PyTorchKR Papers

최신 논문

총 1,872편
태그·기간 등 상세 필터

카테고리 탐색

로그인 후 이 태그 구독

논문 ID: document/1041243

Investigating the Performance and Reliability, of the Q-Learning Algorithm in Various Unknown Environments

Self-reinforcement algorithms, especially Q-learning and value iteration have been popular and effective for navigating mobile robots. To provide a deeper insight through their performance and usage, this paper investigates solving a simple Q-Learning problem for various working environments for mobile robots. No matter how quick or reliable they are, all temporal difference algorithms employ iterative methods to produce desired results. For this reason, in this paper, we looked at the relationship between episode steps, mesh sizes, and most importantly the impact of the environment on both convergence rate and solution reliability. As previously indicated, the majority of the conclusions of this study about the relationship between computation cost and environment and also dependability can be transferred to more sophisticated temporal difference-based algorithms because all methods are iterative. As many robotic applications for reinforcement learning have two or three-dimensional state space for path planning, knowing the approximate convergence episode count would be a useful tool for researchers to tackle non-optimal episodes, especially on embedded systems with computational constraints. The content also discussed the relationship between three mesh sizes and tried to guide researchers to implement their reinforcement learning pipeline more effectively. As shown by this work, the performance and reliability of iterative reinforcement learning algorithms depend deeply on the environment. In certain cases, increasing the number of episodes would not alter the results entirely. Therefore, when solving these kinds of maps, researchers would refrain from using Q-learning techniques.

arXiv:2402.03678공식 코드 · Papers with Code

Logical Specifications-guided Dynamic Task Sampling for Reinforcement Learning Agents

Reinforcement Learning (RL) has made significant strides in enabling artificial agents to learn diverse behaviors. However, learning an effective policy often requires a large number of environment interactions. To mitigate sample complexity issues, recent approaches have used high-level task specifications, such as Linear Temporal Logic (LTL$_f$) formulas or Reward Machines (RM), to guide the learning progress of the agent. In this work, we propose a novel approach, called Logical Specifications-guided Dynamic Task Sampling (LSTS), that learns a set of RL policies to guide an agent from an initial state to a goal state based on a high-level task specification, while minimizing the number of environmental interactions. Unlike previous work, LSTS does not assume information about the environment dynamics or the Reward Machine, and dynamically samples promising tasks that lead to successful goal policies. We evaluate LSTS on a gridworld and show that it achieves improved time-to-threshold performance on complex sequential decision-making problems compared to state-of-the-art RM and Automaton-guided RL baselines, such as Q-Learning for Reward Machines and Compositional RL from logical Specifications (DIRL). Moreover, we demonstrate that our method outperforms RM and Automaton-guided RL baselines in terms of sample-efficiency, both in a partially observable robotic task and in a continuous control robotic manipulation task.

arXiv:2402.03570

Diffusion World Model: Future Modeling Beyond Step-by-Step Rollout for Offline Reinforcement Learning

We introduce Diffusion World Model (DWM), a conditional diffusion model capable of predicting multistep future states and rewards concurrently. As opposed to traditional one-step dynamics models, DWM offers long-horizon predictions in a single forward pass, eliminating the need for recursive queries. We integrate DWM into model-based value estimation, where the short-term return is simulated by future trajectories sampled from DWM. In the context of offline reinforcement learning, DWM can be viewed as a conservative value regularization through generative modeling. Alternatively, it can be seen as a data source that enables offline Q-learning with synthetic data. Our experiments on the D4RL dataset confirm the robustness of DWM to long-horizon simulation. In terms of absolute performance, DWM significantly surpasses one-step dynamics models with a $44\%$ performance gain, and is comparable to or slightly surpassing their model-free counterparts.

