Agent faults pose a significant threat to the performance of multi-agent reinforcement learning (MARL) algorithms, introducing two key challenges. First, agents often struggle to extract critical information from the chaotic state space created by unexpected faults. Second, transitions recorded before and after faults in the replay buffer affect training unevenly, leading to a sample imbalance problem. To overcome these challenges, this paper enhances the fault tolerance of MARL by combining optimized model architecture with a tailored training data sampling strategy. Specifically, an attention mechanism is incorporated into the actor and critic networks to automatically detect faults and dynamically regulate the attention given to faulty agents. Additionally, a prioritization mechanism is introduced to selectively sample transitions critical to current training needs. To further support research in this area, we design and open-source a highly decoupled code platform for fault-tolerant MARL, aimed at improving the efficiency of studying related problems. Experimental results demonstrate the effectiveness of our method in handling various types of faults, faults occurring in any agent, and faults arising at random times.
The AI safety literature is full of examples of powerful AI agents that, in blindly pursuing a specific and usually narrow objective, ends up with unacceptable and even catastrophic collateral damage to others. In this paper, we consider the problem of social harms that can result from actions taken by learning and utility-maximising agents in a multi-agent environment. The problem of measuring social harms or impacts in such multi-agent settings, especially when the agents are artificial generally intelligent (AGI) agents, was listed as an open problem in Everitt et al, 2018. We attempt a partial answer to that open problem in the form of market-based mechanisms to quantify and control the cost of such social harms. The proposed setup captures many well-studied special cases and is more general than existing formulations of multi-agent reinforcement learning with mechanism design in two ways: (i) the underlying environment is a history-based general reinforcement learning environment like in AIXI; (ii) the reinforcement-learning agents participating in the environment can have different learning strategies and planning horizons. To demonstrate the practicality of the proposed setup, we survey some key classes of learning algorithms and present a few applications, including a discussion of the Paperclips problem and pollution control with a cap-and-trade system.
Current approximate Coarse Correlated Equilibria (CCE) algorithms struggle with equilibrium approximation for games in large stochastic environments but are theoretically guaranteed to converge to a strong solution concept. In contrast, modern Reinforcement Learning (RL) algorithms provide faster training yet yield weaker solutions. We introduce Exp3-IXrl - a blend of RL and game-theoretic approach, separating the RL agent's action selection from the equilibrium computation while preserving the integrity of the learning process. We demonstrate that our algorithm expands the application of equilibrium approximation algorithms to new environments. Specifically, we show the improved performance in a complex and adversarial cybersecurity network environment - the Cyber Operations Research Gym - and in the classical multi-armed bandit settings.
With computing now ubiquitous across government, industry, and education, cybersecurity has become a critical component for every organization on the planet. Due to this ubiquity of computing, cyber threats have continued to grow year over year, leading to labor shortages and a skills gap in cybersecurity. As a result, many cybersecurity product vendors and security organizations have looked to artificial intelligence to shore up their defenses. This work considers how to characterize attackers and defenders in one approach to the automation of cyber defense -- the application of reinforcement learning. Specifically, we characterize the types of attackers and defenders in the sense of Bayesian games and, using reinforcement learning, derive empirical findings about how to best train agents that defend against multiple types of attackers.
The increasing demand for scalable, efficient resource management in hybrid cloud environments has led to the exploration of AI-driven approaches for dynamic resource allocation. This paper presents an AI-driven framework for resource allocation among microservices in hybrid cloud platforms. The framework employs reinforcement learning (RL)-based resource utilization optimization to reduce costs and improve performance. The framework integrates AI models with cloud management tools to respond to challenges of dynamic scaling and cost-efficient low-latency service delivery. The reinforcement learning model continuously adjusts provisioned resources as required by the microservices and predicts the future consumption trends to minimize both under- and over-provisioning of resources. Preliminary simulation results indicate that using AI in the provision of resources related to costs can reduce expenditure by up to 30-40% compared to manual provisioning and threshold-based auto-scaling approaches. It is also estimated that the efficiency in resource utilization is expected to improve by 20%-30% with a corresponding latency cut of 15%-20% during the peak demand periods. This study compares the AI-driven approach with existing static and rule-based resource allocation methods, demonstrating the capability of this new model to outperform them in terms of flexibility and real-time interests. The results indicate that reinforcement learning can make optimization of hybrid cloud platforms even better, offering a 25-35% improvement in cost efficiency and the power of scaling for microservice-based applications. The proposed framework is a strong and scalable solution to managing cloud resources in dynamic and performance-critical environments.
