PyTorchKR Papers

최신 논문

총 1,371편
태그·기간 등 상세 필터

카테고리 탐색

로그인 후 이 태그 구독

arXiv:2405.11982공식 코드 · Papers with Code

Robust Deep Reinforcement Learning with Adaptive Adversarial Perturbations in Action Space

Deep reinforcement learning (DRL) algorithms can suffer from modeling errors between the simulation and the real world. Many studies use adversarial learning to generate perturbation during training process to model the discrepancy and improve the robustness of DRL. However, most of these approaches use a fixed parameter to control the intensity of the adversarial perturbation, which can lead to a trade-off between average performance and robustness. In fact, finding the optimal parameter of the perturbation is challenging, as excessive perturbations may destabilize training and compromise agent performance, while insufficient perturbations may not impart enough information to enhance robustness. To keep the training stable while improving robustness, we propose a simple but effective method, namely, Adaptive Adversarial Perturbation (A2P), which can dynamically select appropriate adversarial perturbations for each sample. Specifically, we propose an adaptive adversarial coefficient framework to adjust the effect of the adversarial perturbation during training. By designing a metric for the current intensity of the perturbation, our method can calculate the suitable perturbation levels based on the current relative performance. The appealing feature of our method is that it is simple to deploy in real-world applications and does not require accessing the simulator in advance. The experiments in MuJoCo show that our method can improve the training stability and learn a robust policy when migrated to different test environments. The code is available at https://github.com/Lqm00/A2P-SAC.

arXiv:2405.11432공식 코드 · Papers with Code

On Robust Reinforcement Learning with Lipschitz-Bounded Policy Networks

This paper presents a study of robust policy networks in deep reinforcement learning. We investigate the benefits of policy parameterizations that naturally satisfy constraints on their Lipschitz bound, analyzing their empirical performance and robustness on two representative problems: pendulum swing-up and Atari Pong. We illustrate that policy networks with smaller Lipschitz bounds are more robust to disturbances, random noise, and targeted adversarial attacks than unconstrained policies composed of vanilla multi-layer perceptrons or convolutional neural networks. However, the structure of the Lipschitz layer is important. We find that the widely-used method of spectral normalization is too conservative and severely impacts clean performance, whereas more expressive Lipschitz layers such as the recently-proposed Sandwich layer can achieve improved robustness without sacrificing clean performance.

arXiv:2405.04342공식 코드 · Papers with Code

The Curse of Diversity in Ensemble-Based Exploration

We uncover a surprising phenomenon in deep reinforcement learning: training a diverse ensemble of data-sharing agents -- a well-established exploration strategy -- can significantly impair the performance of the individual ensemble members when compared to standard single-agent training. Through careful analysis, we attribute the degradation in performance to the low proportion of self-generated data in the shared training data for each ensemble member, as well as the inefficiency of the individual ensemble members to learn from such highly off-policy data. We thus name this phenomenon the curse of diversity. We find that several intuitive solutions -- such as a larger replay buffer or a smaller ensemble size -- either fail to consistently mitigate the performance loss or undermine the advantages of ensembling. Finally, we demonstrate the potential of representation learning to counteract the curse of diversity with a novel method named Cross-Ensemble Representation Learning (CERL) in both discrete and continuous control domains. Our work offers valuable insights into an unexpected pitfall in ensemble-based exploration and raises important caveats for future applications of similar approaches.

arXiv:2405.02676공식 코드 · Papers with Code

Hand-Object Interaction Controller (HOIC): Deep Reinforcement Learning for Reconstructing Interactions with Physics

Hand manipulating objects is an important interaction motion in our daily activities. We faithfully reconstruct this motion with a single RGBD camera by a novel deep reinforcement learning method to leverage physics. Firstly, we propose object compensation control which establishes direct object control to make the network training more stable. Meanwhile, by leveraging the compensation force and torque, we seamlessly upgrade the simple point contact model to a more physical-plausible surface contact model, further improving the reconstruction accuracy and physical correctness. Experiments indicate that without involving any heuristic physical rules, this work still successfully involves physics in the reconstruction of hand-object interactions which are complex motions hard to imitate with deep reinforcement learning. Our code and data are available at https://github.com/hu-hy17/HOIC.

