PyTorchKR Papers

최신 논문

총 13,741편
태그·기간 등 상세 필터

카테고리 탐색

로그인 후 이 태그 구독

arXiv:2409.05291

Towards Fast Rates for Federated and Multi-Task Reinforcement Learning

We consider a setting involving $N$ agents, where each agent interacts with an environment modeled as a Markov Decision Process (MDP). The agents' MDPs differ in their reward functions, capturing heterogeneous objectives/tasks. The collective goal of the agents is to communicate intermittently via a central server to find a policy that maximizes the average of long-term cumulative rewards across environments. The limited existing work on this topic either only provide asymptotic rates, or generate biased policies, or fail to establish any benefits of collaboration. In response, we propose Fast-FedPG - a novel federated policy gradient algorithm with a carefully designed bias-correction mechanism. Under a gradient-domination condition, we prove that our algorithm guarantees (i) fast linear convergence with exact gradients, and (ii) sub-linear rates that enjoy a linear speedup w.r.t. the number of agents with noisy, truncated policy gradients. Notably, in each case, the convergence is to a globally optimal policy with no heterogeneity-induced bias. In the absence of gradient-domination, we establish convergence to a first-order stationary point at a rate that continues to benefit from collaboration.

arXiv:2409.05435공식 코드 · Papers with Code

Semifactual Explanations for Reinforcement Learning

Reinforcement Learning (RL) is a learning paradigm in which the agent learns from its environment through trial and error. Deep reinforcement learning (DRL) algorithms represent the agent's policies using neural networks, making their decisions difficult to interpret. Explaining the behaviour of DRL agents is necessary to advance user trust, increase engagement, and facilitate integration with real-life tasks. Semifactual explanations aim to explain an outcome by providing "even if" scenarios, such as "even if the car were moving twice as slowly, it would still have to swerve to avoid crashing". Semifactuals help users understand the effects of different factors on the outcome and support the optimisation of resources. While extensively studied in psychology and even utilised in supervised learning, semifactuals have not been used to explain the decisions of RL systems. In this work, we develop a first approach to generating semifactual explanations for RL agents. We start by defining five properties of desirable semifactual explanations in RL and then introducing SGRL-Rewind and SGRL-Advance, the first algorithms for generating semifactual explanations in RL. We evaluate the algorithms in two standard RL environments and find that they generate semifactuals that are easier to reach, represent the agent's policy better, and are more diverse compared to baselines. Lastly, we conduct and analyse a user study to assess the participant's perception of semifactual explanations of the agent's actions.

arXiv:2409.05433

State-Novelty Guided Action Persistence in Deep Reinforcement Learning

While a powerful and promising approach, deep reinforcement learning (DRL) still suffers from sample inefficiency, which can be notably improved by resorting to more sophisticated techniques to address the exploration-exploitation dilemma. One such technique relies on action persistence (i.e., repeating an action over multiple steps). However, previous work exploiting action persistence either applies a fixed strategy or learns additional value functions (or policy) for selecting the repetition number. In this paper, we propose a novel method to dynamically adjust the action persistence based on the current exploration status of the state space. In such a way, our method does not require training of additional value functions or policy. Moreover, the use of a smooth scheduling of the repeat probability allows a more effective balance between exploration and exploitation. Furthermore, our method can be seamlessly integrated into various basic exploration strategies to incorporate temporal persistence. Finally, extensive experiments on different DMControl tasks demonstrate that our state-novelty guided action persistence method significantly improves the sample efficiency.

arXiv:2409.04896

Reinforcement Learning-Based Adaptive Load Balancing for Dynamic Cloud Environments