arXiv:2402.02165공식 코드 · Papers with Code

Towards Optimal Adversarial Robust Q-learning with Bellman Infinity-error

Establishing robust policies is essential to counter attacks or disturbances affecting deep reinforcement learning (DRL) agents. Recent studies explore state-adversarial robustness and suggest the potential lack of an optimal robust policy (ORP), posing challenges in setting strict robustness constraints. This work further investigates ORP: At first, we introduce a consistency assumption of policy (CAP) stating that optimal actions in the Markov decision process remain consistent with minor perturbations, supported by empirical and theoretical evidence. Building upon CAP, we crucially prove the existence of a deterministic and stationary ORP that aligns with the Bellman optimal policy. Furthermore, we illustrate the necessity of $L^{\infty}$-norm when minimizing Bellman error to attain ORP. This finding clarifies the vulnerability of prior DRL algorithms that target the Bellman optimal policy with $L^{1}$-norm and motivates us to train a Consistent Adversarial Robust Deep Q-Network (CAR-DQN) by minimizing a surrogate of Bellman Infinity-error. The top-tier performance of CAR-DQN across various benchmarks validates its practical effectiveness and reinforces the soundness of our theoretical analysis.

arXiv:2402.02957

Multi-Agent Reinforcement Learning for Offloading Cellular Communications with Cooperating UAVs

Effective solutions for intelligent data collection in terrestrial cellular networks are crucial, especially in the context of Internet of Things applications. The limited spectrum and coverage area of terrestrial base stations pose challenges in meeting the escalating data rate demands of network users. Unmanned aerial vehicles, known for their high agility, mobility, and flexibility, present an alternative means to offload data traffic from terrestrial BSs, serving as additional access points. This paper introduces a novel approach to efficiently maximize the utilization of multiple UAVs for data traffic offloading from terrestrial BSs. Specifically, the focus is on maximizing user association with UAVs by jointly optimizing UAV trajectories and users association indicators under quality of service constraints. Since, the formulated UAVs control problem is nonconvex and combinatorial, this study leverages the multi agent reinforcement learning framework. In this framework, each UAV acts as an independent agent, aiming to maintain inter UAV cooperative behavior. The proposed approach utilizes the finite state Markov decision process to account for UAVs velocity constraints and the relationship between their trajectories and state space. A low complexity distributed state action reward state action algorithm is presented to determine UAVs optimal sequential decision making policies over training episodes. The extensive simulation results validate the proposed analysis and offer valuable insights into the optimal UAV trajectories. The derived trajectories demonstrate superior average UAV association performance compared to benchmark techniques such as Q learning and particle swarm optimization.

arXiv:2402.01574

DRL-Based Dynamic Channel Access and SCLAR Maximization for Networks Under Jamming

This paper investigates a deep reinforcement learning (DRL)-based approach for managing channel access in wireless networks. Specifically, we consider a scenario in which an intelligent user device (iUD) shares a time-varying uplink wireless channel with several fixed transmission schedule user devices (fUDs) and an unknown-schedule malicious jammer. The iUD aims to harmoniously coexist with the fUDs, avoid the jammer, and adaptively learn an optimal channel access strategy in the face of dynamic channel conditions, to maximize the network's sum cross-layer achievable rate (SCLAR). Through extensive simulations, we demonstrate that when we appropriately define the state space, action space, and rewards within the DRL framework, the iUD can effectively coexist with other UDs and optimize the network's SCLAR. We show that the proposed algorithm outperforms the tabular Q-learning and a fully connected deep neural network approach.

arXiv:2402.00091

Nash Soft Actor-Critic LEO Satellite Handover Management Algorithm for Flying Vehicles

