Off-policy inverse Q-learning for discrete-time antagonistic unknown systems

Energy-efficient and damage-recovery slithering gait design for a snake-like robot based on reinforcement learning and inverse reinforcement learning

This work develops a novel high-dimensional inverse reinforcement learning (IRL) algorithm for human motion analysis in medical, clinical, and robotics applications. The method is based on the assumption that a surgical robot operators’ skill or a patient’s motor skill is encoded into the innate reward function during motion planning and recovered by an IRL algorithm from motion demonstrations. This class of applications is characterized by high-dimensional sensory data, which is computationally prohibitive for most existing IRL algorithms. We propose a novel function approximation framework and reformulate the Bellman optimality equation to handle high-dimensional state spaces efficiently. We compare different function approximators in simulated environments, and adopt a deep neural network as the function approximator. The technique is applied to evaluating human patients with spinal cord injuries under spinal stimulation, and the skill levels of surgical robot operators. The results demonstrate the efficiency and effectiveness of the proposed method.

In our previous work, we proposed a systematic cross-layer framework for dynamic multimedia systems, which allows each layer to make autonomous and foresighted decisions that maximize the system's long-term performance, while meeting the application's real-time delay constraints. The proposed solution solved the cross-layer optimization offline, under the assumption that the multimedia system's probabilistic dynamics were known a priori, by modeling the system as a layered Markov decision process. In practice, however, these dynamics are unknown a priori and, therefore, must be learned online. In this paper, we address this problem by allowing the multimedia system layers to learn, through repeated interactions with each other, to autonomously optimize the system's long-term performance at run-time. The two key challenges in this layered learning setting are: (i) each layer's learning performance is directly impacted by not only its own dynamics, but also by the learning processes of the other layers with which it interacts; and (ii) selecting a learning model that appropriately balances time-complexity (i.e., learning speed) with the multimedia system's limited memory and the multimedia application's real-time delay constraints. We propose two reinforcement learning algorithms for optimizing the system under different design constraints: the first algorithm solves the cross-layer optimization in a centralized manner and the second solves it in a decentralized manner. We analyze both algorithms in terms of their required computation, memory, and interlayer communication overheads. After noting that the proposed reinforcement learning algorithms learn too slowly, we introduce a complementary accelerated learning algorithm that exploits partial knowledge about the system's dynamics in order to dramatically improve the system's performance. In our experiments, we demonstrate that decentralized learning can perform equally as well as centralized learning, while enabling the layers to act autonomously. Additionally, we show that existing application-independent reinforcement learning algorithms, and existing myopic learning algorithms deployed in multimedia systems, perform significantly worse than our proposed application-aware and foresighted learning methods.

Reinforcement Learning (RL) algorithms depend on well-defined reward functions for policy optimization. Designing such functions is a complex task, even for domain experts. However, valid task demonstrations can still be collected from moderately skilled individuals. This motivates the use of methods such as Imitation Learning (IL) and Inverse Reinforcement Learning (IRL), where an expert provides demonstrations, allowing the algorithm to infer a policy or reward function that aligns with observed behavior. A common assumption in IRL is that demonstrations come from highly skilled experts. While some studies have explored the impact of suboptimal demonstrators, the influence of intentionally malicious demonstrations remains underexplored. This study introduces an adversarial demonstrator framework that systematically perturbs a subset of demonstrations to manipulate the reward function inferred by an IRL algorithm. Additionally, it quantifies the impact of such adversarial manipulations on the learned policy. Our results show that simply altering 10% of the demonstrations can lead the IRL algorithm to learn a faulty reward function, ultimately degrading the performance of the trained policy by up to three times the effect of adding 10% random trajectories to the result.

With the implementation of reinforcement learning (RL) algorithms, current state-of-art autonomous vehicle technology have the potential to get closer to full automation. However, most of the applications have been limited to game domains or discrete action space which are far from the real world driving. Moreover, it is very tough to tune the parameters of reward mechanism since the driving styles vary a lot among the different users. For instance, an aggressive driver may prefer driving with high acceleration whereas some conservative drivers prefer a safer driving style. Therefore, we propose an apprenticeship learning in combination with deep reinforcement learning approach that allows the agent to learn the driving and stopping behaviors with continuous actions. We use gradient inverse reinforcement learning (GIRL) algorithm to recover the unknown reward function and employ REINFORCE as well as Deep Deterministic Policy Gradient algorithm (DDPG) to learn the optimal policy. The performance of our method is evaluated in simulation-based scenario and the results demonstrate that the agent performs human like driving and even better in some aspects after training.

In this paper, we study the inverse reinforcement learning (IRL) algorithm for semi-Markov decision processes (SMDPs) with average reward based on the performance sensitivity analysis. By analyzing the structural form of the performance difference formula between any two different policies, we utilize the expert policy to transform the IRL problems of SMDPs into convex optimization problems. Based on two different performance difference formulas, two IRL algorithms are proposed and the algorithms are verified on a grid maze with options. The feasibility and effectiveness of algorithms are illustrated in the simulation results.

