Recent advancements in large language models (LLMs) have sparked significant interest in the automatic generation of Register Transfer Level (RTL) designs, particularly using Verilog. Current research on this topic primarily focuses on pre-training and instruction tuning, but the effectiveness of these methods is constrained by the limited availability of training data, as public Verilog code is far less abundant than software code. In particular, these methods struggle to effectively capture Verilog parallel code structures, which fundamentally differ from the imperative, sequential control flow typical in most software programming languages. This paper introduces VeriSeek, an LLM enhanced by reinforcement learning using a limited amount of high-quality training data to achieve high Verilog code generation performance. Our reinforcement learning approach employs code structure information as feedback signals to refine the pre-trained model, enabling it to effectively learn important patterns from Verilog code with parallel structures. Experiments show that VeriSeek outperforms state-of-the-art methods across multiple benchmarks.
This paper introduces a new empirical methodology, the Cross-environment Hyperparameter Setting Benchmark, that compares RL algorithms across environments using a single hyperparameter setting, encouraging algorithmic development which is insensitive to hyperparameters. We demonstrate that this benchmark is robust to statistical noise and obtains qualitatively similar results across repeated applications, even when using few samples. This robustness makes the benchmark computationally cheap to apply, allowing statistically sound insights at low cost. We demonstrate two example instantiations of the CHS, on a set of six small control environments (SC-CHS) and on the entire DM Control suite of 28 environments (DMC-CHS). Finally, to illustrate the applicability of the CHS to modern RL algorithms on challenging environments, we conduct a novel empirical study of an open question in the continuous control literature. We show, with high confidence, that there is no meaningful difference in performance between Ornstein-Uhlenbeck noise and uncorrelated Gaussian noise for exploration with the DDPG algorithm on the DMC-CHS.
The transition to sustainable energy is a key challenge of our time, requiring modifications in the entire pipeline of energy production, storage, transmission, and consumption. At every stage, new sequential decision-making challenges emerge, ranging from the operation of wind farms to the management of electrical grids or the scheduling of electric vehicle charging stations. All such problems are well suited for reinforcement learning, the branch of machine learning that learns behavior from data. Therefore, numerous studies have explored the use of reinforcement learning for sustainable energy. This paper surveys this literature with the intention of bridging both the underlying research communities: energy and machine learning. After a brief introduction of both fields, we systematically list relevant sustainability challenges, how they can be modeled as a reinforcement learning problem, and what solution approaches currently exist in the literature. Afterwards, we zoom out and identify overarching reinforcement learning themes that appear throughout sustainability, such as multi-agent, offline, and safe reinforcement learning. Lastly, we also cover standardization of environments, which will be crucial for connecting both research fields, and highlight potential directions for future work. In summary, this survey provides an extensive overview of reinforcement learning methods for sustainable energy, which may play a vital role in the energy transition.
Episodic control, inspired by the role of episodic memory in the human brain, has been shown to improve the sample inefficiency of model-free reinforcement learning by reusing high-return past experiences. However, the memory growth of episodic control is undesirable in large-scale multi-agent problems such as vehicle traffic management. This paper proposes a novel replay memory architecture called Dual-Memory Integrated Learning, to augment to multi-agent reinforcement learning methods for congestion control via adaptive light signal scheduling. Our dual-memory architecture mimics two core capabilities of human decision-making. First, it relies on diverse types of memory--semantic and episodic, short-term and long-term--in order to remember high-return states that occur often in the network and filter out states that don't. Second, it employs equivalence classes to group together similar state-action pairs and that can be controlled using the same action (i.e., light signal sequence). Theoretical analyses establish memory growth bounds, and simulation experiments on several intersection networks showcase improved congestion performance (e.g., vehicle throughput) from our method.
