of state representation capability, sample efficiency, and algorithm robustness in the DDPG algorithm under complex dynamic environments. First, a multihead self-attention module is constructed within the Critic network to enhance the network’s spatial modeling capability for complex environments by parallel computing multidimensional state-action association features. This improves the accuracy of Q-value estimation and the stability of training. Second, an adversarial training mechanism is introduced, where adversarial samples are proportionally mixed into the training data, enhancing the algorithm’s adaptability to state disturbances. Meanwhile, a prioritized experience replay pool is designed based on the SumTree structure, improving the reuse efficiency of high-value samples. Finally, dynamic and static scenarios are built on the Gazebo simulation platform, and real-world experiments are conducted. The results show that, compared with the original DDPG algorithm, the improved algorithm achieves a 55.3% faster convergence speed in dynamic scenarios, an 80.2% reduction in Critic loss, and stronger generalization ability across different scenarios. Real-world tests further validate the superiority of the algorithm in dynamic obstacle avoidance and trajectory smoothness.

In this study we investigate the potential of using Deep Reinforcement Learning (DRL) to day trade stocks, taking into account the constraints imposed by the stock market, such as liquidity, latency, slippage and transaction costs. More specifically, we use a Deep Deterministic Policy Gradient (DDPG) algorithm to solve a series of asset allocation problems in order to define the percentage of capital that must be invested in each asset at each period, executing exclusively day trade operations. DDPG is a model-free, off-policy actor-critic method that can learn policies in high-dimensional and continuous action and state spaces, like the ones normally found in financial market environments. The proposed day trading system was tested in B3 - Brazil Stock Exchange, an important and understudied market, especially considering the application of DRL techniques to alpha generation. A series of experiments were performed from the beginning of 2017 until the end of 2019 and compared with ten benchmarks, including Ibovespa, the most important Brazilian market index, and the stock portfolios suggested by the main Brazilian banks and brokers during these years. The results were evaluated considering return and risk metrics and showed that the proposed method outperformed the benchmarks by a huge margin. The best results obtained by the algorithm had a cumulative percentage return of 311% in three years, with an annual average maximum drawdown around 19%.

An optimal solutions-guided deep reinforcement learning approach for online energy storage control

The food industry faces significant challenges in managing operational costs due to its high energy intensity and rising energy prices. Industrial food-processing facilities, with substantial thermal capacities and large demands for cooling and heating, offer promising opportunities for demand response (DR) strategies. This study explores the application of deep reinforcement learning (RL) as an innovative, data-driven approach for DR in the food industry. By leveraging the adaptive, self-learning capabilities of RL, energy costs in the investigated plant are effectively decreased. The RL algorithm was compared with the well-established optimization method Mixed Integer Linear Programming (MILP), and both were benchmarked against a reference scenario without DR. The two optimization strategies demonstrate cost savings of 17.57% and 18.65% for RL and MILP, respectively. Although RL is slightly less efficient in cost reduction, it significantly outperforms in computational speed, being approximately 20 times faster. During operation, RL only needs 2ms per optimization compared to 19s for MILP, making it a promising optimization tool for edge computing. Moreover, while MILP’s computation time increases considerably with the number of binary variables, RL efficiently learns dynamic system behavior and scales to more complex systems without significant performance degradation. These results highlight that deep RL, when applied to DR, offers substantial cost savings and computational efficiency, with broad applicability to energy management in various applications.