Knowledge distillation (KD) enhances the performance of a student network by allowing it to learn the knowledge transferred from a teacher network incrementally. Existing methods dynamically adjust the temperature to enable the student network to adapt to the varying learning difficulties at different learning stages of KD. KD is a continuous process, but when adjusting the temperature, these methods consider only the immediate benefits of the operation in the current learning phase and fail to take into account its future returns. To address this issue, we formulate the adjustment of temperature as a sequential decision-making task and propose a method based on reinforcement learning, termed RLKD. Importantly, we design a novel state representation to enable the agent to make more informed action (i.e. instance temperature adjustment). To handle the problem of delayed rewards in our method due to the KD setting, we explore an instance reward calibration approach. In addition,we devise an efficient exploration strategy that enables the agent to learn valuable instance temperature adjustment policy more efficiently. Our framework can serve as a plug-and-play technique to be inserted into various KD methods easily, and we validate its effectiveness on both image classification and object detection tasks. Our project is at https://www.zayx.me/ITKD.github.io/.

ATARI is a suite of video games used by reinforcement learning (RL) researchers to test the effectiveness of the learning algorithm. Receiving only the raw pixels and the game score, the agent learns to develop sophisticated strategies, even to the comparable level of a professional human games tester. Ideally, we also want an agent requiring very few interactions with the environment. Previous competitive model-free algorithms for the task use the valued-based Rainbow algorithm without any policy head. In this paper, we change it by proposing a practical discrete variant of the soft actor-critic (SAC) algorithm. The new variant enables off-policy learning using policy heads for discrete domains. By incorporating it into the advanced Rainbow variant, i.e., the ``bigger, better, faster'' (BBF), the resulting SAC-BBF improves the previous state-of-the-art interquartile mean (IQM) from 1.045 to 1.088, and it achieves these results using only replay ratio (RR) 2. By using lower RR 2, the training time of SAC-BBF is strictly one-third of the time required for BBF to achieve an IQM of 1.045 using RR 8. As a value of IQM greater than one indicates super-human performance, SAC-BBF is also the only model-free algorithm with a super-human level using only RR 2. The code is publicly available on GitHub at https://github.com/lezhang-thu/bigger-better-faster-SAC.

Different classes of safe reinforcement learning algorithms have shown satisfactory performance in various types of safety requirement scenarios. However, the existing methods mainly address one or several classes of specific safety requirement scenario problems and cannot be applied to arbitrary safety requirement scenarios. In addition, the optimization objectives of existing reinforcement learning algorithms are misaligned with the task requirements. Based on the need to address these issues, we propose $\mathrm{E^{2}CFD}$, an effective and efficient cost function design framework. $\mathrm{E^{2}CFD}$ leverages the capabilities of a large language model (LLM) to comprehend various safety scenarios and generate corresponding cost functions. It incorporates the \textit{fast performance evaluation (FPE)} method to facilitate rapid and iterative updates to the generated cost function. Through this iterative process, $\mathrm{E^{2}CFD}$ aims to obtain the most suitable cost function for policy training, tailored to the specific tasks within the safety scenario. Experiments have proven that the performance of policies trained using this framework is superior to traditional safe reinforcement learning algorithms and policies trained with carefully designed cost functions.

In this article, we introduce the concept of discounted pseudocosts, inspired by discounted total reward in reinforcement learning, and explore their application in mixed-integer linear programming (MILP). Traditional pseudocosts estimate changes in the objective function due to variable bound changes during the branch-and-bound process. By integrating reinforcement learning concepts, we propose a novel approach incorporating a forward-looking perspective into pseudocost estimation. We present the motivation behind discounted pseudocosts and discuss how they represent the anticipated reward for branching after one level of exploration in the MILP problem space. Initial experiments on MIPLIB 2017 benchmark instances demonstrate the potential of discounted pseudocosts to enhance branching strategies and accelerate the solution process for challenging MILP problems.

Recent interest in humanoid robots as general purpose robots has lead to a significant increase in humanoid robotics research and development in both industry and academia. A main reason for the interest is because humanoid robots have the ability to perform repetitive and dull tasks in human environments. A core skill necessary for many tasks, like moving boxes around a warehouse, is robust locomotion. Locomotion planning and control algorithms vary greatly from linear inverted pendulum walking (LIPM) [4] to online whole-body MPC walking [3]. Reinforcement learning (RL) has also been a method of choice recently for robotic motion generation given its ability to adapt to different environments or conditions and generalize well to many scenarios.