Efficient load balancing is crucial in cloud computing environments to ensure optimal resource utilization, minimize response times, and prevent server overload. Traditional load balancing algorithms, such as round-robin or least connections, are often static and unable to adapt to the dynamic and fluctuating nature of cloud workloads. In this paper, we propose a novel adaptive load balancing framework using Reinforcement Learning (RL) to address these challenges. The RL-based approach continuously learns and improves the distribution of tasks by observing real-time system performance and making decisions based on traffic patterns and resource availability. Our framework is designed to dynamically reallocate tasks to minimize latency and ensure balanced resource usage across servers. Experimental results show that the proposed RL-based load balancer outperforms traditional algorithms in terms of response time, resource utilization, and adaptability to changing workloads. These findings highlight the potential of AI-driven solutions for enhancing the efficiency and scalability of cloud infrastructures.

arXiv:2409.05846

An Introduction to Quantum Reinforcement Learning (QRL)

Recent advancements in quantum computing (QC) and machine learning (ML) have sparked considerable interest in the integration of these two cutting-edge fields. Among the various ML techniques, reinforcement learning (RL) stands out for its ability to address complex sequential decision-making problems. RL has already demonstrated substantial success in the classical ML community. Now, the emerging field of Quantum Reinforcement Learning (QRL) seeks to enhance RL algorithms by incorporating principles from quantum computing. This paper offers an introduction to this exciting area for the broader AI and ML community.

arXiv:2409.04122

Prompt-based Personality Profiling: Reinforcement Learning for Relevance Filtering

Author profiling is the task of inferring characteristics about individuals by analyzing content they share. Supervised machine learning still dominates automatic systems that perform this task, despite the popularity of prompting large language models to address natural language understanding tasks. One reason is that the classification instances consist of large amounts of posts, potentially a whole user profile, which may exceed the input length of Transformers. Even if a model can use a large context window, the entirety of posts makes the application of API-accessed black box systems costly and slow, next to issues which come with such "needle-in-the-haystack" tasks. To mitigate this limitation, we propose a new method for author profiling which aims at distinguishing relevant from irrelevant content first, followed by the actual user profiling only with relevant data. To circumvent the need for relevance-annotated data, we optimize this relevance filter via reinforcement learning with a reward function that utilizes the zero-shot capabilities of large language models. We evaluate our method for Big Five personality trait prediction on two Twitter corpora. On publicly available real-world data with a skewed label distribution, our method shows similar efficacy to using all posts in a user profile, but with a substantially shorter context. An evaluation on a version of these data balanced with artificial posts shows that the filtering to relevant posts leads to a significantly improved accuracy of the predictions.

arXiv:2409.03915

Asynchronous Stochastic Approximation and Average-Reward Reinforcement Learning

This paper studies asynchronous stochastic approximation (SA) algorithms and their theoretical application to reinforcement learning in semi-Markov decision processes (SMDPs) with an average-reward criterion. We first extend Borkar and Meyn's stability proof method to accommodate more general noise conditions, yielding broader convergence guarantees for asynchronous SA. To sharpen the convergence analysis, we further examine shadowing properties in the asynchronous setting, building on a dynamical-systems approach of Hirsch and Bena\"{i}m. Leveraging these SA results, we establish the convergence of an asynchronous SA analogue of Schweitzer's classical relative value iteration algorithm, RVI Q-learning, for finite-space, weakly communicating SMDPs. Moreover, to make full use of these SA results in this application, we introduce new monotonicity conditions for estimating the optimal reward rate in RVI Q-learning. These conditions substantially expand the previously considered algorithmic framework, and we address them with novel arguments in the stability and convergence analysis of RVI Q-learning.

arXiv:2409.03273

Robust synchronization and policy adaptation for networked heterogeneous agents

We propose a robust adaptive online synchronization method for leader-follower networks of nonlinear heterogeneous agents with system uncertainties and input magnitude saturation. Synchronization is achieved using a Distributed input Magnitude Saturation Adaptive Control with Reinforcement Learning (DMSAC-RL), which improves the empirical performance of policies trained on off-the-shelf models using Reinforcement Learning (RL) strategies. The leader observes the performance of a reference model, and followers observe the states and actions of the agents they are connected to, but not the reference model. The leader and followers may differ from the reference model in which the RL control policy was trained. DMSAC-RL uses an internal loop that adjusts the learned policy for the agents in the form of augmented input to solve the distributed control problem, including input-matched uncertainty parameters. We show that the synchronization error of the heterogeneous network is Uniformly Ultimately Bounded (UUB). Numerical analysis of a network of Multiple Input Multiple Output (MIMO) systems supports our theoretical findings.

