scholarly journals Policy Search by Target Distribution Learning for Continuous Control

2020 ◽  
Vol 34 (04) ◽  
pp. 6770-6777
Author(s):  
Chuheng Zhang ◽  
Yuanqi Li ◽  
Jian Li
Keyword(s):  
State Of The Art ◽  
Gradient Methods ◽  
Continuous Control ◽  
Policy Network ◽  
Current Policy ◽  
Training Process ◽  
Target Distribution ◽  
Policy Gradient ◽  
And Training ◽  
Better Than

It is known that existing policy gradient methods (such as vanilla policy gradient, PPO, A2C) may suffer from overly large gradients when the current policy is close to deterministic, leading to an unstable training process. We show that such instability can happen even in a very simple environment. To address this issue, we propose a new method, called target distribution learning (TDL), for policy improvement in reinforcement learning. TDL alternates between proposing a target distribution and training the policy network to approach the target distribution. TDL is more effective in constraining the KL divergence between updated policies, and hence leads to more stable policy improvements over iterations. Our experiments show that TDL algorithms perform comparably to (or better than) state-of-the-art algorithms for most continuous control tasks in the MuJoCo environment while being more stable in training.

scholarly journals Deterministic Value-Policy Gradients

2020 ◽  
Vol 34 (04) ◽  
pp. 3316-3323
Author(s):  
Qingpeng Cai ◽  
Ling Pan ◽  
Pingzhong Tang
Keyword(s):  
Reinforcement Learning ◽  
State Of The Art ◽  
Learning Algorithms ◽  
Infinite Horizon ◽  
Gradient Algorithm ◽  
Continuous Control ◽  
Model Bias ◽  
Model Free ◽  
Policy Gradient ◽  
Analytical Gradients

Reinforcement learning algorithms such as the deep deterministic policy gradient algorithm (DDPG) has been widely used in continuous control tasks. However, the model-free DDPG algorithm suffers from high sample complexity. In this paper we consider the deterministic value gradients to improve the sample efficiency of deep reinforcement learning algorithms. Previous works consider deterministic value gradients with the finite horizon, but it is too myopic compared with infinite horizon. We firstly give a theoretical guarantee of the existence of the value gradients in this infinite setting. Based on this theoretical guarantee, we propose a class of the deterministic value gradient algorithm (DVG) with infinite horizon, and different rollout steps of the analytical gradients by the learned model trade off between the variance of the value gradients and the model bias. Furthermore, to better combine the model-based deterministic value gradient estimators with the model-free deterministic policy gradient estimator, we propose the deterministic value-policy gradient (DVPG) algorithm. We finally conduct extensive experiments comparing DVPG with state-of-the-art methods on several standard continuous control benchmarks. Results demonstrate that DVPG substantially outperforms other baselines.

Future Directions in Cognitive Engineering and Naturalistic Decision Making

1995 ◽  
Vol 39 (9) ◽  
pp. 450-453 ◽  
Author(s):  
Mica R. Endsley ◽  
Gary Klein ◽  
David D. Woods ◽  
Philip J. Smith ◽  
Stephen J. Selcon
Keyword(s):  
Decision Making ◽  
State Of The Art ◽  
Cognitive Engineering ◽  
Training Process ◽  
Naturalistic Decision Making ◽  
Future Directions ◽  
Current State ◽  
Near Future ◽  
And Training ◽  
Research Domain

Cognitive Engineering and Naturalistic Decision Making are presented as two related fields of endeavor that seek to understand how people process information and perform within complex systems and to develop ways of applying this knowledge within the design and training process This panel presents an overview of the current state of the art in this research domain and charts paths for needed developments in the field in the near future.

scholarly journals The Successful Ingredients of Policy Gradient Algorithms

2021 ◽  
Author(s):  
Sven Gronauer ◽  
Martin Gottwald ◽  
Klaus Diepold
Keyword(s):  
Reinforcement Learning ◽  
State Of The Art ◽  
Gradient Methods ◽  
Gradient Algorithms ◽  
The Sublime ◽  
Policy Gradient ◽  
Art Performance ◽  
Underlying Mechanisms

