Algorithmic trading or Financial robots have been conquering the stock markets with their ability to fathom complex statistical trading strategies. But with the recent development of deep learning technologies, these strategies are becoming impotent. The DQN and A2C models have previously outperformed eminent humans in game-playing and robotics. In our work, we propose a reinforced portfolio manager offering assistance in the allocation of weights to assets. The environment proffers the manager the freedom to go long and even short on the assets. The weight allocation advisements are restricted to the choice of portfolio assets and tested empirically to knock benchmark indices. The manager performs financial transactions in a postulated liquid market without any transaction charges. This work provides the conclusion that the proposed portfolio manager with actions centered on weight allocations can surpass the risk-adjusted returns of conventional portfolio managers.
Robust Reinforcement Learning (RRL) is a promising Reinforcement Learning (RL) paradigm aimed at training robust to uncertainty or disturbances models, making them more efficient for real-world applications. Following this paradigm, uncertainty or disturbances are interpreted as actions of a second adversarial agent, and thus, the problem is reduced to seeking the agents' policies robust to any opponent's actions. This paper is the first to propose considering the RRL problems within the positional differential game theory, which helps us to obtain theoretically justified intuition to develop a centralized Q-learning approach. Namely, we prove that under Isaacs's condition (sufficiently general for real-world dynamical systems), the same Q-function can be utilized as an approximate solution of both minimax and maximin Bellman equations. Based on these results, we present the Isaacs Deep Q-Network algorithms and demonstrate their superiority compared to other baseline RRL and Multi-Agent RL algorithms in various environments.
Designing protein nanomaterials of predefined shape and characteristics has the potential to dramatically impact the medical industry. Machine learning (ML) has proven successful in protein design, reducing the need for expensive wet lab experiment rounds. However, challenges persist in efficiently exploring the protein fitness landscapes to identify optimal protein designs. In response, we propose the use of AlphaZero to generate protein backbones, meeting shape and structural scoring requirements. We extend an existing Monte Carlo tree search (MCTS) framework by incorporating a novel threshold-based reward and secondary objectives to improve design precision. This innovation considerably outperforms existing approaches, leading to protein backbones that better respect structural scores. The application of AlphaZero is novel in the context of protein backbone design and demonstrates promising performance. AlphaZero consistently surpasses baseline MCTS by more than 100% in top-down protein design tasks. Additionally, our application of AlphaZero with secondary objectives uncovers further promising outcomes, indicating the potential of model-based reinforcement learning (RL) in navigating the intricate and nuanced aspects of protein design
Multi-agent systems (MAS) need to adaptively cope with dynamic environments, changing agent populations, and diverse tasks. However, most of the multi-agent systems cannot easily handle them, due to the complexity of the state and task space. The social impact theory regards the complex influencing factors as forces acting on an agent, emanating from the environment, other agents, and the agent's intrinsic motivation, referring to the social force. Inspired by this concept, we propose a novel gradient-based state representation for multi-agent reinforcement learning. To non-trivially model the social forces, we further introduce a data-driven method, where we employ denoising score matching to learn the social gradient fields (SocialGFs) from offline samples, e.g., the attractive or repulsive outcomes of each force. During interactions, the agents take actions based on the multi-dimensional gradients to maximize their own rewards. In practice, we integrate SocialGFs into the widely used multi-agent reinforcement learning algorithms, e.g., MAPPO. The empirical results reveal that SocialGFs offer four advantages for multi-agent systems: 1) they can be learned without requiring online interaction, 2) they demonstrate transferability across diverse tasks, 3) they facilitate credit assignment in challenging reward settings, and 4) they are scalable with the increasing number of agents.
In recent years, semi-supervised learning (SSL) has gained significant attention due to its ability to leverage both labeled and unlabeled data to improve model performance, especially when labeled data is scarce. However, most current SSL methods rely on heuristics or predefined rules for generating pseudo-labels and leveraging unlabeled data. They are limited to exploiting loss functions and regularization methods within the standard norm. In this paper, we propose a novel Reinforcement Learning (RL) Guided SSL method, RLGSSL, that formulates SSL as a one-armed bandit problem and deploys an innovative RL loss based on weighted reward to adaptively guide the learning process of the prediction model. RLGSSL incorporates a carefully designed reward function that balances the use of labeled and unlabeled data to enhance generalization performance. A semi-supervised teacher-student framework is further deployed to increase the learning stability. We demonstrate the effectiveness of RLGSSL through extensive experiments on several benchmark datasets and show that our approach achieves consistent superior performance compared to state-of-the-art SSL methods.