arXiv:2409.03577

CHIRPs: Change-Induced Regret Proxy metrics for Lifelong Reinforcement Learning

Reinforcement learning (RL) agents are costly to train and fragile to environmental changes. They often perform poorly when there are many changing tasks, prohibiting their widespread deployment in the real world. Many Lifelong RL agent designs have been proposed to mitigate issues such as catastrophic forgetting or demonstrate positive characteristics like forward transfer when change occurs. However, no prior work has established whether the impact on agent performance can be predicted from the change itself. Understanding this relationship will help agents proactively mitigate a change's impact for improved learning performance. We propose Change-Induced Regret Proxy (CHIRP) metrics to link change to agent performance drops and use two environments to demonstrate a CHIRP's utility in lifelong learning. A simple CHIRP-based agent achieved $48\%$ higher performance than the next best method in one benchmark and attained the best success rates in 8 of 10 tasks in a second benchmark which proved difficult for existing lifelong RL agents.

arXiv:2409.03489공식 코드 · Papers with Code

Sparsifying Parametric Models with L0 Regularization

This document contains an educational introduction to the problem of sparsifying parametric models with L0 regularization. We utilize this approach together with dictionary learning to learn sparse polynomial policies for deep reinforcement learning to control parametric partial differential equations. The code and a tutorial are provided here: https://github.com/nicob15/Sparsifying-Parametric-Models-with-L0.

arXiv:2409.03301공식 코드 · Papers with Code

ELO-Rated Sequence Rewards: Advancing Reinforcement Learning Models

Reinforcement Learning (RL) is highly dependent on the meticulous design of the reward function. However, accurately assigning rewards to each state-action pair in Long-Term RL (LTRL) challenges is formidable. Consequently, RL agents are predominantly trained with expert guidance. Drawing on the principles of ordinal utility theory from economics, we propose a novel reward estimation algorithm: ELO-Rating based RL (ERRL). This approach is distinguished by two main features. Firstly, it leverages expert preferences over trajectories instead of cardinal rewards (utilities) to compute the ELO rating of each trajectory as its reward. Secondly, a new reward redistribution algorithm is introduced to mitigate training volatility in the absence of a fixed anchor reward. Our method demonstrates superior performance over several leading baselines in long-term scenarios (extending up to 5000 steps), where conventional RL algorithms falter. Furthermore, we conduct a thorough analysis of how expert preferences affect the outcomes.

arXiv:2409.00328

Foundations of Multivariate Distributional Reinforcement Learning

In reinforcement learning (RL), the consideration of multivariate reward signals has led to fundamental advancements in multi-objective decision-making, transfer learning, and representation learning. This work introduces the first oracle-free and computationally-tractable algorithms for provably convergent multivariate distributional dynamic programming and temporal difference learning. Our convergence rates match the familiar rates in the scalar reward setting, and additionally provide new insights into the fidelity of approximate return distribution representations as a function of the reward dimension. Surprisingly, when the reward dimension is larger than $1$, we show that standard analysis of categorical TD learning fails, which we resolve with a novel projection onto the space of mass-$1$ signed measures. Finally, with the aid of our technical results and simulations, we identify tradeoffs between distribution representations that influence the performance of multivariate distributional RL in practice.