Despite the sublime success in recent years, the underlying mechanisms powering the advances of reinforcement learning are yet poorly understood. In this paper, we identify these mechanisms - which we call ingredients - in on-policy policy gradient methods and empirically determine their impact on the learning. To allow an equitable assessment, we conduct our experiments based on a unified and modular implementation. Our results underline the significance of recent algorithmic advances and demonstrate that reaching state-of-the-art performance may not need sophisticated algorithms but can also be accomplished by the combination of a few simple ingredients.

scholarly journals Androgen Receptor Binding Category Prediction with Deep Neural Networks and Structure-, Ligand-, and Statistically Based Features

Molecules ◽  
2021 ◽  
Vol 26 (5) ◽  
pp. 1285
Author(s):  
Alfonso T. García-Sosa
Keyword(s):  
Neural Networks ◽  
Androgen Receptor ◽  
Logistic Model ◽  
Deep Neural Networks ◽  
State Of The Art ◽  
Protein Structures ◽  
Training Set ◽  
Multivariate Logistic Model ◽  
And Training ◽  
Better Than

Substances that can modify the androgen receptor pathway in humans and animals are entering the environment and food chain with the proven ability to disrupt hormonal systems and leading to toxicity and adverse effects on reproduction, brain development, and prostate cancer, among others. State-of-the-art databases with experimental data of human, chimp, and rat effects by chemicals have been used to build machine-learning classifiers and regressors and to evaluate these on independent sets. Different featurizations, algorithms, and protein structures lead to different results, with deep neural networks (DNNs) on user-defined physicochemically relevant features developed for this work outperforming graph convolutional, random forest, and large featurizations. The results show that these user-provided structure-, ligand-, and statistically based features and specific DNNs provided the best results as determined by AUC (0.87), MCC (0.47), and other metrics and by their interpretability and chemical meaning of the descriptors/features. In addition, the same features in the DNN method performed better than in a multivariate logistic model: validation MCC = 0.468 and training MCC = 0.868 for the present work compared to evaluation set MCC = 0.2036 and training set MCC = 0.5364 for the multivariate logistic regression on the full, unbalanced set. Techniques of this type may improve AR and toxicity description and prediction, improving assessment and design of compounds. Source code and data are available on github.

scholarly journals Efficient Robot Skills Learning with Weighted Near-Optimal Experiences Policy Optimization

2021 ◽  
Vol 11 (3) ◽  
pp. 1131
Author(s):  
Liwei Hou ◽  
Hengsheng Wang ◽  
Haoran Zou ◽  
Qun Wang
Keyword(s):  
Reinforcement Learning ◽  
Learning Process ◽  
Gradient Methods ◽  
Policy Network ◽  
Practice Phase ◽  
Network Learning ◽  
Network Parameters ◽  
Model Free ◽  
Policy Gradient ◽  
Skills Learning

Autonomous learning of robotic skills seems to be more natural and more practical than engineered skills, analogous to the learning process of human individuals. Policy gradient methods are a type of reinforcement learning technique which have great potential in solving robot skills learning problems. However, policy gradient methods require too many instances of robot online interaction with the environment in order to learn a good policy, which means lower efficiency of the learning process and a higher likelihood of damage to both the robot and the environment. In this paper, we propose a two-phase (imitation phase and practice phase) framework for efficient learning of robot walking skills, in which we pay more attention to the quality of skill learning and sample efficiency at the same time. The training starts with what we call the first stage or the imitation phase of learning, updating the parameters of the policy network in a supervised learning manner. The training set used in the policy network learning is composed of the experienced trajectories output by the iterative linear Gaussian controller. This paper also refers to these trajectories as near-optimal experiences. In the second stage, or the practice phase, the experiences for policy network learning are collected directly from online interactions, and the policy network parameters are updated with model-free reinforcement learning. The experiences from both stages are stored in the weighted replay buffer, and they are arranged in order according to the experience scoring algorithm proposed in this paper. The proposed framework is tested on a biped robot walking task in a MATLAB simulation environment. The results show that the sample efficiency of the proposed framework is much higher than ordinary policy gradient algorithms. The algorithm proposed in this paper achieved the highest cumulative reward, and the robot learned better walking skills autonomously. In addition, the weighted replay buffer method can be made as a general module for other model-free reinforcement learning algorithms. Our framework provides a new way to combine model-based reinforcement learning with model-free reinforcement learning to efficiently update the policy network parameters in the process of robot skills learning.