Existing studies on constrained reinforcement learning (RL) may obtain a well-performing policy in the training environment. However, when deployed in a real environment, it may easily violate constraints that were originally satisfied during training because there might be model mismatch between the training and real environments. To address the above challenge, we formulate the problem as constrained RL under model uncertainty, where the goal is to learn a good policy that optimizes the reward and at the same time satisfy the constraint under model mismatch. We develop a Robust Constrained Policy Optimization (RCPO) algorithm, which is the first algorithm that applies to large/continuous state space and has theoretical guarantees on worst-case reward improvement and constraint violation at each iteration during the training. We demonstrate the effectiveness of our algorithm on a set of RL tasks with constraints.
The existing Motion Imitation models typically require expert data obtained through MoCap devices, but the vast amount of training data needed is difficult to acquire, necessitating substantial investments of financial resources, manpower, and time. This project combines 3D human pose estimation with reinforcement learning, proposing a novel model that simplifies Motion Imitation into a prediction problem of joint angle values in reinforcement learning. This significantly reduces the reliance on vast amounts of training data, enabling the agent to learn an imitation policy from just a few seconds of video and exhibit strong generalization capabilities. It can quickly apply the learned policy to imitate human arm motions in unfamiliar videos. The model first extracts skeletal motions of human arms from a given video using 3D human pose estimation. These extracted arm motions are then morphologically retargeted onto a robotic manipulator. Subsequently, the retargeted motions are used to generate reference motions. Finally, these reference motions are used to formulate a reinforcement learning problem, enabling the agent to learn a policy for imitating human arm motions. This project excels at imitation tasks and demonstrates robust transferability, accurately imitating human arm motions from other unfamiliar videos. This project provides a lightweight, convenient, efficient, and accurate Motion Imitation model. While simplifying the complex process of Motion Imitation, it achieves notably outstanding performance.
In the realm of multi-arm bandit problems, the Gittins index policy is known to be optimal in maximizing the expected total discounted reward obtained from pulling the Markovian arms. In most realistic scenarios however, the Markovian state transition probabilities are unknown and therefore the Gittins indices cannot be computed. One can then resort to reinforcement learning (RL) algorithms that explore the state space to learn these indices while exploiting to maximize the reward collected. In this work, we propose tabular (QGI) and Deep RL (DGN) algorithms for learning the Gittins index that are based on the retirement formulation for the multi-arm bandit problem. When compared with existing RL algorithms that learn the Gittins index, our algorithms have a lower run time, require less storage space (small Q-table size in QGI and smaller replay buffer in DGN), and illustrate better empirical convergence to the Gittins index. This makes our algorithm well suited for problems with large state spaces and is a viable alternative to existing methods. As a key application, we demonstrate the use of our algorithms in minimizing the mean flowtime in a job scheduling problem when jobs are available in batches and have an unknown service time distribution.
Reinforcement learning policies are typically represented by black-box neural networks, which are non-interpretable and not well-suited for safety-critical domains. To address both of these issues, we propose constrained normalizing flow policies as interpretable and safe-by-construction policy models. We achieve safety for reinforcement learning problems with instantaneous safety constraints, for which we can exploit domain knowledge by analytically constructing a normalizing flow that ensures constraint satisfaction. The normalizing flow corresponds to an interpretable sequence of transformations on action samples, each ensuring alignment with respect to a particular constraint. Our experiments reveal benefits beyond interpretability in an easier learning objective and maintained constraint satisfaction throughout the entire learning process. Our approach leverages constraints over reward engineering while offering enhanced interpretability, safety, and direct means of providing domain knowledge to the agent without relying on complex reward functions.
The ability to autonomously assemble structures is crucial for the development of future space infrastructure. However, the unpredictable conditions of space pose significant challenges for robotic systems, necessitating the development of advanced learning techniques to enable autonomous assembly. In this study, we present a novel approach for learning autonomous peg-in-hole assembly in the context of space robotics. Our focus is on enhancing the generalization and adaptability of autonomous systems through deep reinforcement learning. By integrating procedural generation and domain randomization, we train agents in a highly parallelized simulation environment across a spectrum of diverse scenarios with the aim of acquiring a robust policy. The proposed approach is evaluated using three distinct reinforcement learning algorithms to investigate the trade-offs among various paradigms. We demonstrate the adaptability of our agents to novel scenarios and assembly sequences while emphasizing the potential of leveraging advanced simulation techniques for robot learning in space. Our findings set the stage for future advancements in intelligent robotic systems capable of supporting ambitious space missions and infrastructure development beyond Earth.
