PyTorchKR Papers

최신 논문

총 1,872편
태그·기간 등 상세 필터

카테고리 탐색

로그인 후 이 태그 구독

arXiv:2106.14642

Expert Q-learning: Deep Reinforcement Learning with Coarse State Values from Offline Expert Examples

In this article, we propose a novel algorithm for deep reinforcement learning named Expert Q-learning. Expert Q-learning is inspired by Dueling Q-learning and aims at incorporating semi-supervised learning into reinforcement learning through splitting Q-values into state values and action advantages. We require that an offline expert assesses the value of a state in a coarse manner using three discrete values. An expert network is designed in addition to the Q-network, which updates each time following the regular offline minibatch update whenever the expert example buffer is not empty. Using the board game Othello, we compare our algorithm with the baseline Q-learning algorithm, which is a combination of Double Q-learning and Dueling Q-learning. Our results show that Expert Q-learning is indeed useful and more resistant to the overestimation bias. The baseline Q-learning algorithm exhibits unstable and suboptimal behavior in non-deterministic settings, whereas Expert Q-learning demonstrates more robust performance with higher scores, illustrating that our algorithm is indeed suitable to integrate state values from expert examples into Q-learning.

arXiv:2106.13755

Reinforcement Learning for Mean Field Games, with Applications to Economics

Mean field games (MFG) and mean field control problems (MFC) are frameworks to study Nash equilibria or social optima in games with a continuum of agents. These problems can be used to approximate competitive or cooperative games with a large finite number of agents and have found a broad range of applications, in particular in economics. In recent years, the question of learning in MFG and MFC has garnered interest, both as a way to compute solutions and as a way to model how large populations of learners converge to an equilibrium. Of particular interest is the setting where the agents do not know the model, which leads to the development of reinforcement learning (RL) methods. After reviewing the literature on this topic, we present a two timescale approach with RL for MFG and MFC, which relies on a unified Q-learning algorithm. The main novelty of this method is to simultaneously update an action-value function and a distribution but with different rates, in a model-free fashion. Depending on the ratio of the two learning rates, the algorithm learns either the MFG or the MFC solution. To illustrate this method, we apply it to a mean field problem of accumulated consumption in finite horizon with HARA utility function, and to a trader's optimal liquidation problem.

arXiv:2106.12928

Exploration-Exploitation in Multi-Agent Competition: Convergence with Bounded Rationality

The interplay between exploration and exploitation in competitive multi-agent learning is still far from being well understood. Motivated by this, we study smooth Q-learning, a prototypical learning model that explicitly captures the balance between game rewards and exploration costs. We show that Q-learning always converges to the unique quantal-response equilibrium (QRE), the standard solution concept for games under bounded rationality, in weighted zero-sum polymatrix games with heterogeneous learning agents using positive exploration rates. Complementing recent results about convergence in weighted potential games, we show that fast convergence of Q-learning in competitive settings is obtained regardless of the number of agents and without any need for parameter fine-tuning. As showcased by our experiments in network zero-sum games, these theoretical results provide the necessary guarantees for an algorithmic approach to the currently open problem of equilibrium selection in competitive multi-agent settings.

arXiv:2106.12534공식 코드 · Papers with Code

Coarse-to-Fine Q-attention: Efficient Learning for Visual Robotic Manipulation via Discretisation

We present a coarse-to-fine discretisation method that enables the use of discrete reinforcement learning approaches in place of unstable and data-inefficient actor-critic methods in continuous robotics domains. This approach builds on the recently released ARM algorithm, which replaces the continuous next-best pose agent with a discrete one, with coarse-to-fine Q-attention. Given a voxelised scene, coarse-to-fine Q-attention learns what part of the scene to 'zoom' into. When this 'zooming' behaviour is applied iteratively, it results in a near-lossless discretisation of the translation space, and allows the use of a discrete action, deep Q-learning method. We show that our new coarse-to-fine algorithm achieves state-of-the-art performance on several difficult sparsely rewarded RLBench vision-based robotics tasks, and can train real-world policies, tabula rasa, in a matter of minutes, with as little as 3 demonstrations.

