PyTorchKR Papers

최신 논문

총 3,220편
태그·기간 등 상세 필터

카테고리 탐색

로그인 후 이 태그 구독

arXiv:2503.15049공식 코드 · Papers with Code

HAD-Gen: Human-like and Diverse Driving Behavior Modeling for Controllable Scenario Generation

Simulation-based testing has emerged as an essential tool for verifying and validating autonomous vehicles (AVs). However, contemporary methodologies, such as deterministic and imitation learning-based driver models, struggle to capture the variability of human-like driving behavior. Given these challenges, we propose HAD-Gen, a general framework for realistic traffic scenario generation that simulates diverse human-like driving behaviors. The framework first clusters the vehicle trajectory data into different driving styles according to safety features. It then employs maximum entropy inverse reinforcement learning on each of the clusters to learn the reward function corresponding to each driving style. Using these reward functions, the method integrates offline reinforcement learning pre-training and multi-agent reinforcement learning algorithms to obtain general and robust driving policies. Multi-perspective simulation results show that our proposed scenario generation framework can simulate diverse, human-like driving behaviors with strong generalization capability. The proposed framework achieves a 90.96% goal-reaching rate, an off-road rate of 2.08%, and a collision rate of 6.91% in the generalization test, outperforming prior approaches by over 20% in goal-reaching performance. The source code is released at https://github.com/RoboSafe-Lab/Sim4AD.

arXiv:2503.12395공식 코드 · Papers with Code

TERL: Large-Scale Multi-Target Encirclement Using Transformer-Enhanced Reinforcement Learning

Pursuit-evasion (PE) problem is a critical challenge in multi-robot systems (MRS). While reinforcement learning (RL) has shown its promise in addressing PE tasks, research has primarily focused on single-target pursuit, with limited exploration of multi-target encirclement, particularly in large-scale settings. This paper proposes a Transformer-Enhanced Reinforcement Learning (TERL) framework for large-scale multi-target encirclement. By integrating a transformer-based policy network with target selection, TERL enables robots to adaptively prioritize targets and safely coordinate robots. Results show that TERL outperforms existing RL-based methods in terms of encirclement success rate and task completion time, while maintaining good performance in large-scale scenarios. Notably, TERL, trained on small-scale scenarios (15 pursuers, 4 targets), generalizes effectively to large-scale settings (80 pursuers, 20 targets) without retraining, achieving a 100% success rate.

arXiv:2503.15629공식 코드 · Papers with Code

Neural Lyapunov Function Approximation with Self-Supervised Reinforcement Learning

Control Lyapunov functions are traditionally used to design a controller which ensures convergence to a desired state, yet deriving these functions for nonlinear systems remains a complex challenge. This paper presents a novel, sample-efficient method for neural approximation of nonlinear Lyapunov functions, leveraging self-supervised Reinforcement Learning (RL) to enhance training data generation, particularly for inaccurately represented regions of the state space. The proposed approach employs a data-driven World Model to train Lyapunov functions from off-policy trajectories. The method is validated on both standard and goal-conditioned robotic tasks, demonstrating faster convergence and higher approximation accuracy compared to the state-of-the-art neural Lyapunov approximation baseline. The code is available at: https://github.com/CAV-Research-Lab/SACLA.git

arXiv:2503.14976공식 코드 · Papers with Code

Application of linear regression method to the deep reinforcement learning in continuous action cases

The linear regression (LR) method offers the advantage that optimal parameters can be calculated relatively easily, although its representation capability is limited than that of the deep learning technique. To improve deep reinforcement learning, the Least Squares Deep Q Network (LS-DQN) method was proposed by Levine et al., which combines Deep Q Network (DQN) with LR method. However, the LS-DQN method assumes that the actions are discrete. In this study, we propose the Double Least Squares Deep Deterministic Policy Gradient (DLS-DDPG) method to address this limitation. This method combines the LR method with the Deep Deterministic Policy Gradient (DDPG) technique, one of the representative deep reinforcement learning algorithms for continuous action cases. Numerical experiments conducted in MuJoCo environments showed that the LR update improved performance at least in some tasks, although there are difficulties such as the inability to make the regularization terms small.