Transesophageal echocardiography (TEE) plays a pivotal role in cardiology for diagnostic and interventional procedures. However, using it effectively requires extensive training due to the intricate nature of image acquisition and interpretation. To enhance the efficiency of novice sonographers and reduce variability in scan acquisitions, we propose a novel ultrasound (US) navigation assistance method based on contrastive learning as goal-conditioned reinforcement learning (GCRL). We augment the previous framework using a novel contrastive patient batching method (CPB) and a data-augmented contrastive loss, both of which we demonstrate are essential to ensure generalization to anatomical variations across patients. The proposed framework enables navigation to both standard diagnostic as well as intricate interventional views with a single model. Our method was developed with a large dataset of 789 patients and obtained an average error of 6.56 mm in position and 9.36 degrees in angle on a testing dataset of 140 patients, which is competitive or superior to models trained on individual views. Furthermore, we quantitatively validate our method's ability to navigate to interventional views such as the Left Atrial Appendage (LAA) view used in LAA closure. Our approach holds promise in providing valuable guidance during transesophageal ultrasound examinations, contributing to the advancement of skill acquisition for cardiac ultrasound practitioners.
We address eco-driving at roundabouts in mixed traffic to enhance traffic flow and traffic efficiency in urban areas. The aim is to proactively optimize speed of automated or non-automated connected vehicles (CVs), ensuring both an efficient approach and smooth entry into roundabouts. We incorporate the traffic situation ahead, i.e. preceding vehicles and waiting queues. Further, we develop two approaches: a rule-based and an Reinforcement Learning (RL) based eco-driving system, with both using the approach link and information from conflicting CVs for speed optimization. A fair comparison of rule-based and RL-based approaches is performed to explore RL as a viable alternative to classical optimization. Results show that both approaches outperform the baseline. Improvements significantly increase with growing traffic volumes, leading to best results on average being obtained at high volumes. Near capacity, performance deteriorates, indicating limited applicability at capacity limits. Examining different CV penetration rates, a decline in performance is observed, but with substantial results still being achieved at lower CV rates. RL agents can discover effective policies for speed optimization in dynamic roundabout settings, but they do not offer a substantial advantage over classical approaches, especially at higher traffic volumes or lower CV penetration rates.
In Multi-objective Reinforcement Learning (MORL) agents are tasked with optimising decision-making behaviours that trade-off between multiple, possibly conflicting, objectives. MORL based on decomposition is a family of solution methods that employ a number of utility functions to decompose the multi-objective problem into individual single-objective problems solved simultaneously in order to approximate a Pareto front of policies. We focus on the case of linear utility functions parameterised by weight vectors w. We introduce a method based on Upper Confidence Bound to efficiently search for the most promising weight vectors during different stages of the learning process, with the aim of maximising the hypervolume of the resulting Pareto front. The proposed method is shown to outperform various MORL baselines on Mujoco benchmark problems across different random seeds. The code is online at: https://github.com/SYCAMORE-1/ucb-MOPPO.
Buildings account for 40% of global energy consumption. A considerable portion of building energy consumption stems from heating, ventilation, and air conditioning (HVAC), and thus implementing smart, energy-efficient HVAC systems has the potential to significantly impact the course of climate change. In recent years, model-free reinforcement learning algorithms have been increasingly assessed for this purpose due to their ability to learn and adapt purely from experience. They have been shown to outperform classical controllers in terms of energy cost and consumption, as well as thermal comfort. However, their weakness lies in their relatively poor data efficiency, requiring long periods of training to reach acceptable policies, making them inapplicable to real-world controllers directly. In this paper, we demonstrate that using federated learning to train the reinforcement learning controller of HVAC systems can improve the learning speed, as well as improve their ability to generalize, which in turn facilitates transfer learning to unseen building environments. In our setting, a global control policy is learned by aggregating local policies trained on multiple data centers located in different climate zones. The goal of the policy is to minimize energy consumption and maximize thermal comfort. We perform experiments evaluating three different optimizers for local policy training, as well as three different federated learning algorithms against two alternative baselines. Our experiments show that these effects lead to a faster learning speed, as well as greater generalization capabilities in the federated policy compared to any individually trained policy. Furthermore, the learning stability is significantly improved, with the learning process and performance of the federated policy being less sensitive to the choice of parameters and the inherent randomness of reinforcement learning.
Reinforcement learning for multi-agent games has attracted lots of attention recently. However, given the challenge of solving Nash equilibria for large population games, existing works with guaranteed polynomial complexities either focus on variants of zero-sum and potential games, or aim at solving (coarse) correlated equilibria, or require access to simulators, or rely on certain assumptions that are hard to verify. This work proposes MF-OML (Mean-Field Occupation-Measure Learning), an online mean-field reinforcement learning algorithm for computing approximate Nash equilibria of large population sequential symmetric games. MF-OML is the first fully polynomial multi-agent reinforcement learning algorithm for provably solving Nash equilibria (up to mean-field approximation gaps that vanish as the number of players $N$ goes to infinity) beyond variants of zero-sum and potential games. When evaluated by the cumulative deviation from Nash equilibria, the algorithm is shown to achieve a high probability regret bound of $\tilde{O}(M^{3/4}+N^{-1/2}M)$ for games with the strong Lasry-Lions monotonicity condition, and a regret bound of $\tilde{O}(M^{11/12}+N^{- 1/6}M)$ for games with only the Lasry-Lions monotonicity condition, where $M$ is the total number of episodes and $N$ is the number of agents of the game. As a byproduct, we also obtain the first tractable globally convergent computational algorithm for computing approximate Nash equilibria of monotone mean-field games.
