No full-text available
To read the full-text of this research,
you can request a copy directly from the authors.
Deep Reinforcement Learning using Cyclical Learning Rates
... In DRL, it is necessary to provide the agent with a set of optimal hyperparameters to improve the performance and effect of learning [24]. ...
Frequency and voltage deviation are important standards for measuring energy indicators. It is important for microgrids to maintain the stability of voltage and frequency (VF). Aiming at the VF regulation of microgrid caused by wind disturbance and load fluctuation, a comprehensive VF control strategy for an islanded microgrid with electric vehicles (EVs) based on Deep Deterministic Policy Gradient (DDPG) is proposed in this paper. First of all, the SOC constraints of EVs are added to construct a cluster-EV charging model, by considering the randomness of users’ travel demand and charging behavior. In addition, a four-quadrant two-way charger capacity model is introduced to build a microgrid VF control model including load, micro gas turbine (MT), EVs, and their random power increment constraints. Secondly, according to the two control goals of microgrid frequency and voltage, the structure of DDPG controller is designed. Then, the definition of space, the design of global and local reward functions, and the selection of optimal hyperparameters are completed. Finally, different scenarios are set up in an islanded microgrid with EVs, and the simulation results are compared with traditional PI control and R(λ) control. The simulation results show that the proposed DDPG controller can quickly and efficiently suppress the VF fluctuations caused by wind disturbance and load fluctuations at the same time.
... In deep reinforcement learning, the single-step average reward value of each episode is an important indicator to measure the training effect [30][31][32][33]. This paper counts the average single-step rewards of [22] and DCPER-DDPG algorithm in 6000 episodes. ...
In an autonomous vehicle, the lane following algorithm is an important component, which is a basic function of autonomous driving. However, the existing lane following system has a few shortcomings: first, the control method it adopts requires an accurate system model, and different vehicles have different parameters, which needs a lot of parameter calibration work. The second is that it may fail on road sections where the lateral acceleration requirements of vehicles are large, such as large curves. Third, its decision-making system is defined based on rules, which has disadvantages: it is difficult to formulate; human subjective factors cannot guarantee objectivity; coverage is difficult to guarantee. In recent years, the deep deterministic policy gradient (DDPG) algorithm has been widely used in the field of autonomous driving due to its strong nonlinear fitting ability and generalization performance. However, the DDPG algorithm has overestimated state action values and large cumulative errors, low training efficiency and other issues. Therefore, this paper improves the DDPG algorithm based on the double critic networks and priority experience replay mechanism. Then this paper proposes a lane following method based on this algorithm. Experiment shows that the algorithm can achieve excellent following results under various road conditions.
The performance of stochastic gradient descent (SGD) depends critically on how learning rates are tuned and decreased over time. We propose a method to automatically adjust multiple learning rates so as to minimize the expected error at any one time. The method relies on local gradient variations across samples. In our approach, learning rates can in-crease as well as decrease, making it suitable for non-stationary problems. Using a number of convex and non-convex learning tasks, we show that the resulting algorithm matches the performance of SGD or other adaptive approaches with their best settings obtained through systematic search, and effectively re-moves the need for learning rate tuning.
The performance of stochastic gradient descent (SGD) depends critically on
how learning rates are tuned and decreased over time. We propose a method to
automatically adjust multiple learning rates so as to minimize the expected
error at any one time. The method relies on local gradient variations across
samples. In our approach, learning rates can increase as well as decrease,
making it suitable for non-stationary problems. Using a number of convex and
non-convex learning tasks, we show that the resulting algorithm matches the
performance of SGD or other adaptive approaches with their best settings
obtained through systematic search, and effectively removes the need for
learning rate tuning.
Model-free deep reinforcement learning (RL) algorithms have been demonstrated on a range of challenging decision making and control tasks. However, these methods typically suffer from two major challenges: very high sample complexity and brittle convergence properties, which necessitate meticulous hyperparameter tuning. Both of these challenges severely limit the applicability of such methods to complex, real-world domains. In this paper, we propose soft actor-critic, an off-policy actor-critic deep RL algorithm based on the maximum entropy reinforcement learning framework. In this framework, the actor aims to maximize expected reward while also maximizing entropy - that is, succeed at the task while acting as randomly as possible. Prior deep RL methods based on this framework have been formulated as Q-learning methods. By combining off-policy updates with a stable stochastic actor-critic formulation, our method achieves state-of-the-art performance on a range of continuous control benchmark tasks, outperforming prior on-policy and off-policy methods. Furthermore, we demonstrate that, in contrast to other off-policy algorithms, our approach is very stable, achieving very similar performance across different random seeds.