arXiv:2503.13842공식 코드 · Papers with Code

Counterfactual experience augmented off-policy reinforcement learning

Reinforcement learning control algorithms face significant challenges due to out-of-distribution and inefficient exploration problems. While model-based reinforcement learning enhances the agent's reasoning and planning capabilities by constructing virtual environments, training such virtual environments can be very complex. In order to build an efficient inference model and enhance the representativeness of learning data, we propose the Counterfactual Experience Augmentation (CEA) algorithm. CEA leverages variational autoencoders to model the dynamic patterns of state transitions and introduces randomness to model non-stationarity. This approach focuses on expanding the learning data in the experience pool through counterfactual inference and performs exceptionally well in environments that follow the bisimulation assumption. Environments with bisimulation properties are usually represented by discrete observation and action spaces, we propose a sampling method based on maximum kernel density estimation entropy to extend CEA to various environments. By providing reward signals for counterfactual state transitions based on real information, CEA constructs a complete counterfactual experience to alleviate the out-of-distribution problem of the learning data, and outperforms general SOTA algorithms in environments with difference properties. Finally, we discuss the similarities, differences and properties of generated counterfactual experiences and real experiences. The code is available at https://github.com/Aegis1863/CEA.

arXiv:2503.12358공식 코드 · Papers with Code

IPCGRL: Language-Instructed Reinforcement Learning for Procedural Level Generation

Recent research has highlighted the significance of natural language in enhancing the controllability of generative models. While various efforts have been made to leverage natural language for content generation, research on deep reinforcement learning (DRL) agents utilizing text-based instructions for procedural content generation remains limited. In this paper, we propose IPCGRL, an instruction-based procedural content generation method via reinforcement learning, which incorporates a sentence embedding model. IPCGRL fine-tunes task-specific embedding representations to effectively compress game-level conditions. We evaluate IPCGRL in a two-dimensional level generation task and compare its performance with a general-purpose embedding method. The results indicate that IPCGRL achieves up to a 21.4% improvement in controllability and a 17.2% improvement in generalizability for unseen instructions. Furthermore, the proposed method extends the modality of conditional input, enabling a more flexible and expressive interaction framework for procedural content generation.

arXiv:2503.01919공식 코드 · Papers with Code

Reinforcement learning with combinatorial actions for coupled restless bandits

Reinforcement learning (RL) has increasingly been applied to solve real-world planning problems, with progress in handling large state spaces and time horizons. However, a key bottleneck in many domains is that RL methods cannot accommodate large, combinatorially structured action spaces. In such settings, even representing the set of feasible actions at a single step may require a complex discrete optimization formulation. We leverage recent advances in embedding trained neural networks into optimization problems to propose SEQUOIA, an RL algorithm that directly optimizes for long-term reward over the feasible action space. Our approach embeds a Q-network into a mixed-integer program to select a combinatorial action in each timestep. Here, we focus on planning over restless bandits, a class of planning problems which capture many real-world examples of sequential decision making. We introduce coRMAB, a broader class of restless bandits with combinatorial actions that cannot be decoupled across the arms of the restless bandit, requiring direct solving over the joint, exponentially large action space. We empirically validate SEQUOIA on four novel restless bandit problems with combinatorial constraints: multiple interventions, path constraints, bipartite matching, and capacity constraints. Our approach significantly outperforms existing methods -- which cannot address sequential planning and combinatorial selection simultaneously -- by an average of 24.8\% on these difficult instances.

arXiv:2503.13538공식 코드 · Papers with Code

From Demonstrations to Rewards: Alignment Without Explicit Human Preferences

One of the challenges of aligning large models with human preferences lies in both the data requirements and the technical complexities of current approaches. Predominant methods, such as RLHF, involve multiple steps, each demanding distinct types of data, including demonstration data and preference data. In RLHF, human preferences are typically modeled through a reward model, which serves as a proxy to guide policy learning during the reinforcement learning stage, ultimately producing a policy aligned with human preferences. However, in this paper, we propose a fresh perspective on learning alignment based on inverse reinforcement learning principles, where the optimal policy is still derived from reward maximization. However, instead of relying on preference data, we directly learn the reward model from demonstration data. This new formulation offers the flexibility to be applied even when only demonstration data is available, a capability that current RLHF methods lack, and it also shows that demonstration data offers more utility than what conventional wisdom suggests. Our extensive evaluation, based on public reward benchmark, HuggingFace Open LLM Leaderboard and MT-Bench, demonstrates that our approach compares favorably to state-of-the-art methods that rely solely on demonstration data.

