PyTorchKR Papers

최신 논문

총 13,741편
태그·기간 등 상세 필터

카테고리 탐색

로그인 후 이 태그 구독

arXiv:2410.21240

Quantum Reinforcement Learning-Based Two-Stage Unit Commitment Framework for Enhanced Power Systems Robustness

Unit commitment (UC) optimizes the start-up and shutdown schedules of generating units to meet load demand while minimizing costs. However, the increasing integration of renewable energy introduces uncertainties for real-time scheduling. Existing solutions face limitations both in modeling and algorithmic design. At the modeling level, they fail to incorporate widely adopted virtual power plants (VPPs) as flexibility resources, missing the opportunity to proactively mitigate potential real-time imbalances or ramping constraints through foresight-seeing decision-making. At the algorithmic level, existing probabilistic optimization, multi-stage approaches, and machine learning, face challenges in computational complexity and adaptability. To address these challenges, this study proposes a novel two-stage UC framework that incorporates foresight-seeing sequential decision-making in both day-ahead and real-time scheduling, leveraging VPPs as flexibility resources to proactively reserve capacity and ramping flexibility for upcoming renewable energy uncertainties over several hours. In particular, we develop quantum reinforcement learning (QRL) algorithms that integrate the foresight-seeing sequential decision-making and scalable computation advantages of deep reinforcement learning (DRL) with the parallel and high-efficiency search capabilities of quantum computing. Experimental results demonstrate that the proposed QRL-based approach outperforms in computational efficiency, real-time responsiveness, and solution quality.

arXiv:2410.19859

Multi-Modal Transformer and Reinforcement Learning-based Beam Management

Beam management is an important technique to improve signal strength and reduce interference in wireless communication systems. Recently, there has been increasing interest in using diverse sensing modalities for beam management. However, it remains a big challenge to process multi-modal data efficiently and extract useful information. On the other hand, the recently emerging multi-modal transformer (MMT) is a promising technique that can process multi-modal data by capturing long-range dependencies. While MMT is highly effective in handling multi-modal data and providing robust beam management, integrating reinforcement learning (RL) further enhances their adaptability in dynamic environments. In this work, we propose a two-step beam management method by combining MMT with RL for dynamic beam index prediction. In the first step, we divide available beam indices into several groups and leverage MMT to process diverse data modalities to predict the optimal beam group. In the second step, we employ RL for fast beam decision-making within each group, which in return maximizes throughput. Our proposed framework is tested on a 6G dataset. In this testing scenario, it achieves higher beam prediction accuracy and system throughput compared to both the MMT-only based method and the RL-only based method.

arXiv:2410.20869공식 코드 · Papers with Code

Reward Modeling with Weak Supervision for Language Models

Recent advancements in large language models (LLMs) have led to their increased application across various tasks, with reinforcement learning from human feedback (RLHF) being a crucial part of their training to align responses with user intentions. In the RLHF process, a reward model is trained using responses preferences determined by human labelers or AI systems, which then refines the LLM through reinforcement learning. This work introduces weak supervision as a strategy to extend RLHF datasets and enhance reward model performance. Weak supervision employs noisy or imprecise data labeling, reducing reliance on expensive manually labeled data. By analyzing RLHF datasets to identify heuristics that correlate with response preference, we wrote simple labeling functions and then calibrated a label model to weakly annotate unlabeled data. Our evaluation show that while weak supervision significantly benefits smaller datasets by improving reward model performance, its effectiveness decreases with larger, originally labeled datasets. Additionally, using an LLM to generate and then weakly label responses offers a promising method for extending preference data.

arXiv:2410.19989

On-Robot Reinforcement Learning with Goal-Contrastive Rewards

Reinforcement Learning (RL) has the potential to enable robots to learn from their own actions in the real world. Unfortunately, RL can be prohibitively expensive, in terms of on-robot runtime, due to inefficient exploration when learning from a sparse reward signal. Designing dense reward functions is labour-intensive and requires domain expertise. In our work, we propose GCR (Goal-Contrastive Rewards), a dense reward function learning method that can be trained on passive video demonstrations. By using videos without actions, our method is easier to scale, as we can use arbitrary videos. GCR combines two loss functions, an implicit value loss function that models how the reward increases when traversing a successful trajectory, and a goal-contrastive loss that discriminates between successful and failed trajectories. We perform experiments in simulated manipulation environments across RoboMimic and MimicGen tasks, as well as in the real world using a Franka arm and a Spot quadruped. We find that GCR leads to a more-sample efficient RL, enabling model-free RL to solve about twice as many tasks as our baseline reward learning methods. We also demonstrate positive cross-embodiment transfer from videos of people and of other robots performing a task. Website: https://gcr-robot.github.io/.

