Learning-based intelligent energy management systems for plug-in hybrid electric vehicles (PHEVs) are crucial for achieving efficient energy utilization. However, their application faces system reliability challenges in the real world, which prevents widespread acceptance by original equipment manufacturers (OEMs). This paper begins by establishing a PHEV model based on physical and datadriven models, focusing on the high-fidelity training environment. It then proposes a real-vehicle application-oriented control framework, combining horizon-extended reinforcement learning (RL)- based energy management with the equivalent consumption minimization strategy (ECMS) to enhance practical applicability, and improves the flawed method of equivalent factor evaluation based on instantaneous driving cycle and powertrain states found in existing research. Finally, comprehensive simulation and hardware-in-the-loop validation are carried out which demonstrates the advantages of the proposed control framework in fuel economy over adaptive-ECMS and rule-based strategies. Compared to conventional RL architectures that directly control powertrain components, the proposed control method not only achieves similar optimality but also significantly enhances the disturbance resistance of the energy management system, providing an effective control framework for RL-based energy management strategies aimed at real-vehicle applications by OEMs.

In this paper, we present the $\texttt{e-COP}$ algorithm, the first policy optimization algorithm for constrained Reinforcement Learning (RL) in episodic (finite horizon) settings. Such formulations are applicable when there are separate sets of optimization criteria and constraints on a system's behavior. We approach this problem by first establishing a policy difference lemma for the episodic setting, which provides the theoretical foundation for the algorithm. Then, we propose to combine a set of established and novel solution ideas to yield the $\texttt{e-COP}$ algorithm that is easy to implement and numerically stable, and provide a theoretical guarantee on optimality under certain scaling assumptions. Through extensive empirical analysis using benchmarks in the Safety Gym suite, we show that our algorithm has similar or better performance than SoTA (non-episodic) algorithms adapted for the episodic setting. The scalability of the algorithm opens the door to its application in safety-constrained Reinforcement Learning from Human Feedback for Large Language or Diffusion Models.

Due to the complex physical properties of granular materials, research on robot learning for manipulating such materials predominantly either disregards the consideration of their physical characteristics or uses surrogate models to approximate their physical properties. Learning to manipulate granular materials based on physical information obtained through precise modelling remains an unsolved problem. In this paper, we propose to address this challenge by constructing a differentiable physics simulator for granular materials based on the Taichi programming language and developing a learning framework accelerated by imperfect demonstrations that are generated via gradient-based optimisation on non-granular materials through our simulator. Experimental results show that our method trains three policies that, when chained, are capable of executing the task of transporting granular materials in both simulated and real-world scenarios, which existing popular deep reinforcement learning models fail to accomplish.

While imitation learning requires access to high-quality data, offline reinforcement learning (RL) should, in principle, perform similarly or better with substantially lower data quality by using a value function. However, current results indicate that offline RL often performs worse than imitation learning, and it is often unclear what holds back the performance of offline RL. Motivated by this observation, we aim to understand the bottlenecks in current offline RL algorithms. While poor performance of offline RL is typically attributed to an imperfect value function, we ask: is the main bottleneck of offline RL indeed in learning the value function, or something else? To answer this question, we perform a systematic empirical study of (1) value learning, (2) policy extraction, and (3) policy generalization in offline RL problems, analyzing how these components affect performance. We make two surprising observations. First, we find that the choice of a policy extraction algorithm significantly affects the performance and scalability of offline RL, often more so than the value learning objective. For instance, we show that common value-weighted behavioral cloning objectives (e.g., AWR) do not fully leverage the learned value function, and switching to behavior-constrained policy gradient objectives (e.g., DDPG+BC) often leads to substantial improvements in performance and scalability. Second, we find that a big barrier to improving offline RL performance is often imperfect policy generalization on test-time states out of the support of the training data, rather than policy learning on in-distribution states. We then show that the use of suboptimal but high-coverage data or test-time policy training techniques can address this generalization issue in practice. Specifically, we propose two simple test-time policy improvement methods and show that these methods lead to better performance.

Digital Twins have gained attention in various industries for simulation, monitoring, and decision-making, relying on ever-improving machine learning models. However, agricultural Digital Twin implementations are limited compared to other industries. Meanwhile, machine learning, particularly reinforcement learning, has shown potential in agricultural applications like optimizing decision-making, task automation, and resource management. A key aspect of Digital Twins is representing physical assets or systems in a virtual environment, which aligns well with reinforcement learning's need for environment representations to learn the best policy for a task. Reinforcement learning in agriculture can thus enable various Digital Twin applications in agricultural domains. This review aims to categorize existing research employing reinforcement learning in agricultural settings by application domains like robotics, greenhouse management, irrigation systems, and crop management, identifying potential future areas for reinforcement learning-based Digital Twins. It also categorizes the reinforcement learning techniques used, including tabular methods, Deep Q-Networks (DQN), Policy Gradient methods, and Actor-Critic algorithms, to overview currently employed models. The review seeks to provide insights into the state-of-the-art in integrating Digital Twins and reinforcement learning in agriculture, identifying gaps and opportunities for future research, and exploring synergies to tackle agricultural challenges and optimize farming, paving the way for more efficient and sustainable farming methodologies.