arXiv:2405.02481공식 코드 · Papers with Code

Proximal Curriculum with Task Correlations for Deep Reinforcement Learning

Curriculum design for reinforcement learning (RL) can speed up an agent's learning process and help it learn to perform well on complex tasks. However, existing techniques typically require domain-specific hyperparameter tuning, involve expensive optimization procedures for task selection, or are suitable only for specific learning objectives. In this work, we consider curriculum design in contextual multi-task settings where the agent's final performance is measured w.r.t. a target distribution over complex tasks. We base our curriculum design on the Zone of Proximal Development concept, which has proven to be effective in accelerating the learning process of RL agents for uniform distribution over all tasks. We propose a novel curriculum, ProCuRL-Target, that effectively balances the need for selecting tasks that are not too difficult for the agent while progressing the agent's learning toward the target distribution via leveraging task correlations. We theoretically justify the task selection strategy of ProCuRL-Target by analyzing a simple learning setting with REINFORCE learner model. Our experimental results across various domains with challenging target task distributions affirm the effectiveness of our curriculum strategy over state-of-the-art baselines in accelerating the training process of deep RL agents.

arXiv:2405.03064공식 코드 · Papers with Code

RICE: Breaking Through the Training Bottlenecks of Reinforcement Learning with Explanation

Deep reinforcement learning (DRL) is playing an increasingly important role in real-world applications. However, obtaining an optimally performing DRL agent for complex tasks, especially with sparse rewards, remains a significant challenge. The training of a DRL agent can be often trapped in a bottleneck without further progress. In this paper, we propose RICE, an innovative refining scheme for reinforcement learning that incorporates explanation methods to break through the training bottlenecks. The high-level idea of RICE is to construct a new initial state distribution that combines both the default initial states and critical states identified through explanation methods, thereby encouraging the agent to explore from the mixed initial states. Through careful design, we can theoretically guarantee that our refining scheme has a tighter sub-optimality bound. We evaluate RICE in various popular RL environments and real-world applications. The results demonstrate that RICE significantly outperforms existing refining schemes in enhancing agent performance.

arXiv:2405.01134공식 코드 · Papers with Code

Leveraging Procedural Generation for Learning Autonomous Peg-in-Hole Assembly in Space

The ability to autonomously assemble structures is crucial for the development of future space infrastructure. However, the unpredictable conditions of space pose significant challenges for robotic systems, necessitating the development of advanced learning techniques to enable autonomous assembly. In this study, we present a novel approach for learning autonomous peg-in-hole assembly in the context of space robotics. Our focus is on enhancing the generalization and adaptability of autonomous systems through deep reinforcement learning. By integrating procedural generation and domain randomization, we train agents in a highly parallelized simulation environment across a spectrum of diverse scenarios with the aim of acquiring a robust policy. The proposed approach is evaluated using three distinct reinforcement learning algorithms to investigate the trade-offs among various paradigms. We demonstrate the adaptability of our agents to novel scenarios and assembly sequences while emphasizing the potential of leveraging advanced simulation techniques for robot learning in space. Our findings set the stage for future advancements in intelligent robotic systems capable of supporting ambitious space missions and infrastructure development beyond Earth.

arXiv:2404.17673공식 코드 · Papers with Code

Learning Manipulation Tasks in Dynamic and Shared 3D Spaces

Automating the segregation process is a need for every sector experiencing a high volume of materials handling, repetitive and exhaustive operations, in addition to risky exposures. Learning automated pick-and-place operations can be efficiently done by introducing collaborative autonomous systems (e.g. manipulators) in the workplace and among human operators. In this paper, we propose a deep reinforcement learning strategy to learn the place task of multi-categorical items from a shared workspace between dual-manipulators and to multi-goal destinations, assuming the pick has been already completed. The learning strategy leverages first a stochastic actor-critic framework to train an agent's policy network, and second, a dynamic 3D Gym environment where both static and dynamic obstacles (e.g. human factors and robot mate) constitute the state space of a Markov decision process. Learning is conducted in a Gazebo simulator and experiments show an increase in cumulative reward function for the agent further away from human factors. Future investigations will be conducted to enhance the task performance for both agents simultaneously.

arXiv:2404.18326공식 코드 · Papers with Code

SAFE-RL: Saliency-Aware Counterfactual Explainer for Deep Reinforcement Learning Policies

