PyTorchKR Papers

최신 논문

총 13,741편
태그·기간 등 상세 필터

카테고리 탐색

로그인 후 이 태그 구독

arXiv:2407.14516공식 코드 · Papers with Code

RobocupGym: A challenging continuous control benchmark in Robocup

Reinforcement learning (RL) has progressed substantially over the past decade, with much of this progress being driven by benchmarks. Many benchmarks are focused on video or board games, and a large number of robotics benchmarks lack diversity and real-world applicability. In this paper, we aim to simplify the process of applying reinforcement learning in the 3D simulation league of Robocup, a robotic football competition. To this end, we introduce a Robocup-based RL environment based on the open source rcssserver3d soccer server, simple pre-defined tasks, and integration with a popular RL library, Stable Baselines 3. Our environment enables the creation of high-dimensional continuous control tasks within a robotics football simulation. In each task, an RL agent controls a simulated Nao robot, and can interact with the ball or other agents. We open-source our environment and training code at https://github.com/Michael-Beukman/RobocupGym.

arXiv:2407.15820공식 코드 · Papers with Code

On shallow planning under partial observability

Formulating a real-world problem under the Reinforcement Learning framework involves non-trivial design choices, such as selecting a discount factor for the learning objective (discounted cumulative rewards), which articulates the planning horizon of the agent. This work investigates the impact of the discount factor on the biasvariance trade-off given structural parameters of the underlying Markov Decision Process. Our results support the idea that a shorter planning horizon might be beneficial, especially under partial observability.

arXiv:2407.15626공식 코드 · Papers with Code

Reinforcement Learning Meets Visual Odometry

Visual Odometry (VO) is essential to downstream mobile robotics and augmented/virtual reality tasks. Despite recent advances, existing VO methods still rely on heuristic design choices that require several weeks of hyperparameter tuning by human experts, hindering generalizability and robustness. We address these challenges by reframing VO as a sequential decision-making task and applying Reinforcement Learning (RL) to adapt the VO process dynamically. Our approach introduces a neural network, operating as an agent within the VO pipeline, to make decisions such as keyframe and grid-size selection based on real-time conditions. Our method minimizes reliance on heuristic choices using a reward function based on pose error, runtime, and other metrics to guide the system. Our RL framework treats the VO system and the image sequence as an environment, with the agent receiving observations from keypoints, map statistics, and prior poses. Experimental results using classical VO methods and public benchmarks demonstrate improvements in accuracy and robustness, validating the generalizability of our RL-enhanced VO approach to different scenarios. We believe this paradigm shift advances VO technology by eliminating the need for time-intensive parameter tuning of heuristics.

arXiv:2407.15616공식 코드 · Papers with Code

Sustainable broadcasting in Blockchain Networks with Reinforcement Learning

Recent estimates put the carbon footprint of Bitcoin and Ethereum at an average of 64 and 26 million tonnes of CO2 per year, respectively. To address this growing problem, several possible approaches have been proposed in the literature: creating alternative blockchain consensus mechanisms, applying redundancy reduction techniques, utilizing renewable energy sources, and employing energy-efficient devices, etc. In this paper, we follow the second avenue and propose an efficient approach based on reinforcement learning that improves the block broadcasting scheme in blockchain networks. The analysis and experimental results confirmed that the proposed improvement of the block propagation scheme could cleverly handle network dynamics and achieve better results than the default approach. Additionally, our technical integration of the simulator and developed RL environment can be used as a complete solution for further study of new schemes and protocols that use RL or other ML techniques.

arXiv:2407.14872

Adapt2Reward: Adapting Video-Language Models to Generalizable Robotic Rewards via Failure Prompts