Leveraging the powerful generative capability of diffusion models (DMs) to build decision-making agents has achieved extensive success. However, there is still a demand for an easy-to-use and modularized open-source library that offers customized and efficient development for DM-based decision-making algorithms. In this work, we introduce CleanDiffuser, the first DM library specifically designed for decision-making algorithms. By revisiting the roles of DMs in the decisionmaking domain, we identify a set of essential sub-modules that constitute the core of CleanDiffuser, allowing for the implementation of various DM algorithms with simple and flexible building blocks. To demonstrate the reliability and flexibility of CleanDiffuser, we conduct comprehensive evaluations of various DM algorithms implemented with CleanDiffuser across an extensive range of tasks. The analytical experiments provide a wealth of valuable design choices and insights, reveal opportunities and challenges, and lay a solid groundwork for future research. CleanDiffuser will provide long-term support to the decision-making community, enhancing reproducibility and fostering the development of more robust solutions. The code and documentation of CleanDiffuser are open-sourced on the project website.

We investigate the application of active inference in developing energy-efficient control agents for manufacturing systems. Active inference, rooted in neuroscience, provides a unified probabilistic framework integrating perception, learning, and action, with inherent uncertainty quantification elements. Our study explores deep active inference, an emerging field that combines deep learning with the active inference decision-making framework. Leveraging a deep active inference agent, we focus on controlling parallel and identical machine workstations to enhance energy efficiency. We address challenges posed by the problem's stochastic nature and delayed policy response by introducing tailored enhancements to existing agent architectures. Specifically, we introduce multi-step transition and hybrid horizon methods to mitigate the need for complex planning. Our experimental results demonstrate the effectiveness of these enhancements and highlight the potential of the active inference-based approach.

The Lucas critique emphasizes the importance of considering the impact of policy changes on the expectations of micro-level agents in macroeconomic policymaking. However, the inherently self-interested nature of large-scale micro-agents, who pursue long-term benefits, complicates the formulation of optimal macroeconomic policies. This paper proposes a novel general framework named Dynamic Stackelberg Mean Field Games (Dynamic SMFG) to model such policymaking within sequential decision-making processes, with the government as the leader and households as dynamic followers. Dynamic SMFGs capture the dynamic interactions among large-scale households and their response to macroeconomic policy changes. To solve dynamic SMFGs, we propose the Stackelberg Mean Field Reinforcement Learning (SMFRL) algorithm, which leverages the population distribution of followers to represent high-dimensional joint state and action spaces. In experiments, our method surpasses macroeconomic policies in the real world, existing AI-based and economic methods. It allows the leader to approach the social optimum with the highest performance, while large-scale followers converge toward their best response to the leader's policy. Besides, we demonstrate that our approach retains effectiveness even when some households do not adopt the SMFG policy. In summary, this paper contributes to the field of AI for economics by offering an effective tool for modeling and solving macroeconomic policy-making issues.

The utilization of the experience replay mechanism enables agents to effectively leverage their experiences on several occasions. In previous studies, the sampling probability of the transitions was modified based on their relative significance. The process of reassigning sample probabilities for every transition in the replay buffer after each iteration is considered extremely inefficient. Hence, in order to enhance computing efficiency, experience replay prioritization algorithms reassess the importance of a transition as it is sampled. However, the relative importance of the transitions undergoes dynamic adjustments when the agent's policy and value function are iteratively updated. Furthermore, experience replay is a mechanism that retains the transitions generated by the agent's past policies, which could potentially diverge significantly from the agent's most recent policy. An increased deviation from the agent's most recent policy results in a greater frequency of off-policy updates, which has a negative impact on the agent's performance. In this paper, we develop a novel algorithm, Corrected Uniform Experience Replay (CUER), which stochastically samples the stored experience while considering the fairness among all other experiences without ignoring the dynamic nature of the transition importance by making sampled state distribution more on-policy. CUER provides promising improvements for off-policy continuous control algorithms in terms of sample efficiency, final performance, and stability of the policy during the training.

Model-based offline reinforcement Learning (RL) is a promising approach that leverages existing data effectively in many real-world applications, especially those involving high-dimensional inputs like images and videos. To alleviate the distribution shift issue in offline RL, existing model-based methods heavily rely on the uncertainty of learned dynamics. However, the model uncertainty estimation becomes significantly biased when observations contain complex distractors with non-trivial dynamics. To address this challenge, we propose a new approach - \emph{Separated Model-based Offline Policy Optimization} (SeMOPO) - decomposing latent states into endogenous and exogenous parts via conservative sampling and estimating model uncertainty on the endogenous states only. We provide a theoretical guarantee of model uncertainty and performance bound of SeMOPO. To assess the efficacy, we construct the Low-Quality Vision Deep Data-Driven Datasets for RL (LQV-D4RL), where the data are collected by non-expert policy and the observations include moving distractors. Experimental results show that our method substantially outperforms all baseline methods, and further analytical experiments validate the critical designs in our method. The project website is \href{https://sites.google.com/view/semopo}{https://sites.google.com/view/semopo}.