arXiv:2503.12283공식 코드 · Papers with Code

Towards Optimal Offline Reinforcement Learning

We study offline reinforcement learning problems with a long-run average reward objective. The state-action pairs generated by any fixed behavioral policy thus follow a Markov chain, and the {\em empirical} state-action-next-state distribution satisfies a large deviations principle. We use the rate function of this large deviations principle to construct an uncertainty set for the unknown {\em true} state-action-next-state distribution. We also construct a distribution shift transformation that maps any distribution in this uncertainty set to a state-action-next-state distribution of the Markov chain generated by a fixed evaluation policy, which may differ from the unknown behavioral policy. We prove that the worst-case average reward of the evaluation policy with respect to all distributions in the shifted uncertainty set provides, in a rigorous statistical sense, the least conservative estimator for the average reward under the unknown true distribution. This guarantee is available even if one has only access to one single trajectory of serially correlated state-action pairs. The emerging robust optimization problem can be viewed as a robust Markov decision process with a non-rectangular uncertainty set. We adapt an efficient policy gradient algorithm to solve this problem. Numerical experiments show that our methods compare favorably against state-of-the-art methods.

arXiv:2503.09622공식 코드 · Papers with Code

Dynamics-Invariant Quadrotor Control using Scale-Aware Deep Reinforcement Learning

Due to dynamic variations such as changing payload, aerodynamic disturbances, and varying platforms, a robust solution for quadrotor trajectory tracking remains challenging. To address these challenges, we present a deep reinforcement learning (DRL) framework that achieves physical dynamics invariance by directly optimizing force/torque inputs, eliminating the need for traditional intermediate control layers. Our architecture integrates a temporal trajectory encoder, which processes finite-horizon reference positions/velocities, with a latent dynamics encoder trained on historical state-action pairs to model platform-specific characteristics. Additionally, we introduce scale-aware dynamics randomization parameterized by the quadrotor's arm length, enabling our approach to maintain stability across drones spanning from 30g to 2.1kg and outperform other DRL baselines by 85% in tracking accuracy. Extensive real-world validation of our approach on the Crazyflie 2.1 quadrotor, encompassing over 200 flights, demonstrates robust adaptation to wind, ground effects, and swinging payloads while achieving less than 0.05m RMSE at speeds up to 2.0 m/s. This work introduces a universal quadrotor control paradigm that compensates for dynamic discrepancies across varied conditions and scales, paving the way for more resilient aerial systems.

arXiv:2503.07981공식 코드 · Papers with Code

Regulatory DNA sequence Design with Reinforcement Learning

Cis-regulatory elements (CREs), such as promoters and enhancers, are relatively short DNA sequences that directly regulate gene expression. The fitness of CREs, measured by their ability to modulate gene expression, highly depends on the nucleotide sequences, especially specific motifs known as transcription factor binding sites (TFBSs). Designing high-fitness CREs is crucial for therapeutic and bioengineering applications. Current CRE design methods are limited by two major drawbacks: (1) they typically rely on iterative optimization strategies that modify existing sequences and are prone to local optima, and (2) they lack the guidance of biological prior knowledge in sequence optimization. In this paper, we address these limitations by proposing a generative approach that leverages reinforcement learning (RL) to fine-tune a pre-trained autoregressive (AR) model. Our method incorporates data-driven biological priors by deriving computational inference-based rewards that simulate the addition of activator TFBSs and removal of repressor TFBSs, which are then integrated into the RL process. We evaluate our method on promoter design tasks in two yeast media conditions and enhancer design tasks for three human cell types, demonstrating its ability to generate high-fitness CREs while maintaining sequence diversity. The code is available at https://github.com/yangzhao1230/TACO.

arXiv:2503.08388공식 코드 · Papers with Code

V-Max: A Reinforcement Learning Framework for Autonomous Driving

Learning-based decision-making has the potential to enable generalizable Autonomous Driving (AD) policies, reducing the engineering overhead of rule-based approaches. Imitation Learning (IL) remains the dominant paradigm, benefiting from large-scale human demonstration datasets, but it suffers from inherent limitations such as distribution shift and imitation gaps. Reinforcement Learning (RL) presents a promising alternative, yet its adoption in AD remains limited due to the lack of standardized and efficient research frameworks. To this end, we introduce V-Max, an open research framework providing all the necessary tools to make RL practical for AD. V-Max is built on Waymax, a hardware-accelerated AD simulator designed for large-scale experimentation. We extend it using ScenarioNet's approach, enabling the fast simulation of diverse AD datasets.