We explore a reinforcement learning strategy to automate and accelerate h/p-multigrid methods in high-order solvers. Multigrid methods are very efficient but require fine-tuning of numerical parameters, such as the number of smoothing sweeps per level and the correction fraction (i.e., proportion of the corrected solution that is transferred from a coarser grid to a finer grid). The objective of this paper is to use a proximal policy optimization algorithm to automatically tune the multigrid parameters and, by doing so, improve stability and efficiency of the h/p-multigrid strategy. Our findings reveal that the proposed reinforcement learning h/p-multigrid approach significantly accelerates and improves the robustness of steady-state simulations for one dimensional advection-diffusion and nonlinear Burgers' equations, when discretized using high-order h/p methods, on uniform and nonuniform grids.
We argue for the epistemic and ethical advantages of pluralism in Reinforcement Learning from Human Feedback (RLHF) in the context of Large Language Models (LLM). Drawing on social epistemology and pluralist philosophy of science, we suggest ways in which RHLF can be made more responsive to human needs and how we can address challenges along the way. The paper concludes with an agenda for change, i.e. concrete, actionable steps to improve LLM development.
The increasing deployment of AI is shaping the future landscape of the internet, which is set to become an integrated ecosystem of AI agents. Orchestrating the interaction among AI agents necessitates decentralized, self-sustaining mechanisms that harmonize the tension between individual interests and social welfare. In this paper we tackle this challenge by synergizing reinforcement learning with principal-agent theory from economics. Taken separately, the former allows unrealistic freedom of intervention, while the latter struggles to scale in sequential settings. Combining them achieves the best of both worlds. We propose a framework where a principal guides an agent in a Markov Decision Process (MDP) using a series of contracts, which specify payments by the principal based on observable outcomes of the agent's actions. We present and analyze a meta-algorithm that iteratively optimizes the policies of the principal and agent, showing its equivalence to a contraction operator on the principal's Q-function, and its convergence to subgame-perfect equilibrium. We then scale our algorithm with deep Q-learning and analyze its convergence in the presence of approximation error, both theoretically and through experiments with randomly generated binary game-trees. Extending our framework to multiple agents, we apply our methodology to the combinatorial Coin Game. Addressing this multi-agent sequential social dilemma is a promising first step toward scaling our approach to more complex, real-world instances.
The emergence of quantum reinforcement learning (QRL) is propelled by advancements in quantum computing (QC) and machine learning (ML), particularly through quantum neural networks (QNN) built on variational quantum circuits (VQC). These advancements have proven successful in addressing sequential decision-making tasks. However, constructing effective QRL models demands significant expertise due to challenges in designing quantum circuit architectures, including data encoding and parameterized circuits, which profoundly influence model performance. In this paper, we propose addressing this challenge with differentiable quantum architecture search (DiffQAS), enabling trainable circuit parameters and structure weights using gradient-based optimization. Furthermore, we enhance training efficiency through asynchronous reinforcement learning (RL) methods facilitating parallel training. Through numerical simulations, we demonstrate that our proposed DiffQAS-QRL approach achieves performance comparable to manually-crafted circuit architectures across considered environments, showcasing stability across diverse scenarios. This methodology offers a pathway for designing QRL models without extensive quantum knowledge, ensuring robust performance and fostering broader application of QRL.
This paper introduces MoveLight, a novel traffic signal control system that enhances urban traffic management through movement-centric deep reinforcement learning. By leveraging detailed real-time data and advanced machine learning techniques, MoveLight overcomes the limitations of traditional traffic signal control methods. It employs a lane-level control approach using the FRAP algorithm to achieve dynamic and adaptive traffic signal control, optimizing traffic flow, reducing congestion, and improving overall efficiency. Our research demonstrates the scalability and effectiveness of MoveLight across single intersections, arterial roads, and network levels. Experimental results using real-world datasets from Cologne and Hangzhou show significant improvements in metrics such as queue length, delay, and throughput compared to existing methods. This study highlights the transformative potential of deep reinforcement learning in intelligent traffic signal control, setting a new standard for sustainable and efficient urban transportation systems.