Training deep reinforcement learning (RL) agents necessitates overcoming the highly unstable nonconvex stochastic optimization inherent in the trial-and-error mechanism. To tackle this challenge, we propose a physics-inspired optimization algorithm called relativistic adaptive gradient descent (RAD), which enhances long-term training stability. By conceptualizing neural network (NN) training as the evolution of a conformal Hamiltonian system, we present a universal framework for transferring long-term stability from conformal symplectic integrators to iterative NN updating rules, where the choice of kinetic energy governs the dynamical properties of resulting optimization algorithms. By utilizing relativistic kinetic energy, RAD incorporates principles from special relativity and limits parameter updates below a finite speed, effectively mitigating abnormal gradient influences. Additionally, RAD models NN optimization as the evolution of a multi-particle system where each trainable parameter acts as an independent particle with an individual adaptive learning rate. We prove RAD's sublinear convergence under general nonconvex settings, where smaller gradient variance and larger batch sizes contribute to tighter convergence. Notably, RAD degrades to the well-known adaptive moment estimation (ADAM) algorithm when its speed coefficient is chosen as one and symplectic factor as a small positive value. Experimental results show RAD outperforming nine baseline optimizers with five RL algorithms across twelve environments, including standard benchmarks and challenging scenarios. Notably, RAD achieves up to a 155.1% performance improvement over ADAM in Atari games, showcasing its efficacy in stabilizing and accelerating RL training.
We present a novel method for learning hierarchical abstractions that prioritize competing objectives, leading to improved global expected rewards. Our approach employs a secondary rewarding agent with multiple scalar outputs, each associated with a distinct level of abstraction. The traditional agent then learns to maximize these outputs in a hierarchical manner, conditioning each level on the maximization of the preceding level. We derive an equation that orders these scalar values and the global reward by priority, inducing a hierarchy of needs that informs goal formation. Experimental results on the Pendulum v1 environment demonstrate superior performance compared to a baseline implementation.We achieved state of the art results.
Reinforcement learning (RL) has demonstrated compelling performance in robotic tasks, but its success often hinges on the design of complex, ad hoc reward functions. Researchers have explored how Large Language Models (LLMs) could enable non-expert users to specify reward functions more easily. However, LLMs struggle to balance the importance of different features, generalize poorly to out-of-distribution robotic tasks, and cannot represent the problem properly with only text-based descriptions. To address these challenges, we propose ELEMENTAL (intEractive LEarning froM dEmoNstraTion And Language), a novel framework that combines natural language guidance with visual user demonstrations to align robot behavior with user intentions better. By incorporating visual inputs, ELEMENTAL overcomes the limitations of text-only task specifications, while leveraging inverse reinforcement learning (IRL) to balance feature weights and match the demonstrated behaviors optimally. ELEMENTAL also introduces an iterative feedback-loop through self-reflection to improve feature, reward, and policy learning. Our experiment results demonstrate that ELEMENTAL outperforms prior work by 42.3% on task success, and achieves 41.3% better generalization in out-of-distribution tasks, highlighting its robustness in LfD.
Having explored an environment, intelligent agents should be able to transfer their knowledge to most downstream tasks within that environment. Referred to as "zero-shot learning," this ability remains elusive for general-purpose reinforcement learning algorithms. While recent works have attempted to produce zero-shot RL agents, they make assumptions about the nature of the tasks or the structure of the MDP. We present \emph{Proto Successor Measure}: the basis set for all possible solutions of Reinforcement Learning in a dynamical system. We provably show that any possible policy can be represented using an affine combination of these policy independent basis functions. Given a reward function at test time, we simply need to find the right set of linear weights to combine these basis corresponding to the optimal policy. We derive a practical algorithm to learn these basis functions using only interaction data from the environment and show that our approach can produce the optimal policy at test time for any given reward function without additional environmental interactions. Project page: https://agarwalsiddhant10.github.io/projects/psm.html.
Reinforcement Learning (RL) has emerged as a powerful paradigm in Artificial Intelligence (AI), enabling agents to learn optimal behaviors through interactions with their environments. Drawing from the foundations of trial and error, RL equips agents to make informed decisions through feedback in the form of rewards or penalties. This paper presents a comprehensive survey of RL, meticulously analyzing a wide range of algorithms, from foundational tabular methods to advanced Deep Reinforcement Learning (DRL) techniques. We categorize and evaluate these algorithms based on key criteria such as scalability, sample efficiency, and suitability. We compare the methods in the form of their strengths and weaknesses in diverse settings. Additionally, we offer practical insights into the selection and implementation of RL algorithms, addressing common challenges like convergence, stability, and the exploration-exploitation dilemma. This paper serves as a comprehensive reference for researchers and practitioners aiming to harness the full potential of RL in solving complex, real-world problems.