arXiv:2410.20786

Adversarial Constrained Policy Optimization: Improving Constrained Reinforcement Learning by Adapting Budgets

Constrained reinforcement learning has achieved promising progress in safety-critical fields where both rewards and constraints are considered. However, constrained reinforcement learning methods face challenges in striking the right balance between task performance and constraint satisfaction and it is prone for them to get stuck in over-conservative or constraint violating local minima. In this paper, we propose Adversarial Constrained Policy Optimization (ACPO), which enables simultaneous optimization of reward and the adaptation of cost budgets during training. Our approach divides original constrained problem into two adversarial stages that are solved alternately, and the policy update performance of our algorithm can be theoretically guaranteed. We validate our method through experiments conducted on Safety Gymnasium and quadruped locomotion tasks. Results demonstrate that our algorithm achieves better performances compared to commonly used baselines.

arXiv:2410.20254

Overcoming the Sim-to-Real Gap: Leveraging Simulation to Learn to Explore for Real-World RL

In order to mitigate the sample complexity of real-world reinforcement learning, common practice is to first train a policy in a simulator where samples are cheap, and then deploy this policy in the real world, with the hope that it generalizes effectively. Such \emph{direct sim2real} transfer is not guaranteed to succeed, however, and in cases where it fails, it is unclear how to best utilize the simulator. In this work, we show that in many regimes, while direct sim2real transfer may fail, we can utilize the simulator to learn a set of \emph{exploratory} policies which enable efficient exploration in the real world. In particular, in the setting of low-rank MDPs, we show that coupling these exploratory policies with simple, practical approaches -- least-squares regression oracles and naive randomized exploration -- yields a polynomial sample complexity in the real world, an exponential improvement over direct sim2real transfer, or learning without access to a simulator. To the best of our knowledge, this is the first evidence that simulation transfer yields a provable gain in reinforcement learning in settings where direct sim2real transfer fails. We validate our theoretical results on several realistic robotic simulators and a real-world robotic sim2real task, demonstrating that transferring exploratory policies can yield substantial gains in practice as well.

arXiv:2410.21151

Offline Reinforcement Learning With Combinatorial Action Spaces

Reinforcement learning problems often involve large action spaces arising from the simultaneous execution of multiple sub-actions, resulting in combinatorial action spaces. Learning in combinatorial action spaces is difficult due to the exponential growth in action space size with the number of sub-actions and the dependencies among these sub-actions. In offline settings, this challenge is compounded by limited and suboptimal data. Current methods for offline learning in combinatorial spaces simplify the problem by assuming sub-action independence. We propose Branch Value Estimation (BVE), which effectively captures sub-action dependencies and scales to large combinatorial spaces by learning to evaluate only a small subset of actions at each timestep. Our experiments show that BVE outperforms state-of-the-art methods across a range of action space sizes.

arXiv:2410.21117공식 코드 · Papers with Code

Robustness and Generalization in Quantum Reinforcement Learning via Lipschitz Regularization

Quantum machine learning leverages quantum computing to enhance accuracy and reduce model complexity compared to classical approaches, promising significant advancements in various fields. Within this domain, quantum reinforcement learning has garnered attention, often realized using variational quantum circuits to approximate the policy function. This paper addresses the robustness and generalization of quantum reinforcement learning by combining principles from quantum computing and control theory. Leveraging recent results on robust quantum machine learning, we utilize Lipschitz bounds to propose a regularized version of a quantum policy gradient approach, named the RegQPG algorithm. We show that training with RegQPG improves the robustness and generalization of the resulting policies. Furthermore, we introduce an algorithmic variant that incorporates curriculum learning, which minimizes failures during training. Our findings are validated through numerical experiments, demonstrating the practical benefits of our approach.