This article investigates a control system within the context of six-generation wireless networks. The control performance optimization confronts the technical challenges that arise from the intricate interactions between communication and control sub-systems, asking for a co-design. Accounting for the system dynamics, we formulate the sequential co-design decision-makings of communication and control over the discrete time horizon as a Markov decision process, for which a practical offline learning framework is proposed. Our proposed framework integrates large language models into the elements of reinforcement learning. We present a case study on the age of semantics-aware communication and control co-design to showcase the potentials from our proposed learning framework. Furthermore, we discuss the open issues remaining to make our proposed offline learning framework feasible for realworld implementations, and highlight the research directions for future explorations. Index Terms 6G, control performance optimization, communication and control co-design, Markov decision process, reinforcement learning, large language models. Wireless networked control systems (NCSs) have been focal in contemporary engineering and industrial applications, owing to the flexibility, scalability and cost-savings [1].

Knowledge from animals and humans inspires robotic innovations. Numerous efforts have been made to achieve agile locomotion in quadrupedal robots through classical controllers or reinforcement learning approaches. These methods usually rely on physical models or handcrafted rewards to accurately describe the specific system, rather than on a generalized understanding like animals do. Here we propose a hierarchical framework to construct primitive-, environmental- and strategic-level knowledge that are all pre-trainable, reusable and enrichable for legged robots. The primitive module summarizes knowledge from animal motion data, where, inspired by large pre-trained models in language and image understanding, we introduce deep generative models to produce motor control signals stimulating legged robots to act like real animals. Then, we shape various traversing capabilities at a higher level to align with the environment by reusing the primitive module. Finally, a strategic module is trained focusing on complex downstream tasks by reusing the knowledge from previous levels. We apply the trained hierarchical controllers to the MAX robot, a quadrupedal robot developed in-house, to mimic animals, traverse complex obstacles and play in a designed challenging multi-agent chase tag game, where lifelike agility and strategy emerge in the robots.

Offline reinforcement learning has become one of the most practical RL settings. A recent success story has been RLHF, offline preference-based RL (PBRL) with preference from humans. However, most existing works on offline RL focus on the standard setting with scalar reward feedback. It remains unknown how to universally transfer the existing rich understanding of offline RL from the reward-based to the preference-based setting. In this work, we propose a general framework to bridge this gap. Our key insight is transforming preference feedback to scalar rewards via optimal reward labeling (ORL), and then any reward-based offline RL algorithms can be applied to the dataset with the reward labels. We theoretically show the connection between several recent PBRL techniques and our framework combined with specific offline RL algorithms in terms of how they utilize the preference signals. By combining reward labeling with different algorithms, our framework can lead to new and potentially more efficient offline PBRL algorithms. We empirically test our framework on preference datasets based on the standard D4RL benchmark. When combined with a variety of efficient reward-based offline RL algorithms, the learning result achieved under our framework is comparable to training the same algorithm on the dataset with actual rewards in many cases and better than the recent PBRL baselines in most cases.

Components of cyber physical systems, which affect real-world processes, are often exposed to the internet. Replacing conventional control methods with Deep Reinforcement Learning (DRL) in energy systems is an active area of research, as these systems become increasingly complex with the advent of renewable energy sources and the desire to improve their efficiency. Artificial Neural Networks (ANN) are vulnerable to specific perturbations of their inputs or features, called adversarial examples. These perturbations are difficult to detect when properly regularized, but have significant effects on the ANN's output. Because DRL uses ANN to map optimal actions to observations, they are similarly vulnerable to adversarial examples. This work proposes a novel attack technique for continuous control using Group Difference Logits loss with a bifurcation layer. By combining aspects of targeted and untargeted attacks, the attack significantly increases the impact compared to an untargeted attack, with drastically smaller distortions than an optimally targeted attack. We demonstrate the impacts of powerful gradient-based attacks in a realistic smart energy environment, show how the impacts change with different DRL agents and training procedures, and use statistical and time-series analysis to evaluate attacks' stealth. The results show that adversarial attacks can have significant impacts on DRL controllers, and constraining an attack's perturbations makes it difficult to detect. However, certain DRL architectures are far more robust, and robust training methods can further reduce the impact.

This study proposes the use of a social learning method to estimate a global state within a multi-agent off-policy actor-critic algorithm for reinforcement learning (RL) operating in a partially observable environment. We assume that the network of agents operates in a fully-decentralized manner, possessing the capability to exchange variables with their immediate neighbors. The proposed design methodology is supported by an analysis demonstrating that the difference between final outcomes, obtained when the global state is fully observed versus estimated through the social learning method, is $\varepsilon$-bounded when an appropriate number of iterations of social learning updates are implemented. Unlike many existing dec-POMDP-based RL approaches, the proposed algorithm is suitable for model-free multi-agent reinforcement learning as it does not require knowledge of a transition model. Furthermore, experimental results illustrate the efficacy of the algorithm and demonstrate its superiority over the current state-of-the-art methods.