arXiv:2409.02645

Emergent Language: A Survey and Taxonomy

The field of emergent language represents a novel area of research within the domain of artificial intelligence, particularly within the context of multi-agent reinforcement learning. Although the concept of studying language emergence is not new, early approaches were primarily concerned with explaining human language formation, with little consideration given to its potential utility for artificial agents. In contrast, studies based on reinforcement learning aim to develop communicative capabilities in agents that are comparable to or even superior to human language. Thus, they extend beyond the learned statistical representations that are common in natural language processing research. This gives rise to a number of fundamental questions, from the prerequisites for language emergence to the criteria for measuring its success. This paper addresses these questions by providing a comprehensive review of 181 scientific publications on emergent language in artificial intelligence. Its objective is to serve as a reference for researchers interested in or proficient in the field. Consequently, the main contributions are the definition and overview of the prevailing terminology, the analysis of existing evaluation methods and metrics, and the description of the identified research gaps.

arXiv:2409.02246

Multi-Agent Reinforcement Learning for Joint Police Patrol and Dispatch

Police patrol units need to split their time between performing preventive patrol and being dispatched to serve emergency incidents. In the existing literature, patrol and dispatch decisions are often studied separately. We consider joint optimization of these two decisions to improve police operations efficiency and reduce response time to emergency calls. Methodology/results: We propose a novel method for jointly optimizing multi-agent patrol and dispatch to learn policies yielding rapid response times. Our method treats each patroller as an independent Q-learner (agent) with a shared deep Q-network that represents the state-action values. The dispatching decisions are chosen using mixed-integer programming and value function approximation from combinatorial action spaces. We demonstrate that this heterogeneous multi-agent reinforcement learning approach is capable of learning joint policies that outperform those optimized for patrol or dispatch alone. Managerial Implications: Policies jointly optimized for patrol and dispatch can lead to more effective service while targeting demonstrably flexible objectives, such as those encouraging efficiency and equity in response.

arXiv:2409.02137

Reward Augmentation in Reinforcement Learning for Testing Distributed Systems

Bugs in popular distributed protocol implementations have been the source of many downtimes in popular internet services. We describe a randomized testing approach for distributed protocol implementations based on reinforcement learning. Since the natural reward structure is very sparse, the key to successful exploration in reinforcement learning is reward augmentation. We show two different techniques that build on one another. First, we provide a decaying exploration bonus based on the discovery of new states -- the reward decays as the same state is visited multiple times. The exploration bonus captures the intuition from coverage-guided fuzzing of prioritizing new coverage points; in contrast to other schemes, we show that taking the maximum of the bonus and the Q-value leads to more effective exploration. Second, we provide waypoints to the algorithm as a sequence of predicates that capture interesting semantic scenarios. Waypoints exploit designer insight about the protocol and guide the exploration to ``interesting'' parts of the state space. Our reward structure ensures that new episodes can reliably get to deep interesting states even without execution caching. We have implemented our algorithm in Go. Our evaluation on three large benchmarks (RedisRaft, Etcd, and RSL) shows that our algorithm can significantly outperform baseline approaches in terms of coverage and bug finding.

arXiv:2409.00418

Robust off-policy Reinforcement Learning via Soft Constrained Adversary

Recently, robust reinforcement learning (RL) methods against input observation have garnered significant attention and undergone rapid evolution due to RL's potential vulnerability. Although these advanced methods have achieved reasonable success, there have been two limitations when considering adversary in terms of long-term horizons. First, the mutual dependency between the policy and its corresponding optimal adversary limits the development of off-policy RL algorithms; although obtaining optimal adversary should depend on the current policy, this has restricted applications to off-policy RL. Second, these methods generally assume perturbations based only on the $L_p$-norm, even when prior knowledge of the perturbation distribution in the environment is available. We here introduce another perspective on adversarial RL: an f-divergence constrained problem with the prior knowledge distribution. From this, we derive two typical attacks and their corresponding robust learning frameworks. The evaluation of robustness is conducted and the results demonstrate that our proposed methods achieve excellent performance in sample-efficient off-policy RL.