arXiv:2410.21109

Dual-Agent Deep Reinforcement Learning for Dynamic Pricing and Replenishment

We study the dynamic pricing and replenishment problems under inconsistent decision frequencies. Different from the traditional demand assumption, the discreteness of demand and the parameter within the Poisson distribution as a function of price introduce complexity into analyzing the problem property. We demonstrate the concavity of the single-period profit function with respect to product price and inventory within their respective domains. The demand model is enhanced by integrating a decision tree-based machine learning approach, trained on comprehensive market data. Employing a two-timescale stochastic approximation scheme, we address the discrepancies in decision frequencies between pricing and replenishment, ensuring convergence to local optimum. We further refine our methodology by incorporating deep reinforcement learning (DRL) techniques and propose a fast-slow dual-agent DRL algorithm. In this approach, two agents handle pricing and inventory and are updated on different scales. Numerical results from both single and multiple products scenarios validate the effectiveness of our methods.

arXiv:2410.20657

Video to Video Generative Adversarial Network for Few-shot Learning Based on Policy Gradient

The development of sophisticated models for video-to-video synthesis has been facilitated by recent advances in deep reinforcement learning and generative adversarial networks (GANs). In this paper, we propose RL-V2V-GAN, a new deep neural network approach based on reinforcement learning for unsupervised conditional video-to-video synthesis. While preserving the unique style of the source video domain, our approach aims to learn a mapping from a source video domain to a target video domain. We train the model using policy gradient and employ ConvLSTM layers to capture the spatial and temporal information by designing a fine-grained GAN architecture and incorporating spatio-temporal adversarial goals. The adversarial losses aid in content translation while preserving style. Unlike traditional video-to-video synthesis methods requiring paired inputs, our proposed approach is more general because it does not require paired inputs. Thus, when dealing with limited videos in the target domain, i.e., few-shot learning, it is particularly effective. Our experiments show that RL-V2V-GAN can produce temporally coherent video results. These results highlight the potential of our approach for further advances in video-to-video synthesis.

arXiv:2410.20187

Uncertainty-Penalized Direct Preference Optimization

Aligning Large Language Models (LLMs) to human preferences in content, style, and presentation is challenging, in part because preferences are varied, context-dependent, and sometimes inherently ambiguous. While successful, Reinforcement Learning from Human Feedback (RLHF) and Direct Preference Optimization (DPO) are prone to the issue of proxy reward overoptimization. Analysis of the DPO loss reveals a critical need for regularization for mislabeled or ambiguous preference pairs to avoid reward hacking. In this work, we develop a pessimistic framework for DPO by introducing preference uncertainty penalization schemes, inspired by offline reinforcement learning. The penalization serves as a correction to the loss which attenuates the loss gradient for uncertain samples. Evaluation of the methods is performed with GPT2 Medium on the Anthropic-HH dataset using a model ensemble to obtain uncertainty estimates, and shows improved overall performance compared to vanilla DPO, as well as better completions on prompts from high-uncertainty chosen/rejected responses.

arXiv:2410.20092공식 코드 · Papers with Code

OGBench: Benchmarking Offline Goal-Conditioned RL

Offline goal-conditioned reinforcement learning (GCRL) is a major problem in reinforcement learning (RL) because it provides a simple, unsupervised, and domain-agnostic way to acquire diverse behaviors and representations from unlabeled data without rewards. Despite the importance of this setting, we lack a standard benchmark that can systematically evaluate the capabilities of offline GCRL algorithms. In this work, we propose OGBench, a new, high-quality benchmark for algorithms research in offline goal-conditioned RL. OGBench consists of 8 types of environments, 85 datasets, and reference implementations of 6 representative offline GCRL algorithms. We have designed these challenging and realistic environments and datasets to directly probe different capabilities of algorithms, such as stitching, long-horizon reasoning, and the ability to handle high-dimensional inputs and stochasticity. While representative algorithms may rank similarly on prior benchmarks, our experiments reveal stark strengths and weaknesses in these different capabilities, providing a strong foundation for building new algorithms. Project page: https://seohong.me/projects/ogbench