For a general-purpose robot to operate in reality, executing a broad range of instructions across various environments is imperative. Central to the reinforcement learning and planning for such robotic agents is a generalizable reward function. Recent advances in vision-language models, such as CLIP, have shown remarkable performance in the domain of deep learning, paving the way for open-domain visual recognition. However, collecting data on robots executing various language instructions across multiple environments remains a challenge. This paper aims to transfer video-language models with robust generalization into a generalizable language-conditioned reward function, only utilizing robot video data from a minimal amount of tasks in a singular environment. Unlike common robotic datasets used for training reward functions, human video-language datasets rarely contain trivial failure videos. To enhance the model's ability to distinguish between successful and failed robot executions, we cluster failure video features to enable the model to identify patterns within. For each cluster, we integrate a newly trained failure prompt into the text encoder to represent the corresponding failure mode. Our language-conditioned reward function shows outstanding generalization to new environments and new instructions for robot planning and reinforcement learning.

arXiv:2407.14775

Phase Re-service in Reinforcement Learning Traffic Signal Control

This article proposes a novel approach to traffic signal control that combines phase re-service with reinforcement learning (RL). The RL agent directly determines the duration of the next phase in a pre-defined sequence. Before the RL agent's decision is executed, we use the shock wave theory to estimate queue expansion at the designated movement allowed for re-service and decide if phase re-service is necessary. If necessary, a temporary phase re-service is inserted before the next regular phase. We formulate the RL problem as a semi-Markov decision process (SMDP) and solve it with proximal policy optimization (PPO). We conducted a series of experiments that showed significant improvements thanks to the introduction of phase re-service. Vehicle delays are reduced by up to 29.95% of the average and up to 59.21% of the standard deviation. The number of stops is reduced by 26.05% on average with 45.77% less standard deviation.

arXiv:2407.15168

Mitigating Deep Reinforcement Learning Backdoors in the Neural Activation Space

This paper investigates the threat of backdoors in Deep Reinforcement Learning (DRL) agent policies and proposes a novel method for their detection at runtime. Our study focuses on elusive in-distribution backdoor triggers. Such triggers are designed to induce a deviation in the behaviour of a backdoored agent while blending into the expected data distribution to evade detection. Through experiments conducted in the Atari Breakout environment, we demonstrate the limitations of current sanitisation methods when faced with such triggers and investigate why they present a challenging defence problem. We then evaluate the hypothesis that backdoor triggers might be easier to detect in the neural activation space of the DRL agent's policy network. Our statistical analysis shows that indeed the activation patterns in the agent's policy network are distinct in the presence of a trigger, regardless of how well the trigger is concealed in the environment. Based on this, we propose a new defence approach that uses a classifier trained on clean environment samples and detects abnormal activations. Our results show that even lightweight classifiers can effectively prevent malicious actions with considerable accuracy, indicating the potential of this research direction even against sophisticated adversaries.

arXiv:2407.14262

Hyperparameter Optimization for Driving Strategies Based on Reinforcement Learning

This paper focuses on hyperparameter optimization for autonomous driving strategies based on Reinforcement Learning. We provide a detailed description of training the RL agent in a simulation environment. Subsequently, we employ Efficient Global Optimization algorithm that uses Gaussian Process fitting for hyperparameter optimization in RL. Before this optimization phase, Gaussian process interpolation is applied to fit the surrogate model, for which the hyperparameter set is generated using Latin hypercube sampling. To accelerate the evaluation, parallelization techniques are employed. Following the hyperparameter optimization procedure, a set of hyperparameters is identified, resulting in a noteworthy enhancement in overall driving performance. There is a substantial increase of 4\% when compared to existing manually tuned parameters and the hyperparameters discovered during the initialization process using Latin hypercube sampling. After the optimization, we analyze the obtained results thoroughly and conduct a sensitivity analysis to assess the robustness and generalization capabilities of the learned autonomous driving strategies. The findings from this study contribute to the advancement of Gaussian process based Bayesian optimization to optimize the hyperparameters for autonomous driving in RL, providing valuable insights for the development of efficient and reliable autonomous driving systems.