arXiv:2503.09501공식 코드 · Papers with Code

ReMA: Learning to Meta-think for LLMs with Multi-Agent Reinforcement Learning

Recent research on Reasoning of Large Language Models (LLMs) has sought to further enhance their performance by integrating meta-thinking -- enabling models to monitor, evaluate, and control their reasoning processes for more adaptive and effective problem-solving. However, current single-agent work lacks a specialized design for acquiring meta-thinking, resulting in low efficacy. To address this challenge, we introduce Reinforced Meta-thinking Agents (ReMA), a novel framework that leverages Multi-Agent Reinforcement Learning (MARL) to elicit meta-thinking behaviors, encouraging LLMs to think about thinking. ReMA decouples the reasoning process into two hierarchical agents: a high-level meta-thinking agent responsible for generating strategic oversight and plans, and a low-level reasoning agent for detailed executions. Through iterative reinforcement learning with aligned objectives, these agents explore and learn collaboration, leading to improved generalization and robustness. Empirical results from single-turn experiments demonstrate that ReMA outperforms single-agent RL baselines on complex reasoning tasks, including competitive-level mathematical benchmarks and LLM-as-a-Judge benchmarks. Additionally, we further extend ReMA to multi-turn interaction settings, leveraging turn-level ratio and parameter sharing to improve efficiency. Comprehensive ablation studies further illustrate the evolving dynamics of each distinct agent, providing valuable insights into how the meta-thinking reasoning process enhances the reasoning capabilities of LLMs. Our code can be found in https://github.com/ziyuwan/ReMA-public

arXiv:2503.05306공식 코드 · Papers with Code

Adversarial Policy Optimization for Offline Preference-based Reinforcement Learning

In this paper, we study offline preference-based reinforcement learning (PbRL), where learning is based on pre-collected preference feedback over pairs of trajectories. While offline PbRL has demonstrated remarkable empirical success, existing theoretical approaches face challenges in ensuring conservatism under uncertainty, requiring computationally intractable confidence set constructions. We address this limitation by proposing Adversarial Preference-based Policy Optimization (APPO), a computationally efficient algorithm for offline PbRL that guarantees sample complexity bounds without relying on explicit confidence sets. By framing PbRL as a two-player game between a policy and a model, our approach enforces conservatism in a tractable manner. Using standard assumptions on function approximation and bounded trajectory concentrability, we derive a sample complexity bound. To our knowledge, APPO is the first offline PbRL algorithm to offer both statistical efficiency and practical applicability. Experimental results on continuous control tasks demonstrate that APPO effectively learns from complex datasets, showing comparable performance with existing state-of-the-art methods.

arXiv:2503.05207공식 코드 · Papers with Code

Policy Constraint by Only Support Constraint for Offline Reinforcement Learning

Offline reinforcement learning (RL) aims to optimize a policy by using pre-collected datasets, to maximize cumulative rewards. However, offline reinforcement learning suffers challenges due to the distributional shift between the learned and behavior policies, leading to errors when computing Q-values for out-of-distribution (OOD) actions. To mitigate this issue, policy constraint methods aim to constrain the learned policy's distribution with the distribution of the behavior policy or confine action selection within the support of the behavior policy. However, current policy constraint methods tend to exhibit excessive conservatism, hindering the policy from further surpassing the behavior policy's performance. In this work, we present Only Support Constraint (OSC) which is derived from maximizing the total probability of learned policy in the support of behavior policy, to address the conservatism of policy constraint. OSC presents a regularization term that only restricts policies to the support without imposing extra constraints on actions within the support. Additionally, to fully harness the performance of the new policy constraints, OSC utilizes a diffusion model to effectively characterize the support of behavior policies. Experimental evaluations across a variety of offline RL benchmarks demonstrate that OSC significantly enhances performance, alleviating the challenges associated with distributional shifts and mitigating conservatism of policy constraints. Code is available at https://github.com/MoreanP/OSC.