While Deep Reinforcement Learning (DRL) has emerged as a promising solution for intricate control tasks, the lack of explainability of the learned policies impedes its uptake in safety-critical applications, such as automated driving systems (ADS). Counterfactual (CF) explanations have recently gained prominence for their ability to interpret black-box Deep Learning (DL) models. CF examples are associated with minimal changes in the input, resulting in a complementary output by the DL model. Finding such alternations, particularly for high-dimensional visual inputs, poses significant challenges. Besides, the temporal dependency introduced by the reliance of the DRL agent action on a history of past state observations further complicates the generation of CF examples. To address these challenges, we propose using a saliency map to identify the most influential input pixels across the sequence of past observed states by the agent. Then, we feed this map to a deep generative model, enabling the generation of plausible CFs with constrained modifications centred on the salient regions. We evaluate the effectiveness of our framework in diverse domains, including ADS, Atari Pong, Pacman and space-invaders games, using traditional performance metrics such as validity, proximity and sparsity. Experimental results demonstrate that this framework generates more informative and plausible CFs than the state-of-the-art for a wide range of environments and DRL agents. In order to foster research in this area, we have made our datasets and codes publicly available at https://github.com/Amir-Samadi/SAFE-RL.

arXiv:2404.18922공식 코드 · Papers with Code

DPO Meets PPO: Reinforced Token Optimization for RLHF

In the classical Reinforcement Learning from Human Feedback (RLHF) framework, Proximal Policy Optimization (PPO) is employed to learn from sparse, sentence-level rewards -- a challenging scenario in traditional deep reinforcement learning. Despite the great successes of PPO in the alignment of large language models, its open-source implementation is still largely sub-optimal. To address these issues, we introduce a framework that models RLHF problems as a Markov decision process (MDP), enabling the capture of fine-grained token-wise information. Under this framework, we introduce an algorithm Reinforced Token Optimization (\texttt{RTO}), which learns the token-wise reward function from preference data and performs policy optimization based on this learned token-wise reward signal. Theoretically, \texttt{RTO} is proven to have the capability of finding the near-optimal policy sample-efficiently. For its practical implementation, \texttt{RTO} innovatively integrates Direct Preference Optimization (DPO) and PPO. DPO, originally derived from sparse sentence rewards, surprisingly provides us with a token-wise characterization of response quality, which is seamlessly incorporated into our subsequent PPO training stage. Extensive experiments demonstrate that \texttt{RTO} performs better than PPO and other direct preference learning algorithms. In particular, RTO outperforms PPO by 7.5 points on the AlpacaEval 2 benchmark and by 4.1 points on Arena-Hard. Our code and models are available at \href{https://github.com/zkshan2002/RTO}{https://github.com/zkshan2002/RTO}.

arXiv:2404.18713공식 코드 · Papers with Code

Task and Domain Adaptive Reinforcement Learning for Robot Control

Deep reinforcement learning (DRL) has shown remarkable success in simulation domains, yet its application in designing robot controllers remains limited, due to its single-task orientation and insufficient adaptability to environmental changes. To overcome these limitations, we present a novel adaptive agent that leverages transfer learning techniques to dynamically adapt policy in response to different tasks and environmental conditions. The approach is validated through the blimp control challenge, where multitasking capabilities and environmental adaptability are essential. The agent is trained using a custom, highly parallelized simulator built on IsaacGym. We perform zero-shot transfer to fly the blimp in the real world to solve various tasks. We share our code at https://github.com/robot-perception-group/adaptive_agent.

arXiv:2404.16388공식 코드 · Papers with Code

SwarmRL: Building the Future of Smart Active Systems

This work introduces SwarmRL, a Python package designed to study intelligent active particles. SwarmRL provides an easy-to-use interface for developing models to control microscopic colloids using classical control and deep reinforcement learning approaches. These models may be deployed in simulations or real-world environments under a common framework. We explain the structure of the software and its key features and demonstrate how it can be used to accelerate research. With SwarmRL, we aim to streamline research into micro-robotic control while bridging the gap between experimental and simulation-driven sciences. SwarmRL is available open-source on GitHub at https://github.com/SwarmRL/SwarmRL.

arXiv:2404.12754공식 코드 · Papers with Code

Adaptive Regularization of Representation Rank as an Implicit Constraint of Bellman Equation