arXiv:2407.14175

On Policy Evaluation Algorithms in Distributional Reinforcement Learning

We introduce a novel class of algorithms to efficiently approximate the unknown return distributions in policy evaluation problems from distributional reinforcement learning (DRL). The proposed distributional dynamic programming algorithms are suitable for underlying Markov decision processes (MDPs) having an arbitrary probabilistic reward mechanism, including continuous reward distributions with unbounded support being potentially heavy-tailed. For a plain instance of our proposed class of algorithms we prove error bounds, both within Wasserstein and Kolmogorov--Smirnov distances. Furthermore, for return distributions having probability density functions the algorithms yield approximations for these densities; error bounds are given within supremum norm. We introduce the concept of quantile-spline discretizations to come up with algorithms showing promising results in simulation experiments. While the performance of our algorithms can rigorously be analysed they can be seen as universal black box algorithms applicable to a large class of MDPs. We also derive new properties of probability metrics commonly used in DRL on which our quantitative analysis is based.

arXiv:2407.11719공식 코드 · Papers with Code

Pareto local search for a multi-objective demand response problem in residential areas with heat pumps and electric vehicles

In future energy systems characterized by significant shares of fluctuating renewable energy sources, there is a need for a fundamental change in electricity consumption. The energy system requires the ability to adapt to the intermittent electricity generation of renewable energy sources. This can be achieved by integrating flexible electrical loads, such as electric heating devices and electric vehicles, in combination with efficient control methods. In this paper, we introduce the Pareto local search method PALSS with heuristic search operations to solve the multi-objective optimization problem of a residential area with different types of flexible loads. PALSS shifts the flexible electricity load with the objective of minimizing the electricity cost and peak load while maintaining the inhabitants' comfort in favorable ranges. Further, we include reinforcement learning into the heuristic search operations in the approach RELAPALSS and use the dichotomous method for obtaining all Pareto-optimal solutions of the multi-objective optimization problem with conflicting goals. The methods are evaluated in simulations with different configurations of the residential area. The results show that PALSS and RELAPALSS strongly outperform the two multi-objective evolutionary algorithms NSGA-II and SPEA-II from the literature and the conventional control approach. The inclusion of reinforcement learning in RELAPALSS leads to additional improvements. Our study reveals the need for multi-objective optimization methods to utilize renewable energy sources in residential areas.

arXiv:2407.12794

Learned Graph Rewriting with Equality Saturation: A New Paradigm in Relational Query Rewrite and Beyond

Query rewrite systems perform graph substitutions using rewrite rules to generate optimal SQL query plans. Rewriting logical and physical relational query plans is proven to be an NP-hard sequential decision-making problem with a search space exponential in the number of rewrite rules. In this paper, we address the query rewrite problem by interleaving Equality Saturation and Graph Reinforcement Learning (RL). The proposed system, Aurora, rewrites relational queries by guiding Equality Saturation, a method from compiler literature to perform non-destructive graph rewriting, with a novel RL agent that embeds both the spatial structure of the query graph as well as the temporal dimension associated with the sequential construction of query plans. Our results show Graph Reinforcement Learning for non-destructive graph rewriting yields SQL plans orders of magnitude faster than existing equality saturation solvers, while also achieving competitive results against mainstream query optimisers.

arXiv:2407.11047

An open source Multi-Agent Deep Reinforcement Learning Routing Simulator for satellite networks

This paper introduces an open source simulator for packet routing in Low Earth Orbit Satellite Constellations (LSatCs) considering the dynamic system uncertainties. The simulator, implemented in Python, supports traditional Dijkstra's based routing as well as more advanced learning solutions, specifically Q-Routing and Multi-Agent Deep Reinforcement Learning (MA-DRL) from our previous work. It uses an event-based approach with the SimPy module to accurately simulate packet creation, routing and queuing, providing real-time tracking of queues and latency. The simulator is highly configurable, allowing adjustments in routing policies, traffic, ground and space layer topologies, communication parameters, and learning hyperparameters. Key features include the ability to visualize system motion and track packet paths. Results highlight significant improvements in end-to-end (E2E) latency using Reinforcement Learning (RL)-based routing policies compared to traditional methods. The source code, the documentation and a Jupyter notebook with post-processing results and analysis are available on GitHub.