We propose a new family of policy gradient methods for reinforcement learning, which alternate between sampling data through interaction with the environment, and optimizing a "surrogate" objective function using stochastic gradient ascent. Whereas standard policy gradient methods perform one gradient update per data sample, we propose a novel objective function that enables multiple epochs of minibatch updates. The new methods, which we call proximal policy optimization (PPO), have some of the benefits of trust region policy optimization (TRPO), but they are much simpler to implement, more general, and have better sample complexity (empirically). Our experiments test PPO on a collection of benchmark tasks, including simulated robotic locomotion and Atari game playing, and we show that PPO outperforms other online policy gradient methods, and overall strikes a favorable balance between sample complexity, simplicity, and wall-time.
OpenAI Gym is a toolkit for reinforcement learning research. It includes a growing collection of benchmark problems that expose a common interface, and a website where people can share their results and compare the performance of algorithms. This whitepaper discusses the components of OpenAI Gym and the design decisions that went into the software.
Deeper neural networks are more difficult to train. We present a residual
learning framework to ease the training of networks that are substantially
deeper than those used previously. We explicitly reformulate the layers as
learning residual functions with reference to the layer inputs, instead of
learning unreferenced functions. We provide comprehensive empirical evidence
showing that these residual networks are easier to optimize, and can gain
accuracy from considerably increased depth. On the ImageNet dataset we evaluate
residual nets with a depth of up to 152 layers---8x deeper than VGG nets but
still having lower complexity. An ensemble of these residual nets achieves
3.57% error on the ImageNet test set. This result won the 1st place on the
ILSVRC 2015 classification task. We also present analysis on CIFAR-10 with 100
and 1000 layers.
The depth of representations is of central importance for many visual
recognition tasks. Solely due to our extremely deep representations, we obtain
a 28% relative improvement on the COCO object detection dataset. Deep residual
nets are foundations of our submissions to ILSVRC & COCO 2015 competitions,
where we also won the 1st places on the tasks of ImageNet detection, ImageNet
localization, COCO detection, and COCO segmentation.
2014 In this paper we consider deterministic policy gradient algorithms for reinforcement learning with continuous actions. The deterministic policy gradient has a particularly appealing form: it is the expected gradient of the action-value function. This simple form means that the deterministic policy gradient can be estimated much more efficiently than the usual stochastic policy gradient. To ensure adequate exploration, we introduce an off-policy actor-critic algorithm that learns a deterministic target policy from an exploratory behaviour policy. We demonstrate that deterministic policy gradient algorithms can significantly outperform their stochastic counterparts in high-dimensional action spaces.
Despite significant recent advances in the field of face recognition,
implementing face verification and recognition efficiently at scale presents
serious challenges to current approaches. In this paper we present a system,
called FaceNet, that directly learns a mapping from face images to a compact
Euclidean space where distances directly correspond to a measure of face
similarity. Once this space has been produced, tasks such as face recognition,
verification and clustering can be easily implemented using standard techniques
with FaceNet embeddings as feature vectors.
Our method uses a deep convolutional network trained to directly optimize the
embedding itself, rather than an intermediate bottleneck layer as in previous
deep learning approaches. To train, we use triplets of roughly aligned matching
/ non-matching face patches generated using a novel online triplet mining
method. The benefit of our approach is much greater representational
efficiency: we achieve state-of-the-art face recognition performance using only
128-bytes per face.
On the widely used Labeled Faces in the Wild (LFW) dataset, our system
achieves a new record accuracy of 99.63%. On YouTube Faces DB it achieves
95.12%. Our system cuts the error rate in comparison to the best published
result by 30% on both datasets.
Of several responses made to the same situation, those which are accompanied or closely followed by satisfaction to the animal will, other things being equal, be more firmly connected with the situation, so that, when it recurs, they will be more likely to recur; those which are accompanied or closely followed by discomfort to the animal will, other things being equal, have their connections with that situation weakened, so that, when it recurs, they will be less likely to occur. The greater the satisfaction or discomfort, the greater the strengthening or weakening of the bond. (Thorndike, 1911) The idea of learning to make appropriate responses based on reinforcing events has its roots in early psychological theories such as Thorndike's "law of effect" (quoted above). Although several important contributions were made in the 1950s, 1960s and 1970s by illustrious luminaries such as Bellman, Minsky, Klopf and others (Farley and Clark, 1954; Bellman, 1957; Minsky, 1961; Samuel, 1963; Michie and Chambers, 1968; Grossberg, 1975; Klopf, 1982), the last two decades have wit- nessed perhaps the strongest advances in the mathematical foundations of reinforcement learning, in addition to several impressive demonstrations of the performance of reinforcement learning algo- rithms in real world tasks. The introductory book by Sutton and Barto, two of the most influential and recognized leaders in the field, is therefore both timely and welcome. The book is divided into three parts. In the first part, the authors introduce and elaborate on the es- sential characteristics of the reinforcement learning problem, namely, the problem of learning "poli- cies" or mappings from environmental states to actions so as to maximize the amount of "reward"
A disciplined approach to neural network hyperparameters
- L N Smith