Compared with the terrestrial networks (TN), which can only support limited coverage areas, low-earth orbit (LEO) satellites can provide seamless global coverage and high survivability in case of emergencies. Nevertheless, the swift movement of the LEO satellites poses a challenge: frequent handovers are inevitable, compromising the quality of service (QoS) of users and leading to discontinuous connectivity. Moreover, considering LEO satellite connectivity for different flying vehicles (FVs) when coexisting with ground terminals, an efficient satellite handover decision control and mobility management strategy is required to reduce the number of handovers and allocate resources that align with different users' requirements. In this paper, a novel distributed satellite handover strategy based on Multi-Agent Reinforcement Learning (MARL) and game theory named Nash-SAC has been proposed to solve these problems. From the simulation results, the Nash-SAC-based handover strategy can effectively reduce the handovers by over 16 percent and the blocking rate by over 18 percent, outperforming local benchmarks such as traditional Q-learning. It also greatly improves the network utility used to quantify the performance of the whole system by up to 48 percent and caters to different users requirements, providing reliable and robust connectivity for both FVs and ground terminals.

arXiv:2402.00738

FM3Q: Factorized Multi-Agent MiniMax Q-Learning for Two-Team Zero-Sum Markov Game

Many real-world applications involve some agents that fall into two teams, with payoffs that are equal within the same team but of opposite sign across the opponent team. The so-called two-team zero-sum Markov games (2t0sMGs) can be resolved with reinforcement learning in recent years. However, existing methods are thus inefficient in light of insufficient consideration of intra-team credit assignment, data utilization and computational intractability. In this paper, we propose the individual-global-minimax (IGMM) principle to ensure the coherence between two-team minimax behaviors and the individual greedy behaviors through Q functions in 2t0sMGs. Based on it, we present a novel multi-agent reinforcement learning framework, Factorized Multi-Agent MiniMax Q-Learning (FM3Q), which can factorize the joint minimax Q function into individual ones and iteratively solve for the IGMM-satisfied minimax Q functions for 2t0sMGs. Moreover, an online learning algorithm with neural networks is proposed to implement FM3Q and obtain the deterministic and decentralized minimax policies for two-team players. A theoretical analysis is provided to prove the convergence of FM3Q. Empirically, we use three environments to evaluate the learning efficiency and final performance of FM3Q and show its superiority on 2t0sMGs.

arXiv:2402.00676

Deep Robot Sketching: An application of Deep Q-Learning Networks for human-like sketching

The current success of Reinforcement Learning algorithms for its performance in complex environments has inspired many recent theoretical approaches to cognitive science. Artistic environments are studied within the cognitive science community as rich, natural, multi-sensory, multi-cultural environments. In this work, we propose the introduction of Reinforcement Learning for improving the control of artistic robot applications. Deep Q-learning Neural Networks (DQN) is one of the most successful algorithms for the implementation of Reinforcement Learning in robotics. DQN methods generate complex control policies for the execution of complex robot applications in a wide set of environments. Current art painting robot applications use simple control laws that limits the adaptability of the frameworks to a set of simple environments. In this work, the introduction of DQN within an art painting robot application is proposed. The goal is to study how the introduction of a complex control policy impacts the performance of a basic art painting robot application. The main expected contribution of this work is to serve as a first baseline for future works introducing DQN methods for complex art painting robot frameworks. Experiments consist of real world executions of human drawn sketches using the DQN generated policy and TEO, the humanoid robot. Results are compared in terms of similarity and obtained reward with respect to the reference inputs

arXiv:2402.00468공식 코드 · Papers with Code

RadDQN: a Deep Q Learning-based Architecture for Finding Time-efficient Minimum Radiation Exposure Pathway

Recent advancements in deep reinforcement learning (DRL) techniques have sparked its multifaceted applications in the automation sector. Managing complex decision-making problems with DRL encourages its use in the nuclear industry for tasks such as optimizing radiation exposure to the personnel during normal operating conditions and potential accidental scenarios. However, the lack of efficient reward function and effective exploration strategy thwarted its implementation in the development of radiation-aware autonomous unmanned aerial vehicle (UAV) for achieving maximum radiation protection. Here, in this article, we address these intriguing issues and introduce a deep Q-learning based architecture (RadDQN) that operates on a radiation-aware reward function to provide time-efficient minimum radiation-exposure pathway in a radiation zone. We propose a set of unique exploration strategies that fine-tune the extent of exploration and exploitation based on the state-wise variation in radiation exposure during training. Further, we benchmark the predicted path with grid-based deterministic method. We demonstrate that the formulated reward function in conjugation with adequate exploration strategy is effective in handling several scenarios with drastically different radiation field distributions. When compared to vanilla DQN, our model achieves a superior convergence rate and higher training stability.