Representation rank is an important concept for understanding the role of Neural Networks (NNs) in Deep Reinforcement learning (DRL), which measures the expressive capacity of value networks. Existing studies focus on unboundedly maximizing this rank; nevertheless, that approach would introduce overly complex models in the learning, thus undermining performance. Hence, fine-tuning representation rank presents a challenging and crucial optimization problem. To address this issue, we find a guiding principle for adaptive control of the representation rank. We employ the Bellman equation as a theoretical foundation and derive an upper bound on the cosine similarity of consecutive state-action pairs representations of value networks. We then leverage this upper bound to propose a novel regularizer, namely BEllman Equation-based automatic rank Regularizer (BEER). This regularizer adaptively regularizes the representation rank, thus improving the DRL agent's performance. We first validate the effectiveness of automatic control of rank on illustrative experiments. Then, we scale up BEER to complex continuous control tasks by combining it with the deterministic policy gradient method. Among 12 challenging DeepMind control tasks, BEER outperforms the baselines by a large margin. Besides, BEER demonstrates significant advantages in Q-value approximation. Our code is available at https://github.com/sweetice/BEER-ICLR2024.

arXiv:2404.08006공식 코드 · Papers with Code

Learning Efficient and Fair Policies for Uncertainty-Aware Collaborative Human-Robot Order Picking

In collaborative human-robot order picking systems, human pickers and Autonomous Mobile Robots (AMRs) travel independently through a warehouse and meet at pick locations where pickers load items onto the AMRs. In this paper, we consider an optimization problem in such systems where we allocate pickers to AMRs in a stochastic environment. We propose a novel multi-objective Deep Reinforcement Learning (DRL) approach to learn effective allocation policies to maximize pick efficiency while also aiming to improve workload fairness amongst human pickers. In our approach, we model the warehouse states using a graph, and define a neural network architecture that captures regional information and effectively extracts representations related to efficiency and workload. We develop a discrete-event simulation model, which we use to train and evaluate the proposed DRL approach. In the experiments, we demonstrate that our approach can find non-dominated policy sets that outline good trade-offs between fairness and efficiency objectives. The trained policies outperform the benchmarks in terms of both efficiency and fairness. Moreover, they show good transferability properties when tested on scenarios with different warehouse sizes. The implementation of the simulation model, proposed approach, and experiments are published.

arXiv:2309.14597공식 코드 · Papers with Code

Policy Optimization in a Noisy Neighborhood: On Return Landscapes in Continuous Control

Deep reinforcement learning agents for continuous control are known to exhibit significant instability in their performance over time. In this work, we provide a fresh perspective on these behaviors by studying the return landscape: the mapping between a policy and a return. We find that popular algorithms traverse noisy neighborhoods of this landscape, in which a single update to the policy parameters leads to a wide range of returns. By taking a distributional view of these returns, we map the landscape, characterizing failure-prone regions of policy space and revealing a hidden dimension of policy quality. We show that the landscape exhibits surprising structure by finding simple paths in parameter space which improve the stability of a policy. To conclude, we develop a distribution-aware procedure which finds such paths, navigating away from noisy neighborhoods in order to improve the robustness of a policy. Taken together, our results provide new insight into the optimization, evaluation, and design of agents.

arXiv:2404.05913공식 코드 · Papers with Code

Deep Reinforcement Learning for Personalized Diagnostic Decision Pathways Using Electronic Health Records: A Comparative Study on Anemia and Systemic Lupus Erythematosus

Background: Clinical diagnosis is typically reached by following a series of steps recommended by guidelines authored by colleges of experts. Accordingly, guidelines play a crucial role in rationalizing clinical decisions but suffer from limitations as they are built to cover the majority of the population and fail at covering patients with uncommon conditions. Moreover, their updates are long and expensive, making them unsuitable for emerging diseases and practices. Methods: Inspired by guidelines, we formulate the task of diagnosis as a sequential decision-making problem and study the use of Deep Reinforcement Learning (DRL) algorithms to learn the optimal sequence of actions to perform in order to obtain a correct diagnosis from Electronic Health Records (EHRs). We apply DRL on synthetic, but realistic EHRs and develop two clinical use cases: Anemia diagnosis, where the decision pathways follow the schema of a decision tree; and Systemic Lupus Erythematosus (SLE) diagnosis, which follows a weighted criteria score. We particularly evaluate the robustness of our approaches to noisy and missing data since these frequently occur in EHRs. Results: In both use cases, and in the presence of imperfect data, our best DRL algorithms exhibit competitive performance when compared to the traditional classifiers, with the added advantage that they enable the progressive generation of a pathway to the suggested diagnosis which can both guide and explain the decision-making process. Conclusion: DRL offers the opportunity to learn personalized decision pathways to diagnosis. We illustrate with our two use cases their advantages: they generate step-by-step pathways that are self-explanatory; and their correctness is competitive when compared to state-of-the-art approaches.