Grounding the instruction in the environment is a key step in solving language-guided goal-reaching reinforcement learning problems. In automated reinforcement learning, a key concern is to enhance the model's ability to generalize across various tasks and environments. In goal-reaching scenarios, the agent must comprehend the different parts of the instructions within the environmental context in order to complete the overall task successfully. In this work, we propose CAREL (Cross-modal Auxiliary REinforcement Learning) as a new framework to solve this problem using auxiliary loss functions inspired by video-text retrieval literature and a novel method called instruction tracking, which automatically keeps track of progress in an environment. The results of our experiments suggest superior sample efficiency and systematic generalization for this framework in multi-modal reinforcement learning problems. Our code base is available here.
Reinforcement learning often requires extensive training data. Simulation-to-real transfer offers a promising approach to address this challenge in robotics. While differentiable simulators offer improved sample efficiency through exact gradients, they can be unstable in contact-rich environments and may lead to poor generalization. This paper introduces a novel approach integrating sharpness-aware optimization into gradient-based reinforcement learning algorithms. Our simulation results demonstrate that our method, tested on contact-rich environments, significantly enhances policy robustness to environmental variations and action perturbations while maintaining the sample efficiency of first-order methods. Specifically, our approach improves action noise tolerance compared to standard first-order methods and achieves generalization comparable to zeroth-order methods. This improvement stems from finding flatter minima in the loss landscape, associated with better generalization. Our work offers a promising solution to balance efficient learning and robust sim-to-real transfer in robotics, potentially bridging the gap between simulation and real-world performance.
This paper surveys the field of reinforcement learning from a computer-science perspective. It is written to be accessible to researchers familiar with machine learning. Both the historical basis of the field and a broad selection of current work are summarized. Reinforcement learning is the problem faced by an agent that learns behavior through trial-and-error interactions with a dynamic environment. The work described here has a resemblance to work in psychology, but differs considerably in the details and in the use of the word ``reinforcement.'' The paper discusses central issues of reinforcement learning, including trading off exploration and exploitation, establishing the foundations of the field via Markov decision theory, learning from delayed reinforcement, constructing empirical models to accelerate learning, making use of generalization and hierarchy, and coping with hidden state. It concludes with a survey of some implemented systems and an assessment of the practical utility of current methods for reinforcement learning.
This paper addresses the target-pursuit problem, aiming to ensure each pursuer's safety regarding collision avoidance, sensing range, and input saturation. An input-constrained CBF is proposed to dynamically regulate the pursuer's control, ensuring effective target pursuit even when the target performs evasive maneuvers. To further ensure safety, two sets of CBF constraints are designed to regulate the pursuer's position, enabling it to keep the target within the sensing range while avoiding collision in complex environments with external disturbances. These three CBFs collectively form our safety filter, which filters unsafe outputs from RL by solving a Quadratic Program (QP). Finally, the safety filter, combined with a switch strategy that enhances the feasibility of solving its QP, constitutes the Control Barrier Function (CBF)-Safe Reinforcement Learning (CSRL) algorithm, whose solutions are proven to satisfy the Karush-Kuhn-Tucker (KKT) conditions for all safety constraints. Simulation results validate the effectiveness of the CSRL algorithm, demonstrating its ability to handle complex pursuit scenarios while maintaining safety and improving control performance.
Wastewater treatment plants face unique challenges for process control due to their complex dynamics, slow time constants, and stochastic delays in observations and actions. These characteristics make conventional control methods, such as Proportional-Integral-Derivative controllers, suboptimal for achieving efficient phosphorus removal, a critical component of wastewater treatment to ensure environmental sustainability. This study addresses these challenges using a novel deep reinforcement learning approach based on the Soft Actor-Critic algorithm, integrated with a custom simulator designed to model the delayed feedback inherent in wastewater treatment plants. The simulator incorporates Long Short-Term Memory networks for accurate multi-step state predictions, enabling realistic training scenarios. To account for the stochastic nature of delays, agents were trained under three delay scenarios: no delay, constant delay, and random delay. The results demonstrate that incorporating random delays into the reinforcement learning framework significantly improves phosphorus removal efficiency while reducing operational costs. Specifically, the delay-aware agent achieved 36% reduction in phosphorus emissions, 55% higher reward, 77% lower target deviation from the regulatory limit, and 9% lower total costs than traditional control methods in the simulated environment. These findings underscore the potential of reinforcement learning to overcome the limitations of conventional control strategies in wastewater treatment, providing an adaptive and cost-effective solution for phosphorus removal.