arXiv:2410.19982

Random Policy Enables In-Context Reinforcement Learning within Trust Horizons

Pretrained foundation models have exhibited extraordinary in-context learning performance, allowing zero-shot generalization to new tasks not encountered during pretraining. In the case of reinforcement learning (RL), in-context RL (ICRL) emerges when pretraining FMs on decision-making problems in an autoregressive-supervised manner. Nevertheless, current state-of-the-art ICRL algorithms, like Algorithm Distillation, Decision Pretrained Transformer and Decision Importance Transformer, impose stringent requirements on the pretraining dataset concerning the source policies, context information, and action labels. Notably, these algorithms either demand optimal policies or require varying degrees of well-trained behavior policies for all pretraining environments. This significantly hinders the application of ICRL to real-world scenarios, where acquiring optimal or well-trained policies for a substantial volume of real-world training environments can be intractable. To overcome this challenge, we introduce a novel approach, termed State-Action Distillation (SAD), that allows to generate an effective pretraining dataset guided solely by random policies. In particular, SAD selects query states and corresponding action labels by distilling outstanding state-action pairs from the entire state and action spaces by using random policies within a trust horizon, and then inherits the classical autoregressive-supervised mechanism during pretraining. To the best of our knowledge, this is the first work that enables effective ICRL under random policies and random contexts. We also establish quantitative analysis of the trustworthiness as well as the performance guarantees of SAD. Moreover, our empirical results across multiple popular ICRL benchmark environments demonstrate that, on average, SAD outperforms the best baseline by 236.3% in the offline evaluation and by 135.2% in the online evaluation.

arXiv:2410.19919

Provably Adaptive Average Reward Reinforcement Learning for Metric Spaces

We study infinite-horizon average-reward reinforcement learning (RL) for Lipschitz MDPs and develop an algorithm ZoRL that discretizes the state-action space adaptively and zooms into promising regions of the state-action space. We show that its regret can be bounded as $\mathcal{\tilde{O}}\big(T^{1 - d_{\text{eff.}}^{-1}}\big)$, where $d_{\text{eff.}} = 2d_\mathcal{S} + d_z + 3$, $d_\mathcal{S}$ is the dimension of the state space, and $d_z$ is the zooming dimension. $d_z$ is a problem-dependent quantity, which allows us to conclude that if MDP is benign, then its regret will be small. We note that the existing notion of zooming dimension for average reward RL is defined in terms of policy coverings, and hence it can be huge when the policy class is rich even though the underlying MDP is simple, so that the regret upper bound is nearly $O(T)$. The zooming dimension proposed in the current work is bounded above by $d$, the dimension of the state-action space, and hence is truly adaptive, i.e., shows how to capture adaptivity gains for infinite-horizon average-reward RL. ZoRL outperforms other state-of-the-art algorithms in experiments; thereby demonstrating the gains arising due to adaptivity.

arXiv:2410.20954

Active Legibility in Multiagent Reinforcement Learning

A multiagent sequential decision problem has been seen in many critical applications including urban transportation, autonomous driving cars, military operations, etc. Its widely known solution, namely multiagent reinforcement learning, has evolved tremendously in recent years. Among them, the solution paradigm of modeling other agents attracts our interest, which is different from traditional value decomposition or communication mechanisms. It enables agents to understand and anticipate others' behaviors and facilitates their collaboration. Inspired by recent research on the legibility that allows agents to reveal their intentions through their behavior, we propose a multiagent active legibility framework to improve their performance. The legibility-oriented framework allows agents to conduct legible actions so as to help others optimise their behaviors. In addition, we design a series of problem domains that emulate a common scenario and best characterize the legibility in multiagent reinforcement learning. The experimental results demonstrate that the new framework is more efficient and costs less training time compared to several multiagent reinforcement learning algorithms.

arXiv:2410.20750공식 코드 · Papers with Code

ODRL: A Benchmark for Off-Dynamics Reinforcement Learning

We consider off-dynamics reinforcement learning (RL) where one needs to transfer policies across different domains with dynamics mismatch. Despite the focus on developing dynamics-aware algorithms, this field is hindered due to the lack of a standard benchmark. To bridge this gap, we introduce ODRL, the first benchmark tailored for evaluating off-dynamics RL methods. ODRL contains four experimental settings where the source and target domains can be either online or offline, and provides diverse tasks and a broad spectrum of dynamics shifts, making it a reliable platform to comprehensively evaluate the agent's adaptation ability to the target domain. Furthermore, ODRL includes recent off-dynamics RL algorithms in a unified framework and introduces some extra baselines for different settings, all implemented in a single-file manner. To unpack the true adaptation capability of existing methods, we conduct extensive benchmarking experiments, which show that no method has universal advantages across varied dynamics shifts. We hope this benchmark can serve as a cornerstone for future research endeavors. Our code is publicly available at https://github.com/OffDynamicsRL/off-dynamics-rl.

arXiv:2410.21029공식 코드 · Papers with Code

FairStream: Fair Multimedia Streaming Benchmark for Reinforcement Learning Agents