arXiv:2409.01245

Revisiting Safe Exploration in Safe Reinforcement learning

Safe reinforcement learning (SafeRL) extends standard reinforcement learning with the idea of safety, where safety is typically defined through the constraint of the expected cost return of a trajectory being below a set limit. However, this metric fails to distinguish how costs accrue, treating infrequent severe cost events as equal to frequent mild ones, which can lead to riskier behaviors and result in unsafe exploration. We introduce a new metric, expected maximum consecutive cost steps (EMCC), which addresses safety during training by assessing the severity of unsafe steps based on their consecutive occurrence. This metric is particularly effective for distinguishing between prolonged and occasional safety violations. We apply EMMC in both on- and off-policy algorithm for benchmarking their safe exploration capability. Finally, we validate our metric through a set of benchmarks and propose a new lightweight benchmark task, which allows fast evaluation for algorithm design.

arXiv:2409.01104공식 코드 · Papers with Code

AI Olympics challenge with Evolutionary Soft Actor Critic

In the following report, we describe the solution we propose for the AI Olympics competition held at IROS 2024. Our solution is based on a Model-free Deep Reinforcement Learning approach combined with an evolutionary strategy. We will briefly describe the algorithms that have been used and then provide details of the approach

arXiv:2409.00858공식 코드 · Papers with Code

Trustworthy Human-AI Collaboration: Reinforcement Learning with Human Feedback and Physics Knowledge for Safe Autonomous Driving

In the field of autonomous driving, developing safe and trustworthy autonomous driving policies remains a significant challenge. Recently, Reinforcement Learning with Human Feedback (RLHF) has attracted substantial attention due to its potential to enhance training safety and sampling efficiency. Nevertheless, existing RLHF-enabled methods often falter when faced with imperfect human demonstrations, potentially leading to training oscillations or even worse performance than rule-based approaches. Inspired by the human learning process, we propose Physics-enhanced Reinforcement Learning with Human Feedback (PE-RLHF). This novel framework synergistically integrates human feedback (e.g., human intervention and demonstration) and physics knowledge (e.g., traffic flow model) into the training loop of reinforcement learning. The key advantage of PE-RLHF is its guarantee that the learned policy will perform at least as well as the given physics-based policy, even when human feedback quality deteriorates, thus ensuring trustworthy safety improvements. PE-RLHF introduces a Physics-enhanced Human-AI (PE-HAI) collaborative paradigm for dynamic action selection between human and physics-based actions, employs a reward-free approach with a proxy value function to capture human preferences, and incorporates a minimal intervention mechanism to reduce the cognitive load on human mentors. Extensive experiments across diverse driving scenarios demonstrate that PE-RLHF significantly outperforms traditional methods, achieving state-of-the-art (SOTA) performance in safety, efficiency, and generalizability, even with varying quality of human feedback. The philosophy behind PE-RLHF not only advances autonomous driving technology but can also offer valuable insights for other safety-critical domains. Demo video and code are available at: \https://zilin-huang.github.io/PE-RLHF-website/

arXiv:2409.00754

Cooperative Path Planning with Asynchronous Multiagent Reinforcement Learning

In this paper, we study the shortest path problem (SPP) with multiple source-destination pairs (MSD), namely MSD-SPP, to minimize average travel time of all shortest paths. The inherent traffic capacity limits within a road network contributes to the competition among vehicles. Multi-agent reinforcement learning (MARL) model cannot offer effective and efficient path planning cooperation due to the asynchronous decision making setting in MSD-SPP, where vehicles (a.k.a agents) cannot simultaneously complete routing actions in the previous time step. To tackle the efficiency issue, we propose to divide an entire road network into multiple sub-graphs and subsequently execute a two-stage process of inter-region and intra-region route planning. To address the asynchronous issue, in the proposed asyn-MARL framework, we first design a global state, which exploits a low-dimensional vector to implicitly represent the joint observations and actions of multi-agents. Then we develop a novel trajectory collection mechanism to decrease the redundancy in training trajectories. Additionally, we design a novel actor network to facilitate the cooperation among vehicles towards the same or close destinations and a reachability graph aimed at preventing infinite loops in routing paths. On both synthetic and real road networks, our evaluation result demonstrates that our approach outperforms state-of-the-art planning approaches.