We tackle the problem of policy learning from expert demonstrations without a reward function. A central challenge in this space is that these policies fail upon deployment due to issues of distributional shift, environment stochasticity, or compounding errors. Adversarial imitation learning alleviates this issue but requires additional on-policy training samples for stability, which presents a challenge in realistic domains due to inefficient learning and high sample complexity. One approach to this issue is to learn a world model of the environment, and use synthetic data for policy training. While successful in prior works, we argue that this is sub-optimal due to additional distribution shifts between the learned model and the real environment. Instead, we re-frame imitation learning as a fine-tuning problem, rather than a pure reinforcement learning one. Drawing theoretical connections to offline RL and fine-tuning algorithms, we argue that standard online world model algorithms are not well suited to the imitation learning problem. We derive a principled conservative optimization bound and demonstrate empirically that it leads to improved performance on two very challenging manipulation environments from high-dimensional raw pixel observations. We set a new state-of-the-art performance on the Franka Kitchen environment from images, requiring only 10 demos on no reward labels, as well as solving a complex dexterity manipulation task.

A flexible active safety motion (FASM) control approach is proposed for the avoidance of dynamic obstacles and the reference tracking in robot manipulators. The distinctive feature of the proposed method lies in its utilization of control barrier functions (CBF) to design flexible CBF-guided safety criteria (CBFSC) with dynamically optimized decay rates, thereby offering flexibility and active safety for robot manipulators in dynamic environments. First, discrete-time CBFs are employed to formulate the novel flexible CBFSC with dynamic decay rates for robot manipulators. Following that, the model predictive control (MPC) philosophy is applied, integrating flexible CBFSC as safety constraints into the receding-horizon optimization problem. Significantly, the decay rates of the designed CBFSC are incorporated as decision variables in the optimization problem, facilitating the dynamic enhancement of flexibility during the obstacle avoidance process. In particular, a novel cost function that integrates a penalty term is designed to dynamically adjust the safety margins of the CBFSC. Finally, experiments are conducted in various scenarios using a Universal Robots 5 (UR5) manipulator to validate the effectiveness of the proposed approach.

Learning-based methods have become increasingly popular for solving vehicle routing problems due to their near-optimal performance and fast inference speed. Among them, the combination of deep reinforcement learning and graph representation allows for the abstraction of node topology structures and features in an encoder-decoder style. Such an approach makes it possible to solve routing problems end-to-end without needing complicated heuristic operators designed by domain experts. Existing research studies have been focusing on novel encoding and decoding structures via various neural network models to enhance the node embedding representation. Despite the sophisticated approaches applied, there is a noticeable lack of consideration for the graph-theoretic properties inherent to routing problems. Moreover, the potential ramifications of inter-nodal interactions on the decision-making efficacy of the models have not been adequately explored. To bridge this gap, we propose an adaptive Graph Attention Sampling with the Edges Fusion framework (GASE),where nodes' embedding is determined through attention calculation from certain highly correlated neighbourhoods and edges, utilizing a filtered adjacency matrix. In detail, the selections of particular neighbours and adjacency edges are led by a multi-head attention mechanism, contributing directly to the message passing and node embedding in graph attention sampling networks. Furthermore, we incorporate an adaptive actor-critic algorithm with policy improvements to expedite the training convergence. We then conduct comprehensive experiments against baseline methods on learning-based VRP tasks from different perspectives. Our proposed model outperforms the existing methods by 2.08\%-6.23\% and shows stronger generalization ability, achieving state-of-the-art performance on randomly generated instances and real-world datasets.