arXiv:2106.12142공식 코드 · Papers with Code

IQ-Learn: Inverse soft-Q Learning for Imitation

In many sequential decision-making problems (e.g., robotics control, game playing, sequential prediction), human or expert data is available containing useful information about the task. However, imitation learning (IL) from a small amount of expert data can be challenging in high-dimensional environments with complex dynamics. Behavioral cloning is a simple method that is widely used due to its simplicity of implementation and stable convergence but doesn't utilize any information involving the environment's dynamics. Many existing methods that exploit dynamics information are difficult to train in practice due to an adversarial optimization process over reward and policy approximators or biased, high variance gradient estimators. We introduce a method for dynamics-aware IL which avoids adversarial training by learning a single Q-function, implicitly representing both reward and policy. On standard benchmarks, the implicitly learned rewards show a high positive correlation with the ground-truth rewards, illustrating our method can also be used for inverse reinforcement learning (IRL). Our method, Inverse soft-Q learning (IQ-Learn) obtains state-of-the-art results in offline and online imitation learning settings, significantly outperforming existing methods both in the number of required environment interactions and scalability in high-dimensional spaces, often by more than 3x.

arXiv:2106.12024공식 코드 · Papers with Code

Q-Learning Lagrange Policies for Multi-Action Restless Bandits

Multi-action restless multi-armed bandits (RMABs) are a powerful framework for constrained resource allocation in which $N$ independent processes are managed. However, previous work only study the offline setting where problem dynamics are known. We address this restrictive assumption, designing the first algorithms for learning good policies for Multi-action RMABs online using combinations of Lagrangian relaxation and Q-learning. Our first approach, MAIQL, extends a method for Q-learning the Whittle index in binary-action RMABs to the multi-action setting. We derive a generalized update rule and convergence proof and establish that, under standard assumptions, MAIQL converges to the asymptotically optimal multi-action RMAB policy as $t\rightarrow{}\infty$. However, MAIQL relies on learning Q-functions and indexes on two timescales which leads to slow convergence and requires problem structure to perform well. Thus, we design a second algorithm, LPQL, which learns the well-performing and more general Lagrange policy for multi-action RMABs by learning to minimize the Lagrange bound through a variant of Q-learning. To ensure fast convergence, we take an approximation strategy that enables learning on a single timescale, then give a guarantee relating the approximation's precision to an upper bound of LPQL's return as $t\rightarrow{}\infty$. Finally, we show that our approaches always outperform baselines across multiple settings, including one derived from real-world medication adherence data.

arXiv:2106.11368

Reinforcement Learning for Resource Allocation in Steerable Laser-based Optical Wireless Systems

Vertical Cavity Surface Emitting Lasers (VCSELs) have demonstrated suitability for data transmission in indoor optical wireless communication (OWC) systems due to the high modulation bandwidth and low manufacturing cost of these sources. Specifically, resource allocation is one of the major challenges that can affect the performance of multi-user optical wireless systems. In this paper, an optimisation problem is formulated to optimally assign each user to an optical access point (AP) composed of multiple VCSELs within a VCSEL array at a certain time to maximise the signal to interference plus noise ratio (SINR). In this context, a mixed-integer linear programming (MILP) model is introduced to solve this optimisation problem. Despite the optimality of the MILP model, it is considered impractical due to its high complexity, high memory and full system information requirements. Therefore, reinforcement Learning (RL) is considered, which recently has been widely investigated as a practical solution for various optimization problems in cellular networks due to its ability to interact with environments with no previous experience. In particular, a Q-learning (QL) algorithm is investigated to perform resource management in a steerable VCSEL-based OWC systems. The results demonstrate the ability of the QL algorithm to achieve optimal solutions close to the MILP model. Moreover, the adoption of beam steering, using holograms implemented by exploiting liquid crystal devices, results in further enhancement in the performance of the network considered.