scholarly journals Self-Adaptive Double Bootstrapped DDPG

2018 ◽  
Author(s):  
Zhuobin Zheng ◽  
Chun Yuan ◽  
Zhihui Lin ◽  
Yangyang Cheng ◽  
Hanghao Wu
Keyword(s):  
State Of The Art ◽  
High Dimensional ◽  
Continuous Control ◽  
Ensemble Performance ◽  
Policy Gradient ◽  
Art Performance ◽  
Q Values ◽  
Self Adaptive

Deep Deterministic Policy Gradient (DDPG) algorithm has been successful for state-of-the-art performance in high-dimensional continuous control tasks. However, due to the complexity and randomness of the environment, DDPG tends to suffer from inefficient exploration and unstable training. In this work, we propose Self-Adaptive Double Bootstrapped DDPG (SOUP), an algorithm that extends DDPG to bootstrapped actor-critic architecture. SOUP improves the efficiency of exploration by multiple actor heads capturing more potential actions and multiple critic heads evaluating more reasonable Q-values collaboratively. The crux of double bootstrapped architecture is to tackle the fluctuations in performance, caused by multiple heads of spotty capacity varying throughout training. To alleviate the instability, a self-adaptive confidence mechanism is introduced to dynamically adjust the weights of bootstrapped heads and enhance the ensemble performance effectively and efficiently. We demonstrate that SOUP achieves faster learning by at least 45% while improving cumulative reward and stability substantially in comparison to vanilla DDPG on OpenAI Gym's MuJoCo environments.

scholarly journals Only Relevant Information Matters: Filtering Out Noisy Samples To Boost RL

2020 ◽  
Author(s):  
Yannis Flet-Berliac ◽  
Philippe Preux
Keyword(s):  
Value Function ◽  
Positive Impact ◽  
Gradient Methods ◽  
Relevant Information ◽  
Continuous Control ◽  
Gradient Algorithms ◽  
Policy Gradient ◽  
Sampling Procedures ◽  
The Value Function ◽  
Variance Explained

In reinforcement learning, policy gradient algorithms optimize the policy directly and rely on sampling efficiently an environment. Nevertheless, while most sampling procedures are based on direct policy sampling, self-performance measures could be used to improve such sampling prior to each policy update. Following this line of thought, we introduce SAUNA, a method where non-informative transitions are rejected from the gradient update. The level of information is estimated according to the fraction of variance explained by the value function: a measure of the discrepancy between V and the empirical returns. In this work, we use this criterion to select samples that are useful to learn from, and we demonstrate that this selection can significantly improve the performance of policy gradient methods. In this paper: (a) We introduce the SAUNA method to filter transitions. (b) We conduct experiments on a set of benchmark continuous control problems. SAUNA significantly improves performance. (c) We investigate how SAUNA reliably selects samples with the most positive impact on learning and study its improvement on both performance and sample efficiency.

scholarly journals Visual Navigation with Asynchronous Proximal Policy Optimization in Artificial Agents

2020 ◽  
Vol 2020 ◽  
pp. 1-7
Author(s):  
Fanyu Zeng ◽  
Chen Wang
Keyword(s):  
Reinforcement Learning ◽  
Gradient Descent ◽  
Gradient Methods ◽  
Visual Navigation ◽  
Experimental Results ◽  
Artificial Agents ◽  
Policy Gradient ◽  
Policy Optimization ◽  
Navigation Method ◽  
Better Than