arXiv:2402.00085

Scheduled Curiosity-Deep Dyna-Q: Efficient Exploration for Dialog Policy Learning

Training task-oriented dialog agents based on reinforcement learning is time-consuming and requires a large number of interactions with real users. How to grasp dialog policy within limited dialog experiences remains an obstacle that makes the agent training process less efficient. In addition, most previous frameworks start training by randomly choosing training samples, which differs from the human learning method and hurts the efficiency and stability of training. Therefore, we propose Scheduled Curiosity-Deep Dyna-Q (SC-DDQ), a curiosity-driven curriculum learning framework based on a state-of-the-art model-based reinforcement learning dialog model, Deep Dyna-Q (DDQ). Furthermore, we designed learning schedules for SC-DDQ and DDQ, respectively, following two opposite training strategies: classic curriculum learning and its reverse version. Our results show that by introducing scheduled learning and curiosity, the new framework leads to a significant improvement over the DDQ and Deep Q-learning(DQN). Surprisingly, we found that traditional curriculum learning was not always effective. Specifically, according to the experimental results, the easy-first and difficult-first strategies are more suitable for SC-DDQ and DDQ. To analyze our results, we adopted the entropy of sampled actions to depict action exploration and found that training strategies with high entropy in the first stage and low entropy in the last stage lead to better performance.

arXiv:2401.16073

Emergence of cooperation under punishment: A reinforcement learning perspective

Punishment is a common tactic to sustain cooperation and has been extensively studied for a long time. While most of previous game-theoretic work adopt the imitation learning where players imitate the strategies who are better off, the learning logic in the real world is often much more complex. In this work, we turn to the reinforcement learning paradigm, where individuals make their decisions based upon their past experience and long-term returns. Specifically, we investigate the Prisoners' dilemma game with Q-learning algorithm, and cooperators probabilistically pose punishment on defectors in their neighborhood. Interestingly, we find that punishment could lead to either continuous or discontinuous cooperation phase transitions, and the nucleation process of cooperation clusters is reminiscent of the liquid-gas transition. The uncovered first-order phase transition indicates that great care needs to be taken when implementing the punishment compared to the continuous scenario.

arXiv:2401.16772

Extrinsicaly Rewarded Soft Q Imitation Learning with Discriminator

Imitation learning is often used in addition to reinforcement learning in environments where reward design is difficult or where the reward is sparse, but it is difficult to be able to imitate well in unknown states from a small amount of expert data and sampling data. Supervised learning methods such as Behavioral Cloning do not require sampling data, but usually suffer from distribution shift. The methods based on reinforcement learning, such as inverse reinforcement learning and Generative Adversarial imitation learning (GAIL), can learn from only a few expert data. However, they often need to interact with the environment. Soft Q imitation learning (SQIL) addressed the problems, and it was shown that it could learn efficiently by combining Behavioral Cloning and soft Q-learning with constant rewards. In order to make this algorithm more robust to distribution shift, we propose more efficient and robust algorithm by adding to this method a reward function based on adversarial inverse reinforcement learning that rewards the agent for performing actions in status similar to the demo. We call this algorithm Discriminator Soft Q Imitation Learning (DSQIL). We evaluated it on MuJoCo environments.