arXiv:2106.11365공식 코드 · Papers with Code

Distributed Heuristic Multi-Agent Path Finding with Communication

Multi-Agent Path Finding (MAPF) is essential to large-scale robotic systems. Recent methods have applied reinforcement learning (RL) to learn decentralized polices in partially observable environments. A fundamental challenge of obtaining collision-free policy is that agents need to learn cooperation to handle congested situations. This paper combines communication with deep Q-learning to provide a novel learning based method for MAPF, where agents achieve cooperation via graph convolution. To guide RL algorithm on long-horizon goal-oriented tasks, we embed the potential choices of shortest paths from single source as heuristic guidance instead of using a specific path as in most existing works. Our method treats each agent independently and trains the model from a single agent's perspective. The final trained policy is applied to each agent for decentralized execution. The whole system is distributed during training and is trained under a curriculum learning strategy. Empirical evaluation in obstacle-rich environment indicates the high success rate with low average step of our method.

arXiv:2106.11595공식 코드 · Papers with Code

Reinforcement Learning for Physical Layer Communications

In this chapter, we will give comprehensive examples of applying RL in optimizing the physical layer of wireless communications by defining different class of problems and the possible solutions to handle them. In Section 9.2, we present all the basic theory needed to address a RL problem, i.e. Markov decision process (MDP), Partially observable Markov decision process (POMDP), but also two very important and widely used algorithms for RL, i.e. the Q-learning and SARSA algorithms. We also introduce the deep reinforcement learning (DRL) paradigm and the section ends with an introduction to the multi-armed bandits (MAB) framework. Section 9.3 focuses on some toy examples to illustrate how the basic concepts of RL are employed in communication systems. We present applications extracted from literature with simplified system models using similar notation as in Section 9.2 of this Chapter. In Section 9.3, we also focus on modeling RL problems, i.e. how action and state spaces and rewards are chosen. The Chapter is concluded in Section 9.4 with a prospective thought on RL trends and it ends with a review of a broader state of the art in Section 9.5.

arXiv:2106.11086

Analytically Tractable Bayesian Deep Q-Learning

Reinforcement learning (RL) has gained increasing interest since the demonstration it was able to reach human performance on video game benchmarks using deep Q-learning (DQN). The current consensus for training neural networks on such complex environments is to rely on gradient-based optimization. Although alternative Bayesian deep learning methods exist, most of them still rely on gradient-based optimization, and they typically do not scale on benchmarks such as the Atari game environment. Moreover none of these approaches allow performing the analytical inference for the weights and biases defining the neural network. In this paper, we present how we can adapt the temporal difference Q-learning framework to make it compatible with the tractable approximate Gaussian inference (TAGI), which allows learning the parameters of a neural network using a closed-form analytical method. Throughout the experiments with on- and off-policy reinforcement learning approaches, we demonstrate that TAGI can reach a performance comparable to backpropagation-trained networks while using fewer hyperparameters, and without relying on gradient-based optimization.

arXiv:2106.10411

Boosting Offline Reinforcement Learning with Residual Generative Modeling

Offline reinforcement learning (RL) tries to learn the near-optimal policy with recorded offline experience without online exploration. Current offline RL research includes: 1) generative modeling, i.e., approximating a policy using fixed data; and 2) learning the state-action value function. While most research focuses on the state-action function part through reducing the bootstrapping error in value function approximation induced by the distribution shift of training data, the effects of error propagation in generative modeling have been neglected. In this paper, we analyze the error in generative modeling. We propose AQL (action-conditioned Q-learning), a residual generative model to reduce policy approximation error for offline RL. We show that our method can learn more accurate policy approximations in different benchmark datasets. In addition, we show that the proposed offline RL method can learn more competitive AI agents in complex control tasks under the multiplayer online battle arena (MOBA) game Honor of Kings.

arXiv:2106.09812

Deep reinforcement learning with automated label extraction from clinical reports accurately classifies 3D MRI brain volumes