Visual reinforcement learning (RL) has made significant progress in recent years, but the choice of visual feature extractor remains a crucial design decision. This paper compares the performance of RL algorithms that train a convolutional neural network (CNN) from scratch with those that utilize pre-trained visual representations (PVRs). We evaluate the Dormant Ratio Minimization (DRM) algorithm, a state-of-the-art visual RL method, against three PVRs: ResNet18, DINOv2, and Visual Cortex (VC). We use the Metaworld Push-v2 and Drawer-Open-v2 tasks for our comparison. Our results show that the choice of training from scratch compared to using PVRs for maximising performance is task-dependent, but PVRs offer advantages in terms of reduced replay buffer size and faster training times. We also identify a strong correlation between the dormant ratio and model performance, highlighting the importance of exploration in visual RL. Our study provides insights into the trade-offs between training from scratch and using PVRs, informing the design of future visual RL algorithms.
Reinforcement Learning (RL) is a continuously growing field that has the potential to revolutionize many areas of artificial intelligence. However, despite its promise, RL research is often hindered by the lack of standardization in environment and algorithm implementations. This makes it difficult for researchers to compare and build upon each other's work, slowing down progress in the field. Gymnasium is an open-source library that provides a standard API for RL environments, aiming to tackle this issue. Gymnasium's main feature is a set of abstractions that allow for wide interoperability between environments and training algorithms, making it easier for researchers to develop and test RL algorithms. In addition, Gymnasium provides a collection of easy-to-use environments, tools for easily customizing environments, and tools to ensure the reproducibility and robustness of RL research. Through this unified framework, Gymnasium significantly streamlines the process of developing and testing RL algorithms, enabling researchers to focus more on innovation and less on implementation details. By providing a standardized platform for RL research, Gymnasium helps to drive forward the field of reinforcement learning and unlock its full potential. Gymnasium is available online at https://github.com/Farama-Foundation/Gymnasium
This paper investigates multi-objective reinforcement learning (MORL), which focuses on learning Pareto optimal policies in the presence of multiple reward functions. Despite MORL's significant empirical success, there is still a lack of satisfactory understanding of various MORL optimization targets and efficient learning algorithms. Our work offers a systematic analysis of several optimization targets to assess their abilities to find all Pareto optimal policies and controllability over learned policies by the preferences for different objectives. We then identify Tchebycheff scalarization as a favorable scalarization method for MORL. Considering the non-smoothness of Tchebycheff scalarization, we reformulate its minimization problem into a new min-max-max optimization problem. Then, for the stochastic policy class, we propose efficient algorithms using this reformulation to learn Pareto optimal policies. We first propose an online UCB-based algorithm to achieve an $\varepsilon$ learning error with an $\tilde{\mathcal{O}}(\varepsilon^{-2})$ sample complexity for a single given preference. To further reduce the cost of environment exploration under different preferences, we propose a preference-free framework that first explores the environment without pre-defined preferences and then generates solutions for any number of preferences. We prove that it only requires an $\tilde{\mathcal{O}}(\varepsilon^{-2})$ exploration complexity in the exploration phase and demands no additional exploration afterward. Lastly, we analyze the smooth Tchebycheff scalarization, an extension of Tchebycheff scalarization, which is proved to be more advantageous in distinguishing the Pareto optimal policies from other weakly Pareto optimal policies based on entry values of preference vectors. Furthermore, we extend our algorithms and theoretical analysis to accommodate this optimization target.
Reinforcement learning (RL) enables social robots to generate trajectories without relying on human-designed rules or interventions, making it generally more effective than rule-based systems in adapting to complex, dynamic real-world scenarios. However, social navigation is a safety-critical task that requires robots to avoid collisions with pedestrians, whereas existing RL-based solutions often fall short of ensuring safety in complex environments. In this paper, we propose SoNIC, which to the best of our knowledge is the first algorithm that integrates adaptive conformal inference (ACI) with constrained reinforcement learning (CRL) to enable safe policy learning for social navigation. Specifically, our method not only augments RL observations with ACI-generated nonconformity scores, which inform the agent of the quantified uncertainty but also employs these uncertainty estimates to effectively guide the behaviors of RL agents by using constrained reinforcement learning. This integration regulates the behaviors of RL agents and enables them to handle safety-critical situations. On the standard CrowdNav benchmark, our method achieves a success rate of 96.93%, which is 11.67% higher than the previous state-of-the-art RL method and results in 4.5 times fewer collisions and 2.8 times fewer intrusions to ground-truth human future trajectories as well as enhanced robustness in out-of-distribution scenarios. To further validate our approach, we deploy our algorithm on a real robot by developing a ROS2-based navigation system. Our experiments demonstrate that the system can generate robust and socially polite decision-making when interacting with both sparse and dense crowds. The video demos can be found on our project website: https://sonic-social-nav.github.io/.