Multimedia streaming accounts for the majority of traffic in today's internet. Mechanisms like adaptive bitrate streaming control the bitrate of a stream based on the estimated bandwidth, ideally resulting in smooth playback and a good Quality of Experience (QoE). However, selecting the optimal bitrate is challenging under volatile network conditions. This motivated researchers to train Reinforcement Learning (RL) agents for multimedia streaming. The considered training environments are often simplified, leading to promising results with limited applicability. Additionally, the QoE fairness across multiple streams is seldom considered by recent RL approaches. With this work, we propose a novel multi-agent environment that comprises multiple challenges of fair multimedia streaming: partial observability, multiple objectives, agent heterogeneity and asynchronicity. We provide and analyze baseline approaches across five different traffic classes to gain detailed insights into the behavior of the considered agents, and show that the commonly used Proximal Policy Optimization (PPO) algorithm is outperformed by a simple greedy heuristic. Future work includes the adaptation of multi-agent RL algorithms and further expansions of the environment.

arXiv:2410.19434

Evolving choice hysteresis in reinforcement learning: comparing the adaptive value of positivity bias and gradual perseveration

The tendency of repeating past choices more often than expected from the history of outcomes has been repeatedly empirically observed in reinforcement learning experiments. It can be explained by at least two computational processes: asymmetric update and (gradual) choice perseveration. A recent meta-analysis showed that both mechanisms are detectable in human reinforcement learning. However, while their descriptive value seems to be well established, they have not been compared regarding their possible adaptive value. In this study, we address this gap by simulating reinforcement learning agents in a variety of environments with a new variant of an evolutionary algorithm. Our results show that positivity bias (in the form of asymmetric update) is evolutionary stable in many situations, while the emergence of gradual perseveration is less systematic and robust. Overall, our results illustrate that biases can be adaptive and selected by evolution, in an environment-specific manner.

arXiv:2406.00392공식 코드 · Papers with Code

Artificial Generational Intelligence: Cultural Accumulation in Reinforcement Learning

Cultural accumulation drives the open-ended and diverse progress in capabilities spanning human history. It builds an expanding body of knowledge and skills by combining individual exploration with inter-generational information transmission. Despite its widespread success among humans, the capacity for artificial learning agents to accumulate culture remains under-explored. In particular, approaches to reinforcement learning typically strive for improvements over only a single lifetime. Generational algorithms that do exist fail to capture the open-ended, emergent nature of cultural accumulation, which allows individuals to trade-off innovation and imitation. Building on the previously demonstrated ability for reinforcement learning agents to perform social learning, we find that training setups which balance this with independent learning give rise to cultural accumulation. These accumulating agents outperform those trained for a single lifetime with the same cumulative experience. We explore this accumulation by constructing two models under two distinct notions of a generation: episodic generations, in which accumulation occurs via in-context learning and train-time generations, in which accumulation occurs via in-weights learning. In-context and in-weights cultural accumulation can be interpreted as analogous to knowledge and skill accumulation, respectively. To the best of our knowledge, this work is the first to present general models that achieve emergent cultural accumulation in reinforcement learning, opening up new avenues towards more open-ended learning systems, as well as presenting new opportunities for modelling human culture.

arXiv:2410.19372공식 코드 · Papers with Code

Toward Finding Strong Pareto Optimal Policies in Multi-Agent Reinforcement Learning

In this work, we study the problem of finding Pareto optimal policies in multi-agent reinforcement learning problems with cooperative reward structures. We show that any algorithm where each agent only optimizes their reward is subject to suboptimal convergence. Therefore, to achieve Pareto optimality, agents have to act altruistically by considering the rewards of others. This observation bridges the multi-objective optimization framework and multi-agent reinforcement learning together. We first propose a framework for applying the Multiple Gradient Descent algorithm (MGDA) for learning in multi-agent settings. We further show that standard MGDA is subjected to weak Pareto convergence, a problem that is often overlooked in other learning settings but is prevalent in multi-agent reinforcement learning. To mitigate this issue, we propose MGDA++, an improvement of the existing algorithm to handle the weakly optimal convergence of MGDA properly. Theoretically, we prove that MGDA++ converges to strong Pareto optimal solutions in convex, smooth bi-objective problems. We further demonstrate the superiority of our MGDA++ in cooperative settings in the Gridworld benchmark. The results highlight that our proposed method can converge efficiently and outperform the other methods in terms of the optimality of the convergent policies. The source code is available at \url{https://github.com/giangbang/Strong-Pareto-MARL}.