Purpose: Image classification is perhaps the most fundamental task in imaging AI. However, labeling images is time-consuming and tedious. We have recently demonstrated that reinforcement learning (RL) can classify 2D slices of MRI brain images with high accuracy. Here we make two important steps toward speeding image classification: Firstly, we automatically extract class labels from the clinical reports. Secondly, we extend our prior 2D classification work to fully 3D image volumes from our institution. Hence, we proceed as follows: in Part 1, we extract labels from reports automatically using the SBERT natural language processing approach. Then, in Part 2, we use these labels with RL to train a classification Deep-Q Network (DQN) for 3D image volumes. Methods: For Part 1, we trained SBERT with 90 radiology report impressions. We then used the trained SBERT to predict class labels for use in Part 2. In Part 2, we applied multi-step image classification to allow for combined Deep-Q learning using 3D convolutions and TD(0) Q learning. We trained on a set of 90 images. We tested on a separate set of 61 images, again using the classes predicted from patient reports by the trained SBERT in Part 1. For comparison, we also trained and tested a supervised deep learning classification network on the same set of training and testing images using the same labels. Results: Part 1: Upon training with the corpus of radiology reports, the SBERT model had 100% accuracy for both normal and metastasis-containing scans. Part 2: Then, using these labels, whereas the supervised approach quickly overfit the training data and as expected performed poorly on the testing set (66% accuracy, just over random guessing), the reinforcement learning approach achieved an accuracy of 92%. The results were found to be statistically significant, with a p-value of 3.1 x 10^-5.

arXiv:2106.09556

A Deep Reinforcement Learning Approach towards Pendulum Swing-up Problem based on TF-Agents

Adapting the idea of training CartPole with Deep Q-learning agent, we are able to find a promising result that prevent the pole from falling down. The capacity of reinforcement learning (RL) to learn from the interaction between the environment and agent provides an optimal control strategy. In this paper, we aim to solve the classic pendulum swing-up problem that making the learned pendulum to be in upright position and balanced. Deep Deterministic Policy Gradient algorithm is introduced to operate over continuous action domain in this problem. Salient results of optimal pendulum are proved with increasing average return, decreasing loss, and live video in the code part.

arXiv:2106.08863

Unbiased Methods for Multi-Goal Reinforcement Learning

In multi-goal reinforcement learning (RL) settings, the reward for each goal is sparse, and located in a small neighborhood of the goal. In large dimension, the probability of reaching a reward vanishes and the agent receives little learning signal. Methods such as Hindsight Experience Replay (HER) tackle this issue by also learning from realized but unplanned-for goals. But HER is known to introduce bias, and can converge to low-return policies by overestimating chancy outcomes. First, we vindicate HER by proving that it is actually unbiased in deterministic environments, such as many optimal control settings. Next, for stochastic environments in continuous spaces, we tackle sparse rewards by directly taking the infinitely sparse reward limit. We fully formalize the problem of multi-goal RL with infinitely sparse Dirac rewards at each goal. We introduce unbiased deep Q-learning and actor-critic algorithms that can handle such infinitely sparse rewards, and test them in toy environments.

arXiv:2106.07704공식 코드 · Papers with Code

Efficient (Soft) Q-Learning for Text Generation with Limited Good Data

Maximum likelihood estimation (MLE) is the predominant algorithm for training text generation models. This paradigm relies on direct supervision examples, which is not applicable to many emerging applications, such as generating adversarial attacks or generating prompts to control language models. Reinforcement learning (RL) on the other hand offers a more flexible solution by allowing users to plug in arbitrary task metrics as reward. Yet previous RL algorithms for text generation, such as policy gradient (on-policy RL) and Q-learning (off-policy RL), are often notoriously inefficient or unstable to train due to the large sequence space and the sparse reward received only at the end of sequences. In this paper, we introduce a new RL formulation for text generation from the soft Q-learning (SQL) perspective. It enables us to draw from the latest RL advances, such as path consistency learning, to combine the best of on-/off-policy updates, and learn effectively from sparse reward. We apply the approach to a wide range of novel text generation tasks, including learning from noisy/negative examples, adversarial attacks, and prompt generation. Experiments show our approach consistently outperforms both task-specialized algorithms and the previous RL methods.