Cryptocurrency is a cryptography-based digital asset with extremely volatile prices. Around USD 70 billion worth of cryptocurrency is traded daily on exchanges. Trading cryptocurrency is difficult due to the inherent volatility of the crypto market. This study investigates whether Reinforcement Learning (RL) can enhance decision-making in cryptocurrency algorithmic trading compared to traditional methods. In order to address this question, we combined reinforcement learning with a statistical arbitrage trading technique, pair trading, which exploits the price difference between statistically correlated assets. We constructed RL environments and trained RL agents to determine when and how to trade pairs of cryptocurrencies. We developed new reward shaping and observation/action spaces for reinforcement learning. We performed experiments with the developed reinforcement learner on pairs of BTC-GBP and BTC-EUR data separated by 1 min intervals (n=263,520). The traditional non-RL pair trading technique achieved an annualized profit of 8.33%, while the proposed RL-based pair trading technique achieved annualized profits from 9.94% to 31.53%, depending upon the RL learner. Our results show that RL can significantly outperform manual and traditional pair trading techniques when applied to volatile markets such as~cryptocurrencies.
Many challenging tasks such as managing traffic systems, electricity grids, or supply chains involve complex decision-making processes that must balance multiple conflicting objectives and coordinate the actions of various independent decision-makers (DMs). One perspective for formalising and addressing such tasks is multi-objective multi-agent reinforcement learning (MOMARL). MOMARL broadens reinforcement learning (RL) to problems with multiple agents each needing to consider multiple objectives in their learning process. In reinforcement learning research, benchmarks are crucial in facilitating progress, evaluation, and reproducibility. The significance of benchmarks is underscored by the existence of numerous benchmark frameworks developed for various RL paradigms, including single-agent RL (e.g., Gymnasium), multi-agent RL (e.g., PettingZoo), and single-agent multi-objective RL (e.g., MO-Gymnasium). To support the advancement of the MOMARL field, we introduce MOMAland, the first collection of standardised environments for multi-objective multi-agent reinforcement learning. MOMAland addresses the need for comprehensive benchmarking in this emerging field, offering over 10 diverse environments that vary in the number of agents, state representations, reward structures, and utility considerations. To provide strong baselines for future research, MOMAland also includes algorithms capable of learning policies in such settings.
Traditionally, Reinforcement Learning (RL) problems are aimed at optimization of the behavior of an agent. This paper proposes a novel take on RL, which is used to learn the policy of another agent, to allow real-time recognition of that agent's goals. Goal Recognition (GR) has traditionally been framed as a planning problem where one must recognize an agent's objectives based on its observed actions. Recent approaches have shown how reinforcement learning can be used as part of the GR pipeline, but are limited to recognizing predefined goals and lack scalability in domains with a large goal space. This paper formulates a novel problem, "Online Dynamic Goal Recognition" (ODGR), as a first step to address these limitations. Contributions include introducing the concept of dynamic goals into the standard GR problem definition, revisiting common approaches by reformulating them using ODGR, and demonstrating the feasibility of solving ODGR in a navigation domain using transfer learning. These novel formulations open the door for future extensions of existing transfer learning-based GR methods, which will be robust to changing and expansive real-time environments.