arXiv:2404.05894공식 코드 · Papers with Code

Learning Heuristics for Transit Network Design and Improvement with Deep Reinforcement Learning

Planning a network of public transit routes is a challenging optimization problem. Metaheuristic algorithms search through the space of possible transit networks by applying heuristics that randomly alter routes in a network. The design of these heuristics has a major impact on the quality of the result. In this paper, we use deep reinforcement learning to train a graph neural net to provide heuristics for an evolutionary algorithm. These neural heuristics improve the algorithm's results on benchmark synthetic cities with 70 nodes or more, and achieve new state-of-the-art results on the challenging Mumford benchmark. They also improve upon a simulation of the real transit network in the city of Laval, Canada, by 52% and 25% on two key metrics, and offer cost savings of up to 19% over the city's existing transit network.

arXiv:2404.01308공식 코드 · Papers with Code

Learning to Solve Job Shop Scheduling under Uncertainty

Job-Shop Scheduling Problem (JSSP) is a combinatorial optimization problem where tasks need to be scheduled on machines in order to minimize criteria such as makespan or delay. To address more realistic scenarios, we associate a probability distribution with the duration of each task. Our objective is to generate a robust schedule, i.e. that minimizes the average makespan. This paper introduces a new approach that leverages Deep Reinforcement Learning (DRL) techniques to search for robust solutions, emphasizing JSSPs with uncertain durations. Key contributions of this research include: (1) advancements in DRL applications to JSSPs, enhancing generalization and scalability, (2) a novel method for addressing JSSPs with uncertain durations. The Wheatley approach, which integrates Graph Neural Networks (GNNs) and DRL, is made publicly available for further research and applications.

arXiv:2404.00204공식 코드 · Papers with Code

AirPilot: Interpretable PPO-based DRL Auto-Tuned Nonlinear PID Drone Controller for Robust Autonomous Flights

Navigation precision, speed and stability are crucial for safe Unmanned Aerial Vehicle (UAV) flight maneuvers and effective flight mission executions in dynamic environments. Different flight missions may have varying objectives, such as minimizing energy consumption, achieving precise positioning, or maximizing speed. A controller that can adapt to different objectives on the fly is highly valuable. Proportional Integral Derivative (PID) controllers are one of the most popular and widely used control algorithms for drones and other control systems, but their linear control algorithm fails to capture the nonlinear nature of the dynamic wind conditions and complex drone system. Manually tuning the PID gains for various missions can be time-consuming and requires significant expertise. This paper aims to revolutionize drone flight control by presenting the AirPilot, a nonlinear Deep Reinforcement Learning (DRL) - enhanced Proportional Integral Derivative (PID) drone controller using Proximal Policy Optimization (PPO). AirPilot controller combines the simplicity and effectiveness of traditional PID control with the adaptability, learning capability, and optimization potential of DRL. This makes it better suited for modern drone applications where the environment is dynamic, and mission-specific performance demands are high. We employed a COEX Clover autonomous drone for training the DRL agent within the simulator and implemented it in a real-world lab setting, which marks a significant milestone as one of the first attempts to apply a DRL-based flight controller on an actual drone. Airpilot is capable of reducing the navigation error of the default PX4 PID position controller by 90%, improving effective navigation speed of a fine-tuned PID controller by 21%, reducing settling time and overshoot by 17% and 16% respectively.

arXiv:2403.18364공식 코드 · Papers with Code

Intent-Aware DRL-Based NOMA Uplink Dynamic Scheduler for IIoT

We investigate the problem of supporting Industrial Internet of Things user equipment (IIoT UEs) with intent (i.e., requested quality of service (QoS)) and random traffic arrival. A deep reinforcement learning (DRL) based centralized dynamic scheduler for time-frequency resources is proposed to learn how to schedule the available communication resources among the IIoT UEs. The proposed scheduler leverages an RL framework to adapt to the dynamic changes in the wireless communication system and traffic arrivals. Moreover, a graph-based reduction scheme is proposed to reduce the state and action space of the RL framework to allow fast convergence and a better learning strategy. Simulation results demonstrate the effectiveness of the proposed intelligent scheduler in guaranteeing the expressed intent of IIoT UEs compared to several traditional scheduling schemes, such as round-robin, semi-static, and heuristic approaches. The proposed scheduler also outperforms the contention-free and contention-based schemes in maximizing the number of successfully computed tasks.