arXiv:2401.15196

Regularized Q-Learning with Linear Function Approximation

Regularized Markov Decision Processes serve as models of sequential decision making under uncertainty wherein the decision maker has limited information processing capacity and/or aversion to model ambiguity. With functional approximation, the convergence properties of learning algorithms for regularized MDPs (e.g. soft Q-learning) are not well understood because the composition of the regularized Bellman operator and a projection onto the span of basis vectors is not a contraction with respect to any norm. In this paper, we consider a bi-level optimization formulation of regularized Q-learning with linear functional approximation. The {\em lower} level optimization problem aims to identify a value function approximation that satisfies Bellman's recursive optimality condition and the {\em upper} level aims to find the projection onto the span of basis vectors. This formulation motivates a single-loop algorithm with finite time convergence guarantees. The algorithm operates on two time-scales: updates to the projection of state-action values are `slow' in that they are implemented with a step size that is smaller than the one used for `faster' updates of approximate solutions to Bellman's recursive optimality equation. We show that, under certain assumptions, the proposed algorithm converges to a stationary point in the presence of Markovian noise. In addition, we provide a performance guarantee for the policies derived from the proposed algorithm.

arXiv:2401.13884

Constant Stepsize Q-learning: Distributional Convergence, Bias and Extrapolation

Stochastic Approximation (SA) is a widely used algorithmic approach in various fields, including optimization and reinforcement learning (RL). Among RL algorithms, Q-learning is particularly popular due to its empirical success. In this paper, we study asynchronous Q-learning with constant stepsize, which is commonly used in practice for its fast convergence. By connecting the constant stepsize Q-learning to a time-homogeneous Markov chain, we show the distributional convergence of the iterates in Wasserstein distance and establish its exponential convergence rate. We also establish a Central Limit Theory for Q-learning iterates, demonstrating the asymptotic normality of the averaged iterates. Moreover, we provide an explicit expansion of the asymptotic bias of the averaged iterate in stepsize. Specifically, the bias is proportional to the stepsize up to higher-order terms and we provide an explicit expression for the linear coefficient. This precise characterization of the bias allows the application of Richardson-Romberg (RR) extrapolation technique to construct a new estimate that is provably closer to the optimal Q function. Numerical results corroborate our theoretical finding on the improvement of the RR extrapolation method.

arXiv:2401.11555공식 코드 · Papers with Code

VQC-Based Reinforcement Learning with Data Re-uploading: Performance and Trainability

Reinforcement Learning (RL) consists of designing agents that make intelligent decisions without human supervision. When used alongside function approximators such as Neural Networks (NNs), RL is capable of solving extremely complex problems. Deep Q-Learning, a RL algorithm that uses Deep NNs, achieved super-human performance in some specific tasks. Nonetheless, it is also possible to use Variational Quantum Circuits (VQCs) as function approximators in RL algorithms. This work empirically studies the performance and trainability of such VQC-based Deep Q-Learning models in classic control benchmark environments. More specifically, we research how data re-uploading affects both these metrics. We show that the magnitude and the variance of the gradients of these models remain substantial throughout training due to the moving targets of Deep Q-Learning. Moreover, we empirically show that increasing the number of qubits does not lead to an exponential vanishing behavior of the magnitude and variance of the gradients for a PQC approximating a 2-design, unlike what was expected due to the Barren Plateau Phenomenon. This hints at the possibility of VQCs being specially adequate for being used as function approximators in such a context.

arXiv:2401.11512

Information-Theoretic State Variable Selection for Reinforcement Learning

Identifying the most suitable variables to represent the state is a fundamental challenge in Reinforcement Learning (RL). These variables must efficiently capture the information necessary for making optimal decisions. In order to address this problem, in this paper, we introduce the Transfer Entropy Redundancy Criterion (TERC), an information-theoretic criterion, which determines if there is \textit{entropy transferred} from state variables to actions during training. We define an algorithm based on TERC that provably excludes variables from the state that have no effect on the final performance of the agent, resulting in more sample efficient learning. Experimental results show that this speed-up is present across three different algorithm classes (represented by tabular Q-learning, Actor-Critic, and Proximal Policy Optimization (PPO)) in a variety of environments. Furthermore, to highlight the differences between the proposed methodology and the current state-of-the-art feature selection approaches, we present a series of controlled experiments on synthetic data, before generalizing to real-world decision-making tasks. We also introduce a representation of the problem that compactly captures the transfer of information from state variables to actions as Bayesian networks.