arXiv:2407.13755

Random Latent Exploration for Deep Reinforcement Learning

The ability to efficiently explore high-dimensional state spaces is essential for the practical success of deep Reinforcement Learning (RL). This paper introduces a new exploration technique called Random Latent Exploration (RLE), that combines the strengths of bonus-based and noise-based (two popular approaches for effective exploration in deep RL) exploration strategies. RLE leverages the idea of perturbing rewards by adding structured random rewards to the original task rewards in certain (random) states of the environment, to encourage the agent to explore the environment during training. RLE is straightforward to implement and performs well in practice. To demonstrate the practical effectiveness of RLE, we evaluate it on the challenging Atari and IsaacGym benchmarks and show that RLE exhibits higher overall scores across all the tasks than other approaches.

arXiv:2407.13743

Optimistic Q-learning for average reward and episodic reinforcement learning

We present an optimistic Q-learning algorithm for regret minimization in average reward reinforcement learning under an additional assumption on the underlying MDP that for all policies, the time to visit some frequent state $s_0$ is finite and upper bounded by $H$, either in expectation or with constant probability. Our setting strictly generalizes the episodic setting and is significantly less restrictive than the assumption of bounded hitting time \textit{for all states} made by most previous literature on model-free algorithms in average reward settings. We demonstrate a regret bound of $\tilde{O}(H^5 S\sqrt{AT})$, where $S$ and $A$ are the numbers of states and actions, and $T$ is the horizon. A key technical novelty of our work is the introduction of an $\overline{L}$ operator defined as $\overline{L} v = \frac{1}{H} \sum_{h=1}^H L^h v$ where $L$ denotes the Bellman operator. Under the given assumption, we show that the $\overline{L}$ operator has a strict contraction (in span) even in the average-reward setting where the discount factor is $1$. Our algorithm design uses ideas from episodic Q-learning to estimate and apply this operator iteratively. Thus, we provide a unified view of regret minimization in episodic and non-episodic settings, which may be of independent interest.

arXiv:2407.13518

Model-based Policy Optimization using Symbolic World Model

The application of learning-based control methods in robotics presents significant challenges. One is that model-free reinforcement learning algorithms use observation data with low sample efficiency. To address this challenge, a prevalent approach is model-based reinforcement learning, which involves employing an environment dynamics model. We suggest approximating transition dynamics with symbolic expressions, which are generated via symbolic regression. Approximation of a mechanical system with a symbolic model has fewer parameters than approximation with neural networks, which can potentially lead to higher accuracy and quality of extrapolation. We use a symbolic dynamics model to generate trajectories in model-based policy optimization to improve the sample efficiency of the learning algorithm. We evaluate our approach across various tasks within simulated environments. Our method demonstrates superior sample efficiency in these tasks compared to model-free and model-based baseline methods.

arXiv:2407.13466

LIMT: Language-Informed Multi-Task Visual World Models

Most recent successes in robot reinforcement learning involve learning a specialized single-task agent. However, robots capable of performing multiple tasks can be much more valuable in real-world applications. Multi-task reinforcement learning can be very challenging due to the increased sample complexity and the potentially conflicting task objectives. Previous work on this topic is dominated by model-free approaches. The latter can be very sample inefficient even when learning specialized single-task agents. In this work, we focus on model-based multi-task reinforcement learning. We propose a method for learning multi-task visual world models, leveraging pre-trained language models to extract semantically meaningful task representations. These representations are used by the world model and policy to reason about task similarity in dynamics and behavior. Our results highlight the benefits of using language-driven task representations for world models and a clear advantage of model-based multi-task learning over the more common model-free paradigm.

arXiv:2407.13279

Analyzing and Bridging the Gap between Maximizing Total Reward and Discounted Reward in Deep Reinforcement Learning

In deep reinforcement learning applications, maximizing discounted reward is often employed instead of maximizing total reward to ensure the convergence and stability of algorithms, even though the performance metric for evaluating the policy remains the total reward. However, the optimal policies corresponding to these two objectives may not always be consistent. To address this issue, we analyzed the suboptimality of the policy obtained through maximizing discounted reward in relation to the policy that maximizes total reward and identified the influence of hyperparameters. Additionally, we proposed sufficient conditions for aligning the optimal policies of these two objectives under various settings. The primary contributions are as follows: We theoretically analyzed the factors influencing performance when using discounted reward as a proxy for total reward, thereby enhancing the theoretical understanding of this scenario. Furthermore, we developed methods to align the optimal policies of the two objectives in certain situations, which can improve the performance of reinforcement learning algorithms.