Reinforcement learning (RL) algorithms have been successfully applied to control tasks associated with unmanned aerial vehicles and robotics. In recent years, safe RL has been proposed to allow the safe execution of RL algorithms in industrial and mission-critical systems that operate in closed loops. However, if the system operating conditions change, such as when an unknown fault occurs, typical safe RL algorithms cannot adapt while retaining past knowledge. Continual RL algorithms have been proposed to address this issue. However, the impact of continual adaptation on the system’s safety is an understudied problem. In this paper, we study the intersection of safe and continual RL. First, we empirically demonstrate that a popular continual RL algorithm, elastic weight consolidation, does not satisfy safety constraints in nonlinear systems subject to varying operating conditions. Specifically, we study the MuJoCo HalfCheetah and Ant environments with velocity constraints and sudden joint loss non-stationarity. Then, we show that an agent trained using constrained policy optimization, a safe RL algorithm, experiences catastrophic forgetting in continual learning settings. With this in mind, we explore a simple reward-shaping method to ensure that elastic weight consolidation prioritizes remembering both safety and task performance for safety-constrained, nonlinear, and non-stationary systems.

P2P power trading based on reinforcement learning for nanogrid clusters

This paper proposes a reinforcement learning (RL) algorithm for the security problem of state estimation of cyber-physical system (CPS) under denial-of-service (DoS) attacks. The security of CPS will inevitably decline when faced with malicious cyber attacks. In order to analyze the impact of cyber attacks on CPS performance, a Kalman filter, as an adaptive state estimation technology, is combined with an RL method to evaluate the issue of system security, where estimation performance is adopted as an evaluation criterion. Then, the transition of estimation error covariance under a DoS attack is described as a Markov decision process, and the RL algorithm could be applied to resolve the optimal countermeasures. Meanwhile, the interactive combat between defender and attacker could be regarded as a two-player zero-sum game, where the Nash equilibrium policy exists but needs to be solved. Considering the energy constraints, the action selection of both sides will be restricted by setting certain cost functions. The proposed RL approach is designed from three different perspectives, including the defender, the attacker and the interactive game of two opposite sides. In addition, the framework of Q-learning and state–action–reward–state–action (SARSA) methods are investigated separately in this paper to analyze the influence of different RL algorithms. The results show that both algorithms obtain the corresponding optimal policy and the Nash equilibrium policy of the zero-sum interactive game. Through comparative analysis of two algorithms, it is verified that the differences between Q-Learning and SARSA could be applied effectively into the secure state estimation in CPS.

Deep reinforcement learning is the technology of artificial neural networks in the field of decision-making and control. The traditional model-free reinforcement learning algorithm requires a large amount of environment interactive data to iterate the algorithm. This model’s performance also suffers due to low utilization of training data, while the model-based reinforcement learning (MBRL) algorithm improves the efficiency of the data, MBRL locks into low prediction accuracy. Although MBRL can utilize the additional data generated by the dynamic model, a system dynamics model with low prediction accuracy will provide low-quality data and affect the algorithm’s final result. In this paper, based on the A3C (Asynchronous Advantage Actor-Critic) algorithm, an improved model-based deep reinforcement learning algorithm using a learning degree network (MBRL-LDN) is presented. By comparing the differences between the predicted states outputted by the proposed multidynamic model and the original predicted states, the learning degree of the system dynamics model is calculated. The learning degree represents the quality of the data generated by the dynamic model and is used to decide whether to continue to interact with the dynamic model during a particular episode. Thus, low-quality data will be discarded. The superiority of the proposed method is verified by conducting extensive contrast experiments.

Recent advancement on reinforcement learning (RL) algorithms shows that effective learning of parametric action- selection policies can often be achieved through direct opti- mization of a performance lower bound subject to pre-defined policy behavioral constraints. Driven by this understanding, this paper seeks to develop new policy search techniques where RL is achieved through maximizing a performance lower bound ob- tained originally based on an Expectation-Maximization method. For reliable RL, our new learning techniques must also simul- taneously guarantee constrained policy behavioral changes mea- sured through KL divergence. Two separate approaches will be pursued to tackle our constrained policy optimization problems, resulting in two new RL algorithms. The first algorithm utilizes a conjugate gradient technique and a Bayesian learning method for approximate optimization. The second algorithm focuses on minimizing a loss function derived from solving the Lagrangian for constrained policy search. Both algorithms have been experi- mentally examined on several benchmark problems provided by OpenAI GYM. The experiment results clearly demonstrate that our algorithms can be highly effective in comparison to several well-known RL algorithms.