arXiv:2401.10265

The Best Time for an Update: Risk-Sensitive Minimization of Age-Based Metrics

Popular methods to quantify transmitted data quality are the Age of Information (AoI), the Query Age of Information (QAoI), and the Age of Incorrect Information (AoII). We consider these metrics in a point-to-point wireless communication system, where the transmitter monitors a process and sends status updates to a receiver. The challenge is to decide on the best time for an update, balancing the transmission energy and the age-based metric at the receiver. Due to the inherent risk of high age-based metric values causing complications such as unstable system states, we introduce the new concept of risky states to denote states with high age-based metric. We use this new notion of risky states to quantify and minimize this risk of experiencing high age-based metrics by directly deriving the frequency of risky states as a novel risk-metric. Building on this foundation, we introduce two risk-sensitive strategies for AoI, QAoI and AoII. The first strategy uses system knowledge, i.e., channel quality and packet arrival probability, to find an optimal strategy that transmits when the age-based metric exceeds a tunable threshold. A lower threshold leads to higher risk-sensitivity. The second strategy uses an enhanced Q-learning approach and balances the age-based metric, the transmission energy and the frequency of risky states without requiring knowledge about the system. Numerical results affirm our risk-sensitive strategies' high effectiveness.

arXiv:2401.08850

REValueD: Regularised Ensemble Value-Decomposition for Factorisable Markov Decision Processes

Discrete-action reinforcement learning algorithms often falter in tasks with high-dimensional discrete action spaces due to the vast number of possible actions. A recent advancement leverages value-decomposition, a concept from multi-agent reinforcement learning, to tackle this challenge. This study delves deep into the effects of this value-decomposition, revealing that whilst it curtails the over-estimation bias inherent to Q-learning algorithms, it amplifies target variance. To counteract this, we present an ensemble of critics to mitigate target variance. Moreover, we introduce a regularisation loss that helps to mitigate the effects that exploratory actions in one dimension can have on the value of optimal actions in other dimensions. Our novel algorithm, REValueD, tested on discretised versions of the DeepMind Control Suite tasks, showcases superior performance, especially in the challenging humanoid and dog tasks. We further dissect the factors influencing REValueD's performance, evaluating the significance of the regularisation loss and the scalability of REValueD with increasing sub-actions per dimension.

arXiv:2401.06299

Model-Free Reinforcement Learning for Automated Fluid Administration in Critical Care

Fluid administration, also called fluid resuscitation, is a medical treatment to restore the lost blood volume and optimize cardiac functions in critical care scenarios such as burn, hemorrhage, and septic shock. Automated fluid administration systems (AFAS), a potential means to improve the treatment, employ computational control algorithms to automatically adjust optimal fluid infusion dosages by targeting physiological variables (e.g., blood volume or blood pressure). Most of the existing AFAS control algorithms are model-based approaches, and their performance is highly dependent on the model accuracy, making them less desirable in real-world care of critically ill patients due to complexity and variability of modeling patients physiological states. This work presents a novel model-free reinforcement learning (RL) approach for the control of fluid infusion dosages in AFAS systems. The proposed RL agent learns to adjust the blood volume to a desired value by choosing the optimal infusion dosages using a Q-learning algorithm. The RL agent learns the optimal actions by interacting with the environment (without having the knowledge of system dynamics). The proposed methodology (i) overcomes the need for a precise mathematical model in AFAS systems and (ii) provides a robust performance in rejecting clinical noises and reaching desired hemodynamic states, as will be shown by simulation results.