One strategy in response to pluralistic values in a user population is to personalize an AI system: if the AI can adapt to the specific values of each individual, then we can potentially avoid many of the challenges of pluralism. Unfortunately, this approach creates a significant ethical issue: if there is an external measure of success for the human-AI team, then the adaptive AI system may develop strategies (sometimes deceptive) to compensate for its human teammate. This phenomenon can be viewed as a form of social compensation, where the AI makes decisions based not on predefined goals but on its human partner's deficiencies in relation to the team's performance objectives. We provide a practical ethical analysis of the conditions in which such compensation may nonetheless be justifiable.
In recent years, multi-agent reinforcement learning algorithms have made significant advancements in diverse gaming environments, leading to increased interest in the broader application of such techniques. To address the prevalent challenge of partial observability, communication-based algorithms have improved cooperative performance through the sharing of numerical embedding between agents. However, the understanding of the formation of collaborative mechanisms is still very limited, making designing a human-understandable communication mechanism a valuable problem to address. In this paper, we propose a novel multi-agent reinforcement learning algorithm that embeds large language models into agents, endowing them with the ability to generate human-understandable verbal communication. The entire framework has a message module and an action module. The message module is responsible for generating and sending verbal messages to other agents, effectively enhancing information sharing among agents. To further enhance the message module, we employ a teacher model to generate message labels from the global view and update the student model through Supervised Fine-Tuning (SFT). The action module receives messages from other agents and selects actions based on current local observations and received messages. Experiments conducted on the Overcooked game demonstrate our method significantly enhances the learning efficiency and performance of existing methods, while also providing an interpretable tool for humans to understand the process of multi-agent cooperation.
Reinforcement Learning (RL) provides a framework in which agents can be trained, via trial and error, to solve complex decision-making problems. Learning with little supervision causes RL methods to require large amounts of data, rendering them too expensive for many applications (e.g., robotics). By reusing knowledge from a different task, knowledge transfer methods present an alternative to reduce the training time in RL. Given the severe data scarcity, due to their flexibility, there has been a growing interest in methods capable of transferring knowledge across different domains (i.e., problems with different representations). However, identifying similarities and adapting knowledge across tasks from different domains requires matching their representations or finding domain-invariant features. These processes can be data-demanding, which poses the main challenge in cross-domain knowledge transfer: to select and transform knowledge in a data-efficient way, such that it accelerates learning in the target task, despite the presence of significant differences across problems (e.g., robots with distinct morphologies). Thus, this review presents a unifying analysis of methods focused on transferring knowledge across different domains. Through a taxonomy based on a transfer-approach categorization and a characterization of works based on their data-assumption requirements, the contributions of this article are 1) a comprehensive and systematic revision of knowledge transfer methods for the cross-domain RL setting, 2) a categorization and characterization of such methods to provide an analysis based on relevant features such as their transfer approach and data requirements, and 3) a discussion on the main challenges regarding cross-domain knowledge transfer, as well as on ideas of future directions worth exploring to address these problems.
Large Language Models (LLMs) encapsulate an extensive amount of world knowledge, and this has enabled their application in various domains to improve the performance of a variety of Natural Language Processing (NLP) tasks. This has also facilitated a more accessible paradigm of conversation-based interactions between humans and AI systems to solve intended problems. However, one interesting avenue that shows untapped potential is the use of LLMs as Reinforcement Learning (RL) agents to enable conversational RL problem solving. Therefore, in this study, we explore the concept of formulating Markov Decision Process-based RL problems as LLM prompting tasks. We demonstrate how LLMs can be iteratively prompted to learn and optimize policies for specific RL tasks. In addition, we leverage the introduced prompting technique for episode simulation and Q-Learning, facilitated by LLMs. We then show the practicality of our approach through two detailed case studies for "Research Scientist" and "Legal Matter Intake" workflows.
Reinforcement learning algorithms are used in a wide range of applications, from gaming and robotics to autonomous vehicles. In this paper we describe a set of reinforcement learning-based local weight update rules and their implementation in superconducting hardware. Using SPICE circuit simulations, we implement a small-scale neural network with a learning time of order one nanosecond. This network can be trained to learn new functions simply by changing the target output for a given set of inputs, without the need for any external adjustments to the network. In this implementation the weights are adjusted based on the current state of the overall network response and locally stored information about the previous action. This removes the need to program explicit weight values in these networks, which is one of the primary challenges that analog hardware implementations of neural networks face. The adjustment of weights is based on a global reinforcement signal that obviates the need for circuitry to back-propagate errors.