arXiv:2407.13221공식 코드 · Papers with Code

Multimodal Label Relevance Ranking via Reinforcement Learning

Conventional multi-label recognition methods often focus on label confidence, frequently overlooking the pivotal role of partial order relations consistent with human preference. To resolve these issues, we introduce a novel method for multimodal label relevance ranking, named Label Relevance Ranking with Proximal Policy Optimization (LR\textsuperscript{2}PPO), which effectively discerns partial order relations among labels. LR\textsuperscript{2}PPO first utilizes partial order pairs in the target domain to train a reward model, which aims to capture human preference intrinsic to the specific scenario. Furthermore, we meticulously design state representation and a policy loss tailored for ranking tasks, enabling LR\textsuperscript{2}PPO to boost the performance of label relevance ranking model and largely reduce the requirement of partial order annotation for transferring to new scenes. To assist in the evaluation of our approach and similar methods, we further propose a novel benchmark dataset, LRMovieNet, featuring multimodal labels and their corresponding partial order data. Extensive experiments demonstrate that our LR\textsuperscript{2}PPO algorithm achieves state-of-the-art performance, proving its effectiveness in addressing the multimodal label relevance ranking problem. Codes and the proposed LRMovieNet dataset are publicly available at \url{https://github.com/ChazzyGordon/LR2PPO}.

arXiv:2407.12894

Maintenance Strategies for Sewer Pipes with Multi-State Degradation and Deep Reinforcement Learning

Large-scale infrastructure systems are crucial for societal welfare, and their effective management requires strategic forecasting and intervention methods that account for various complexities. Our study addresses two challenges within the Prognostics and Health Management (PHM) framework applied to sewer assets: modeling pipe degradation across severity levels and developing effective maintenance policies. We employ Multi-State Degradation Models (MSDM) to represent the stochastic degradation process in sewer pipes and use Deep Reinforcement Learning (DRL) to devise maintenance strategies. A case study of a Dutch sewer network exemplifies our methodology. Our findings demonstrate the model's effectiveness in generating intelligent, cost-saving maintenance strategies that surpass heuristics. It adapts its management strategy based on the pipe's age, opting for a passive approach for newer pipes and transitioning to active strategies for older ones to prevent failures and reduce costs. This research highlights DRL's potential in optimizing maintenance policies. Future research will aim improve the model by incorporating partial observability, exploring various reinforcement learning algorithms, and extending this methodology to comprehensive infrastructure management.

arXiv:2407.13320

Deep Reinforcement Learning for Multi-Objective Optimization: Enhancing Wind Turbine Energy Generation while Mitigating Noise Emissions

We develop a torque-pitch control framework using deep reinforcement learning for wind turbines to optimize the generation of wind turbine energy while minimizing operational noise. We employ a double deep Q-learning, coupled to a blade element momentum solver, to enable precise control over wind turbine parameters. In addition to the blade element momentum, we use the wind turbine acoustic model of Brooks Pope and Marcolini. Through training with simple winds, the agent learns optimal control policies that allow efficient control for complex turbulent winds. Our experiments demonstrate that the reinforcement learning is able to find optima at the Pareto front, when maximizing energy while minimizing noise. In addition, the adaptability of the reinforcement learning agent to changing turbulent wind conditions, underscores its efficacy for real-world applications. We validate the methodology using a SWT2.3-93 wind turbine with a rated power of 2.3 MW. We compare the reinforcement learning control to classic controls to show that they are comparable when not taking into account noise emissions. When including a maximum limit of 45 dB to the noise produced (100 meters downwind of the turbine), the extracted yearly energy decreases by 22%. The methodology is flexible and allows for easy tuning of the objectives and constraints through the reward definitions, resulting in a flexible multi-objective optimization framework for wind turbine control. Overall, our findings highlight the potential of RL-based control strategies to improve wind turbine efficiency while mitigating noise pollution, thus advancing sustainable energy generation technologies