Vanilla policy gradient methods suffer from high variance, leading to unstable policies during training, where the policy’s performance fluctuates drastically between iterations. To address this issue, we analyze the policy optimization process of the navigation method based on deep reinforcement learning (DRL) that uses asynchronous gradient descent for optimization. A variant navigation (asynchronous proximal policy optimization navigation, appoNav) is presented that can guarantee the policy monotonic improvement during the process of policy optimization. Our experiments are tested in DeepMind Lab, and the experimental results show that the artificial agents with appoNav perform better than the compared algorithm.

scholarly journals KDAS-ReID: Architecture Search for Person Re-Identification via Distilled Knowledge with Dynamic Temperature

Algorithms ◽  
2021 ◽  
Vol 14 (5) ◽  
pp. 137
Author(s):  
Zhou Lei ◽  
Kangkang Yang ◽  
Kai Jiang ◽  
Shengbo Chen
Keyword(s):  
State Of The Art ◽  
Identification Algorithm ◽  
Student Model ◽  
Deep Convolutional Neural Networks ◽  
Fast Speed ◽  
Training Stage ◽  
Knowledge Distillation ◽  
And Training ◽  
Better Than ◽  
Teacher Model

Person re-Identification(Re-ID) based on deep convolutional neural networks (CNNs) achieves remarkable success with its fast speed. However, prevailing Re-ID models are usually built upon backbones that manually design for classification. In order to automatically design an effective Re-ID architecture, we propose a pedestrian re-identification algorithm based on knowledge distillation, called KDAS-ReID. When the knowledge of the teacher model is transferred to the student model, the importance of knowledge in the teacher model will gradually decrease with the improvement of the performance of the student model. Therefore, instead of applying the distillation loss function directly, we consider using dynamic temperatures during the search stage and training stage. Specifically, we start searching and training at a high temperature and gradually reduce the temperature to 1 so that the student model can better learn from the teacher model through soft targets. Extensive experiments demonstrate that KDAS-ReID performs not only better than other state-of-the-art Re-ID models on three benchmarks, but also better than the teacher model based on the ResNet-50 backbone.

PP-PG: Combining Parameter Perturbation with Policy Gradient Methods for Effective and Efficient Explorations in Deep Reinforcement Learning

2021 ◽  
Vol 12 (3) ◽  
pp. 1-21
Author(s):  
Shilei Li ◽  
Meng Li ◽  
Jiongming Su ◽  
Shaofei Chen ◽  
Zhimin Yuan ◽  
...  
Keyword(s):  
Reinforcement Learning ◽  
Learning Algorithm ◽  
Gradient Methods ◽  
Action Space ◽  
Fine Tuning ◽  
Continuous Control ◽  
Parametric Perturbation ◽  
Gradient Information ◽  
Policy Gradient ◽  
Gradient Based

Efficient and stable exploration remains a key challenge for deep reinforcement learning (DRL) operating in high-dimensional action and state spaces. Recently, a more promising approach by combining the exploration in the action space with the exploration in the parameters space has been proposed to get the best of both methods. In this article, we propose a new iterative and close-loop framework by combining the evolutionary algorithm (EA), which does explorations in a gradient-free manner directly in the parameters space with an actor-critic, and the deep deterministic policy gradient (DDPG) reinforcement learning algorithm, which does explorations in a gradient-based manner in the action space to make these two methods cooperate in a more balanced and efficient way. In our framework, the policies represented by the EA population (the parametric perturbation part) can evolve in a guided manner by utilizing the gradient information provided by the DDPG and the policy gradient part (DDPG) is used only as a fine-tuning tool for the best individual in the EA population to improve the sample efficiency. In particular, we propose a criterion to determine the training steps required for the DDPG to ensure that useful gradient information can be generated from the EA generated samples and the DDPG and EA part can work together in a more balanced way during each generation. Furthermore, within the DDPG part, our algorithm can flexibly switch between fine-tuning the same previous RL-Actor and fine-tuning a new one generated by the EA according to different situations to further improve the efficiency. Experiments on a range of challenging continuous control benchmarks demonstrate that our algorithm outperforms related works and offers a satisfactory trade-off between stability and sample efficiency.

Sign in / Sign up

Export Citation Format

Share Document