arXiv:2503.07347공식 코드 · Papers with Code

DaD: Distilled Reinforcement Learning for Diverse Keypoint Detection

Keypoints are what enable Structure-from-Motion (SfM) systems to scale to thousands of images. However, designing a keypoint detection objective is a non-trivial task, as SfM is non-differentiable. Typically, an auxiliary objective involving a descriptor is optimized. This however induces a dependency on the descriptor, which is undesirable. In this paper we propose a fully self-supervised and descriptor-free objective for keypoint detection, through reinforcement learning. To ensure training does not degenerate, we leverage a balanced top-K sampling strategy. While this already produces competitive models, we find that two qualitatively different types of detectors emerge, which are only able to detect light and dark keypoints respectively. To remedy this, we train a third detector, DaD, that optimizes the Kullback-Leibler divergence of the pointwise maximum of both light and dark detectors. Our approach significantly improve upon SotA across a range of benchmarks. Code and model weights are publicly available at https:github.com/parskatt/dad

arXiv:2503.05132공식 코드 · Papers with Code

R1-Zero's "Aha Moment" in Visual Reasoning on a 2B Non-SFT Model

Recently DeepSeek R1 demonstrated how reinforcement learning with simple rule-based incentives can enable autonomous development of complex reasoning in large language models, characterized by the "aha moment", in which the model manifest self-reflection and increased response length during training. However, attempts to extend this success to multimodal reasoning often failed to reproduce these key characteristics. In this report, we present the first successful replication of these emergent characteristics for multimodal reasoning on only a non-SFT 2B model. Starting with Qwen2-VL-2B and applying reinforcement learning directly on the SAT dataset, our model achieves 59.47% accuracy on CVBench, outperforming the base model by approximately ~30% and exceeding both SFT setting by ~2%. In addition, we share our failed attempts and insights in attempting to achieve R1-like reasoning using RL with instruct models. aiming to shed light on the challenges involved. Our key observations include: (1) applying RL on instruct model often results in trivial reasoning trajectories, and (2) naive length reward are ineffective in eliciting reasoning capabilities. The project code is available at https://github.com/turningpoint-ai/VisualThinker-R1-Zero

arXiv:2503.05905공식 코드 · Papers with Code

Performance Comparisons of Reinforcement Learning Algorithms for Sequential Experimental Design

Recent developments in sequential experimental design look to construct a policy that can efficiently navigate the design space, in a way that maximises the expected information gain. Whilst there is work on achieving tractable policies for experimental design problems, there is significantly less work on obtaining policies that are able to generalise well - i.e. able to give good performance despite a change in the underlying statistical properties of the experiments. Conducting experiments sequentially has recently brought about the use of reinforcement learning, where an agent is trained to navigate the design space to select the most informative designs for experimentation. However, there is still a lack of understanding about the benefits and drawbacks of using certain reinforcement learning algorithms to train these agents. In our work, we investigate several reinforcement learning algorithms and their efficacy in producing agents that take maximally informative design decisions in sequential experimental design scenarios. We find that agent performance is impacted depending on the algorithm used for training, and that particular algorithms, using dropout or ensemble approaches, empirically showcase attractive generalisation properties.

arXiv:2503.06592공식 코드 · Papers with Code

Automated Proof of Polynomial Inequalities via Reinforcement Learning

Polynomial inequality proving is fundamental to many mathematical disciplines and finds wide applications in diverse fields. Current traditional algebraic methods are based on searching for a polynomial positive definite representation over a set of basis. However, these methods are limited by truncation degree. To address this issue, this paper proposes an approach based on reinforcement learning to find a {Krivine-basis} representation for proving polynomial inequalities. Specifically, we formulate the inequality proving problem as a linear programming (LP) problem and encode it as a basis selection problem using reinforcement learning (RL), achieving a non-negative {Krivine basis}. Moreover, a fast multivariate polynomial multiplication method based on Fast Fourier Transform (FFT) is employed to enhance the efficiency of action space search. Furthermore, we have implemented a tool called {APPIRL} (Automated Proof of Polynomial Inequalities via Reinforcement Learning). Experimental evaluation on benchmark problems demonstrates the feasibility and effectiveness of our approach. In addition, {APPIRL} has been successfully applied to solve the maximum stable set problem.

arXiv:2503.02269공식 코드 · Papers with Code

Experience Replay with Random Reshuffling

Experience replay is a key component in reinforcement learning for stabilizing learning and improving sample efficiency. Its typical implementation samples transitions with replacement from a replay buffer. In contrast, in supervised learning with a fixed dataset, it is a common practice to shuffle the dataset every epoch and consume data sequentially, which is called random reshuffling (RR). RR enjoys theoretically better convergence properties and has been shown to outperform with-replacement sampling empirically. To leverage the benefits of RR in reinforcement learning, we propose sampling methods that extend RR to experience replay, both in uniform and prioritized settings. We evaluate our sampling methods on Atari benchmarks, demonstrating their effectiveness in deep reinforcement learning.