Diffusion models have shown strong competitiveness in offline reinforcement learning tasks by formulating decision-making as sequential generation. However, the practicality of these methods is limited due to the lengthy inference processes they require. In this paper, we address this problem by decomposing the sampling process of diffusion models into two decoupled subprocesses: 1) generating a feasible trajectory, which is a time-consuming process, and 2) optimizing the trajectory. With this decomposition approach, we are able to partially separate efficiency and quality factors, enabling us to simultaneously gain efficiency advantages and ensure quality assurance. We propose the Trajectory Diffuser, which utilizes a faster autoregressive model to handle the generation of feasible trajectories while retaining the trajectory optimization process of diffusion models. This allows us to achieve more efficient planning without sacrificing capability. To evaluate the effectiveness and efficiency of the Trajectory Diffuser, we conduct experiments on the D4RL benchmarks. The results demonstrate that our method achieves $\it 3$-$\it 10 \times$ faster inference speed compared to previous sequence modeling methods, while also outperforming them in terms of overall performance. https://github.com/RenMing-Huang/TrajectoryDiffuser Keywords: Reinforcement Learning and Efficient Planning and Diffusion Model
Standard reinforcement learning algorithms with a single policy perform poorly on tasks in complex environments involving sparse rewards, diverse behaviors, or long-term planning. This led to the study of algorithms that incorporate temporal abstraction by training a hierarchy of policies that plan over different time scales. The options framework has been introduced to implement such temporal abstraction by learning low-level options that act as extended actions controlled by a high-level policy. The main challenge in applying these algorithms to real-world problems is that they suffer from high sample complexity to train multiple levels of the hierarchy, which is impossible in online settings. Motivated by this, in this paper, we propose an offline hierarchical RL method that can learn options from existing offline datasets collected by other unknown agents. This is a very challenging problem due to the distribution mismatch between the learned options and the policies responsible for the offline dataset and to our knowledge, this is the first work in this direction. In this work, we propose a framework by which an online hierarchical reinforcement learning algorithm can be trained on an offline dataset of transitions collected by an unknown behavior policy. We validate our method on Gym MuJoCo locomotion environments and robotic gripper block-stacking tasks in the standard as well as transfer and goal-conditioned settings.
Rocket recycling is a crucial pursuit in aerospace technology, aimed at reducing costs and environmental impact in space exploration. The primary focus centers on rocket landing control, involving the guidance of a nonlinear underactuated rocket with limited fuel in real-time. This challenging task prompts the application of reinforcement learning (RL), yet goal-oriented nature of the problem poses difficulties for standard RL algorithms due to the absence of intermediate reward signals. This paper, for the first time, significantly elevates the success rate of rocket landing control from 8% with a baseline controller to 97% on a high-fidelity rocket model using RL. Our approach, called Random Annealing Jump Start (RAJS), is tailored for real-world goal-oriented problems by leveraging prior feedback controllers as guide policy to facilitate environmental exploration and policy learning in RL. In each episode, the guide policy navigates the environment for the guide horizon, followed by the exploration policy taking charge to complete remaining steps. This jump-start strategy prunes exploration space, rendering the problem more tractable to RL algorithms. The guide horizon is sampled from a uniform distribution, with its upper bound annealing to zero based on performance metrics, mitigating distribution shift and mismatch issues in existing methods. Additional enhancements, including cascading jump start, refined reward and terminal condition, and action smoothness regulation, further improve policy performance and practical applicability. The proposed method is validated through extensive evaluation and Hardware-in-the-Loop testing, affirming the effectiveness, real-time feasibility, and smoothness of the proposed controller.
Offline safe reinforcement learning (RL) aims to train a policy that satisfies constraints using a pre-collected dataset. Most current methods struggle with the mismatch between imperfect demonstrations and the desired safe and rewarding performance. In this paper, we introduce OASIS (cOnditionAl diStributIon Shaping), a new paradigm in offline safe RL designed to overcome these critical limitations. OASIS utilizes a conditional diffusion model to synthesize offline datasets, thus shaping the data distribution toward a beneficial target domain. Our approach makes compliance with safety constraints through effective data utilization and regularization techniques to benefit offline safe RL training. Comprehensive evaluations on public benchmarks and varying datasets showcase OASIS's superiority in benefiting offline safe RL agents to achieve high-reward behavior while satisfying the safety constraints, outperforming established baselines. Furthermore, OASIS exhibits high data efficiency and robustness, making it suitable for real-world applications, particularly in tasks where safety is imperative and high-quality demonstrations are scarce.