We introduce the ``soft Deep MaxPain'' (softDMP) algorithm, which integrates the optimization of long-term policy entropy into reward-punishment reinforcement learning objectives. Our motivation is to facilitate a smoother variation of operators utilized in the updating of action values beyond traditional ``max'' and ``min'' operators, where the goal is enhancing sample efficiency and robustness. We also address two unresolved issues from the previous Deep MaxPain method. Firstly, we investigate how the negated (``flipped'') pain-seeking sub-policy, derived from the punishment action value, collaborates with the ``min'' operator to effectively learn the punishment module and how softDMP's smooth learning operator provides insights into the ``flipping'' trick. Secondly, we tackle the challenge of data collection for learning the punishment module to mitigate inconsistencies arising from the involvement of the ``flipped'' sub-policy (pain-avoidance sub-policy) in the unified behavior policy. We empirically explore the first issue in two discrete Markov Decision Process (MDP) environments, elucidating the crucial advancements of the DMP approach and the necessity for soft treatments on the hard operators. For the second issue, we propose a probabilistic classifier based on the ratio of the pain-seeking sub-policy to the sum of the pain-seeking and goal-reaching sub-policies. This classifier assigns roll-outs to separate replay buffers for updating reward and punishment action-value functions, respectively. Our framework demonstrates superior performance in Turtlebot 3's maze navigation tasks under the ROS Gazebo simulation.

Multi-agent reinforcement learning (MARL) algorithms have accomplished remarkable breakthroughs in solving large-scale decision-making tasks. Nonetheless, most existing MARL algorithms are model-free, limiting sample efficiency and hindering their applicability in more challenging scenarios. In contrast, model-based reinforcement learning (MBRL), particularly algorithms integrating planning, such as MuZero, has demonstrated superhuman performance with limited data in many tasks. Hence, we aim to boost the sample efficiency of MARL by adopting model-based approaches. However, incorporating planning and search methods into multi-agent systems poses significant challenges. The expansive action space of multi-agent systems often necessitates leveraging the nearly-independent property of agents to accelerate learning. To tackle this issue, we propose the MAZero algorithm, which combines a centralized model with Monte Carlo Tree Search (MCTS) for policy search. We design a novel network structure to facilitate distributed execution and parameter sharing. To enhance search efficiency in deterministic environments with sizable action spaces, we introduce two novel techniques: Optimistic Search Lambda (OS($\lambda$)) and Advantage-Weighted Policy Optimization (AWPO). Extensive experiments on the SMAC benchmark demonstrate that MAZero outperforms model-free approaches in terms of sample efficiency and provides comparable or better performance than existing model-based methods in terms of both sample and computational efficiency. Our code is available at https://github.com/liuqh16/MAZero.

Offline meta reinforcement learning (OMRL) has emerged as a promising approach for interaction avoidance and strong generalization performance by leveraging pre-collected data and meta-learning techniques. Previous context-based approaches predominantly rely on the intuition that maximizing the mutual information between the task and the task representation ($I(Z;M)$) can lead to performance improvements. Despite achieving attractive results, the theoretical justification of performance improvement for such intuition has been lacking. Motivated by the return discrepancy scheme in the model-based RL field, we find that maximizing $I(Z;M)$ can be interpreted as consistently raising the lower bound of the expected return for a given policy conditioning on the optimal task representation. However, this optimization process ignores the task representation shift between two consecutive updates, which may lead to performance improvement collapse. To address this problem, we turn to use the framework of performance difference bound to consider the impacts of task representation shift explicitly. We demonstrate that by reining the task representation shift, it is possible to achieve monotonic performance improvements, thereby showcasing the advantage against previous approaches. To make it practical, we design an easy yet highly effective algorithm RETRO (\underline{RE}ining \underline{T}ask \underline{R}epresentation shift in context-based \underline{O}ffline meta reinforcement learning) with only adding one line of code compared to the backbone. Empirical results validate its state-of-the-art (SOTA) asymptotic performance, training stability and training-time consumption on MuJoCo and MetaWorld benchmarks.