arXiv:2106.05262공식 코드 · Papers with Code

TempoRL: Learning When to Act

Reinforcement learning is a powerful approach to learn behaviour through interactions with an environment. However, behaviours are usually learned in a purely reactive fashion, where an appropriate action is selected based on an observation. In this form, it is challenging to learn when it is necessary to execute new decisions. This makes learning inefficient, especially in environments that need various degrees of fine and coarse control. To address this, we propose a proactive setting in which the agent not only selects an action in a state but also for how long to commit to that action. Our TempoRL approach introduces skip connections between states and learns a skip-policy for repeating the same action along these skips. We demonstrate the effectiveness of TempoRL on a variety of traditional and deep RL environments, showing that our approach is capable of learning successful policies up to an order of magnitude faster than vanilla Q-learning.

arXiv:2106.02748

Decentralized Q-Learning in Zero-sum Markov Games

We study multi-agent reinforcement learning (MARL) in infinite-horizon discounted zero-sum Markov games. We focus on the practical but challenging setting of decentralized MARL, where agents make decisions without coordination by a centralized controller, but only based on their own payoffs and local actions executed. The agents need not observe the opponent's actions or payoffs, possibly being even oblivious to the presence of the opponent, nor be aware of the zero-sum structure of the underlying game, a setting also referred to as radically uncoupled in the literature of learning in games. In this paper, we develop a radically uncoupled Q-learning dynamics that is both rational and convergent: the learning dynamics converges to the best response to the opponent's strategy when the opponent follows an asymptotically stationary strategy; when both agents adopt the learning dynamics, they converge to the Nash equilibrium of the game. The key challenge in this decentralized setting is the non-stationarity of the environment from an agent's perspective, since both her own payoffs and the system evolution depend on the actions of other agents, and each agent adapts her policies simultaneously and independently. To address this issue, we develop a two-timescale learning dynamics where each agent updates her local Q-function and value function estimates concurrently, with the latter happening at a slower timescale.

arXiv:2106.03400공식 코드 · Papers with Code

Believe What You See: Implicit Constraint Approach for Offline Multi-Agent Reinforcement Learning

Learning from datasets without interaction with environments (Offline Learning) is an essential step to apply Reinforcement Learning (RL) algorithms in real-world scenarios. However, compared with the single-agent counterpart, offline multi-agent RL introduces more agents with the larger state and action space, which is more challenging but attracts little attention. We demonstrate current offline RL algorithms are ineffective in multi-agent systems due to the accumulated extrapolation error. In this paper, we propose a novel offline RL algorithm, named Implicit Constraint Q-learning (ICQ), which effectively alleviates the extrapolation error by only trusting the state-action pairs given in the dataset for value estimation. Moreover, we extend ICQ to multi-agent tasks by decomposing the joint-policy under the implicit constraint. Experimental results demonstrate that the extrapolation error is successfully controlled within a reasonable range and insensitive to the number of agents. We further show that ICQ achieves the state-of-the-art performance in the challenging multi-agent offline tasks (StarCraft II). Our code is public online at https://github.com/YiqinYang/ICQ.

arXiv:2106.02613공식 코드 · Papers with Code

Bridging the Gap Between Target Networks and Functional Regularization

Bootstrapping is behind much of the successes of deep Reinforcement Learning. However, learning the value function via bootstrapping often leads to unstable training due to fast-changing target values. Target Networks are employed to stabilize training by using an additional set of lagging parameters to estimate the target values. Despite the popularity of Target Networks, their effect on the optimization is still misunderstood. In this work, we show that they act as an implicit regularizer which can be beneficial in some cases, but also have disadvantages such as being inflexible and can result in instabilities, even when vanilla TD(0) converges. To overcome these issues, we propose an explicit Functional Regularization alternative that is flexible and a convex regularizer in function space and we theoretically study its convergence. We conduct an experimental study across a range of environments, discount factors, and off-policiness data collections to investigate the effectiveness of the regularization induced by Target Networks and Functional Regularization in terms of performance, accuracy, and stability. Our findings emphasize that Functional Regularization can be used as a drop-in replacement for Target Networks and result in performance improvement. Furthermore, adjusting both the regularization weight and the network update period in Functional Regularization can result in further performance improvements compared to solely adjusting the network update period as typically done with Target Networks. Our approach also enhances the ability to networks to recover accurate $Q$-values.