In this paper, we propose a novel dependency-aware task scheduling strategy for dynamic unmanned aerial vehicle-assisted connected autonomous vehicles (CAVs). Specifically, different computation tasks of CAVs consisting of multiple dependency subtasks are judiciously assigned to nearby CAVs or the base station for promptly completing tasks. Therefore, we formulate a joint scheduling priority and subtask assignment optimization problem with the objective of minimizing the average task completion time. The problem aims at improving the long-term system performance, which is reformulated as a Markov decision process. To solve the problem, we further propose a diffusion-based reinforcement learning algorithm, named Synthetic DDQN based Subtasks Scheduling, which can make adaptive task scheduling decision in real time. A diffusion model-based synthetic experience replay is integrated into the reinforcement learning framework, which can generate sufficient synthetic data in experience replay buffer, thereby significantly accelerating convergence and improving sample efficiency. Simulation results demonstrate the effectiveness of the proposed algorithm on reducing task completion time, comparing to benchmark schemes.
Ensuring the safety of autonomous vehicles (AVs) requires identifying rare but critical failure cases that on-road testing alone cannot discover. High-fidelity simulations provide a scalable alternative, but automatically generating realistic and diverse traffic scenarios that can effectively stress test AV motion planners remains a key challenge. This paper introduces CRASH - Challenging Reinforcement-learning based Adversarial scenarios for Safety Hardening - an adversarial deep reinforcement learning framework to address this issue. First CRASH can control adversarial Non Player Character (NPC) agents in an AV simulator to automatically induce collisions with the Ego vehicle, falsifying its motion planner. We also propose a novel approach, that we term safety hardening, which iteratively refines the motion planner by simulating improvement scenarios against adversarial agents, leveraging the failure cases to strengthen the AV stack. CRASH is evaluated on a simplified two-lane highway scenario, demonstrating its ability to falsify both rule-based and learning-based planners with collision rates exceeding 90%. Additionally, safety hardening reduces the Ego vehicle's collision rate by 26%. While preliminary, these results highlight RL-based safety hardening as a promising approach for scenario-driven simulation testing for autonomous vehicles.
LLMs exhibit advanced reasoning capabilities, offering the potential to transform natural language questions into mathematical models. However, existing open-source datasets in operations research domain lack detailed annotations of the modeling process, such as variable definitions, focusing solely on objective values, which hinders reinforcement learning applications. To address this, we release the StructuredOR dataset, annotated with comprehensive labels that capture the complete mathematical modeling process. We further propose BPP-Search, an algorithm that integrates reinforcement learning into a tree-of-thought structure using Beam search, a Process reward model, and a pairwise Preference algorithm. This approach enables efficient exploration of tree structures, avoiding exhaustive search while improving accuracy. Extensive experiments on StructuredOR, NL4OPT, and MAMO-ComplexLP datasets show that BPP-Search significantly outperforms state-of-the-art methods. In tree-based reasoning, BPP-Search excels in accuracy and efficiency, enabling faster retrieval of correct solutions. The StructuredOR dataset is available at https://github.com/tengwang0318/StructuredOR.
South Africa stands at a crucial juncture, grappling with interwoven socio-economic challenges such as poverty, inequality, unemployment, and the looming climate crisis. The government's Just Transition framework aims to enhance climate resilience, achieve net-zero greenhouse gas emissions by 2050, and promote social inclusion and poverty eradication. According to the Presidential Commission on the Fourth Industrial Revolution, artificial intelligence technologies offer significant promise in addressing these challenges. This paper explores the overlooked potential of Reinforcement Learning (RL) in supporting South Africa's Just Transition. It examines how RL can enhance agriculture and land-use practices, manage complex, decentralised energy networks, and optimise transportation and logistics, thereby playing a critical role in achieving a just and equitable transition to a low-carbon future for all South Africans. We provide a roadmap as to how other researchers in the field may be able to contribute to these pressing problems.
Central to the development of universal learning systems is the ability to solve multiple tasks without retraining from scratch when new data arrives. This is crucial because each task requires significant training time. Addressing the problem of continual learning necessitates various methods due to the complexity of the problem space. This problem space includes: (1) addressing catastrophic forgetting to retain previously learned tasks, (2) demonstrating positive forward transfer for faster learning, (3) ensuring scalability across numerous tasks, and (4) facilitating learning without requiring task labels, even in the absence of clear task boundaries. In this paper, the Task-Agnostic Policy Distillation (TAPD) framework is introduced. This framework alleviates problems (1)-(4) by incorporating a task-agnostic phase, where an agent explores its environment without any external goal and maximizes only its intrinsic motivation. The knowledge gained during this phase is later distilled for further exploration. Therefore, the agent acts in a self-supervised manner by systematically seeking novel states. By utilizing task-agnostic distilled knowledge, the agent can solve downstream tasks more efficiently, leading to improved sample efficiency. Our code is available at the repository: https://github.com/wabbajack1/TAPD.