Quantum Computing aims to streamline machine learning, making it more effective with fewer trainable parameters. This reduction of parameters can speed up the learning process and reduce the use of computational resources. However, in the current phase of quantum computing development, known as the noisy intermediate-scale quantum era (NISQ), learning is difficult due to a limited number of qubits and widespread quantum noise. To overcome these challenges, researchers are focusing on variational quantum circuits (VQCs). VQCs are hybrid algorithms that merge a quantum circuit, which can be adjusted through parameters, with traditional classical optimization techniques. These circuits require only few qubits for effective learning. Recent studies have presented new ways of applying VQCs to reinforcement learning, showing promising results that warrant further exploration. This study investigates the effects of various techniques -- data re-uploading, input scaling, output scaling -- and introduces exponential learning rate decay in the quantum proximal policy optimization algorithm's actor-VQC. We assess these methods in the popular Frozen Lake and Cart Pole environments. Our focus is on their ability to reduce the number of parameters in the VQC without losing effectiveness. Our findings indicate that data re-uploading and an exponential learning rate decay significantly enhance hyperparameter stability and overall performance. While input scaling does not improve parameter efficiency, output scaling effectively manages greediness, leading to increased learning speed and robustness.

Multi-edge cooperative computing that combines constrained resources of multiple edges into a powerful resource pool has the potential to deliver great benefits, such as a tremendous computing power, improved response time, more diversified services. However, the mass heterogeneous resources composition and lack of scheduling strategies make the modeling and cooperating of multi-edge computing system particularly complicated. This paper first proposes a system-level state evaluation model to shield the complex hardware configurations and redefine the different service capabilities at heterogeneous edges. Secondly, an integer linear programming model is designed to cater for optimally dispatching the distributed arriving requests. Finally, a learning-based lightweight real-time scheduler, CoRaiS, is proposed. CoRaiS embeds the real-time states of multi-edge system and requests information, and combines the embeddings with a policy network to schedule the requests, so that the response time of all requests can be minimized. Evaluation results verify that CoRaiS can make a high-quality scheduling decision in real time, and can be generalized to other multi-edge computing system, regardless of system scales. Characteristic validation also demonstrates that CoRaiS successfully learns to balance loads, perceive real-time state and recognize heterogeneity while scheduling.

Deep reinforcement learning (DRL) algorithms can suffer from modeling errors between the simulation and the real world. Many studies use adversarial learning to generate perturbation during training process to model the discrepancy and improve the robustness of DRL. However, most of these approaches use a fixed parameter to control the intensity of the adversarial perturbation, which can lead to a trade-off between average performance and robustness. In fact, finding the optimal parameter of the perturbation is challenging, as excessive perturbations may destabilize training and compromise agent performance, while insufficient perturbations may not impart enough information to enhance robustness. To keep the training stable while improving robustness, we propose a simple but effective method, namely, Adaptive Adversarial Perturbation (A2P), which can dynamically select appropriate adversarial perturbations for each sample. Specifically, we propose an adaptive adversarial coefficient framework to adjust the effect of the adversarial perturbation during training. By designing a metric for the current intensity of the perturbation, our method can calculate the suitable perturbation levels based on the current relative performance. The appealing feature of our method is that it is simple to deploy in real-world applications and does not require accessing the simulator in advance. The experiments in MuJoCo show that our method can improve the training stability and learn a robust policy when migrated to different test environments. The code is available at https://github.com/Lqm00/A2P-SAC.

Text classifiers are vulnerable to adversarial examples -- correctly-classified examples that are deliberately transformed to be misclassified while satisfying acceptability constraints. The conventional approach to finding adversarial examples is to define and solve a combinatorial optimisation problem over a space of allowable transformations. While effective, this approach is slow and limited by the choice of transformations. An alternate approach is to directly generate adversarial examples by fine-tuning a pre-trained language model, as is commonly done for other text-to-text tasks. This approach promises to be much quicker and more expressive, but is relatively unexplored. For this reason, in this work we train an encoder-decoder paraphrase model to generate a diverse range of adversarial examples. For training, we adopt a reinforcement learning algorithm and propose a constraint-enforcing reward that promotes the generation of valid adversarial examples. Experimental results over two text classification datasets show that our model has achieved a higher success rate than the original paraphrase model, and overall has proved more effective than other competitive attacks. Finally, we show how key design choices impact the generated examples and discuss the strengths and weaknesses of the proposed approach.