This paper investigates the error accumulation problem in centralized training and decentralized execution (CTDE) policy‐based multi‐agent reinforcement learning (MARL) algorithms, which arises from local observation inaccuracies. To address this issue, we propose a novel MARL algorithm that incorporates imitation learning using local observations. Firstly, by analysing the multi‐agent proximal policy optimization algorithm and examining the problems arising when global states are replaced with local observations, it is proved that insufficient observations can lead to information loss, thereby introducing errors of advantage function, and it is demonstrated that the generalized advantage estimation method accumulates errors during the training process. Then, imitation learning is introduced and a novel training framework that combines reinforcement learning and imitation learning is proposed. During the reinforcement learning phase, an MARL agent trained with global observations acts as an expert. Subsequently, imitation learning is applied to train another agent that mimics the expert's decisions using only local observations. Finally, the effectiveness of this algorithm is verified in some commonly used multi‐agent environments, which demonstrates its superior performance compared to traditional multi‐agent reinforcement learning algorithms.

Rewards are critical hyperparameters in reinforcement learning (RL), since in most cases different reward values will lead to greatly different performance. Due to their commercial value, RL rewards become the target of reverse engineering by the inverse reinforcement learning (IRL) algorithm family. Existing efforts typically utilize two metrics to measure the IRL performance: the expected value difference and the mean reward loss, which we call them EVD and MRL respectively. Unfortunately, in some cases, EVD and MRL can give completely opposite results, due to MRL focusing on whole state-space rewards while EVD only considering partly sampled rewards. Such situation naturally rises to one fundamental question: whether current metrics and assessment are sufficient and accurate for more general use. Thus, in this paper, based on the metric called normalized mutual information of reward clusters (C-NMI) we propose a novel IRL assessment; we aim to fill this research gap by considering a middle-granularity state space between the entire state space and the specific sampling space. We utilize the agglomerative nesting algorithm (AGNES) to control dynamical C-NMI computing via a 4-order tensor model with injected manipulated trajectories. With such a model, we can uniformly capture different-dimension values of MRL, EVD, and C-NMI, and perform more comprehensive and accurate assessment and analyses. Extensive experiments on several mainstream IRLs are experimented in Object World, hence revealing that the assessing accuracy of our method increases 110.13% and 116.59% respectively when compared with the EVD and MRL. Meanwhile, C-NMI is more robust than EVD and MRL under different demonstrations.

This study introduces a novel controller based on a Reinforcement Learning (RL) algorithm for real-time adaptation of the stimulation pattern during FES-cycling. Core to our approach is the introduction of an RL agent that interacts with the cycling environment and learns through trial and error how to modulate the electrical charge applied to the stimulated muscle groups according to a predefined policy and while tracking a reference cadence. Instead of a static stimulation pattern to be modified by a control law, we hypothesized that a non-stationary baseline set of parameters would better adjust the amount of injected electrical charge to the time-varying characteristics of the musculature. Overground FES-assisted cycling sessions were performed by a subject with spinal cord injury (SCI AIS-A, T8). For tracking a predefined pedaling cadence, two closed-loop control laws were simultaneously used to modulate the pulse intensity of the stimulation channels responsible for evoking the muscle contractions. First, a Proportional-Integral (PI) controller was used to control the current amplitude of the stimulation channels over an initial parameter setting with predefined pulse amplitude, width and fixed frequency parameters. In parallel, an RL algorithm with a decayed-epsilon-greedy strategy was implemented to randomly explore nine different variations of pulse amplitude and width parameters over the same stimulation setting, aiming to adjust the injected electrical charge according to a predefined policy. The performance of this global control strategy was evaluated in two different RL settings and explored in two different cycling scenarios. The participant was able to pedal overground for distances over 3.5 km, and the results evidenced the RL agent learned to modify the stimulation pattern according to the predefined policy and was simultaneously able to track a predefined pedaling cadence. Despite the simplicity of our approach and the existence of more sophisticated RL algorithms, our method can be used to reduce the time needed to define stimulation patterns. Our results suggest interesting research possibilities to be explored in the future to improve cycling performance since more efficient stimulation cost dynamics can be explored and implemented for the agent to learn.

Recent research discovered that Reinforcement Learning (RL) algorithms with simple linear policies can achieve competitive performance as many state-of-the-art RL algorithms designed to train policies in the form of multi-layer neural networks. However, high learning performance is only achieved so far when policies are trained by jointly using multiple episodes of samples. An important research question remains as to whether linear policies can achieve cutting-edge performance when they are trained in a step-wise fashion (i.e., policies are iteratively updated based on every newly obtained sample). This paper presents a confirmatory answer to this question by developing a new RL algorithm called Primal-Dual Regular-gradient Actor-Critic (PD-RAC) as a generalization of RAC, which is a popular step-wise RL technique. Experiments on six benchmark control problems show that PD-RAC can achieve leading performance, in comparison to several recently developed baseline algorithms.