Evolution Strategy (ES) is a powerful black-box optimization technique based on the idea of natural evolution. In each of its iterations, a key step entails ranking candidate solutions based on some fitness score. For an ES method in Reinforcement Learning (RL), this ranking step requires evaluating multiple policies. This is presently done via on-policy approaches: each policy's score is estimated by interacting several times with the environment using that policy. This leads to a lot of wasteful interactions since, once the ranking is done, only the data associated with the top-ranked policies is used for subsequent learning. To improve sample efficiency, we propose a novel off-policy alternative for ranking, based on a local approximation for the fitness function. We demonstrate our idea in the context of a state-of-the-art ES method called the Augmented Random Search (ARS). Simulations in MuJoCo tasks show that, compared to the original ARS, our off-policy variant has similar running times for reaching reward thresholds but needs only around 70% as much data. It also outperforms the recent Trust Region ES. We believe our ideas should be extendable to other ES methods as well.
相關內容
We study the design of sample-efficient algorithms for reinforcement learning in the presence of rich, high-dimensional observations, formalized via the Block MDP problem. Existing algorithms suffer from either 1) computational intractability, 2) strong statistical assumptions that are not necessarily satisfied in practice, or 3) suboptimal sample complexity. We address these issues by providing the first computationally efficient algorithm that attains rate-optimal sample complexity with respect to the desired accuracy level, with minimal statistical assumptions. Our algorithm, MusIK, combines systematic exploration with representation learning based on multi-step inverse kinematics, a learning objective in which the aim is to predict the learner's own action from the current observation and observations in the (potentially distant) future. MusIK is simple and flexible, and can efficiently take advantage of general-purpose function approximation. Our analysis leverages several new techniques tailored to non-optimistic exploration algorithms, which we anticipate will find broader use.
Modern statistical analysis often encounters high dimensional models but with limited sample sizes. This makes the target data based statistical estimation very difficult. Then how to borrow information from another large sized source data for more accurate target model estimation becomes an interesting problem. This leads to the useful idea of transfer learning. Various estimation methods in this regard have been developed recently. In this work, we study transfer learning from a different perspective. Specifically, we consider here the problem of testing for transfer learning sufficiency. By transfer learning sufficiency (denoted as the null hypothesis), we mean that, with the help of the source data, the useful information contained in the feature vectors of the target data can be sufficiently extracted for predicting the interested target response. Therefore, the rejection of the null hypothesis implies that information useful for prediction remains in the feature vectors of the target data and thus calls for further exploration. To this end, we develop a novel testing procedure and a centralized and standardized test statistic, whose asymptotic null distribution is analytically derived. Simulation studies are presented to demonstrate the finite sample performance of the proposed method. A deep learning related real data example is presented for illustration purpose.
Reinforcement learning (RL) is an area of significant research interest, and safe RL in particular is attracting attention due to its ability to handle safety-driven constraints that are crucial for real-world applications of RL algorithms. This work proposes a novel approach to RL training, called control invariant set (CIS) enhanced RL, which leverages the benefits of CIS to improve stability guarantees and sampling efficiency. The approach consists of two learning stages: offline and online. In the offline stage, CIS is incorporated into the reward design, initial state sampling, and state reset procedures. In the online stage, RL is retrained whenever the state is outside of CIS, which serves as a stability criterion. A backup table that utilizes the explicit form of CIS is obtained to ensure the online stability. To evaluate the proposed approach, we apply it to a simulated chemical reactor. The results show a significant improvement in sampling efficiency during offline training and closed-loop stability in the online implementation.
Artificial neural networks are promising for general function approximation but challenging to train on non-independent or non-identically distributed data due to catastrophic forgetting. The experience replay buffer, a standard component in deep reinforcement learning, is often used to reduce forgetting and improve sample efficiency by storing experiences in a large buffer and using them for training later. However, a large replay buffer results in a heavy memory burden, especially for onboard and edge devices with limited memory capacities. We propose memory-efficient reinforcement learning algorithms based on the deep Q-network algorithm to alleviate this problem. Our algorithms reduce forgetting and maintain high sample efficiency by consolidating knowledge from the target Q-network to the current Q-network. Compared to baseline methods, our algorithms achieve comparable or better performance in both feature-based and image-based tasks while easing the burden of large experience replay buffers.
Nowadays, the interpretation of why a machine learning (ML) model makes certain inferences is as crucial as the accuracy of such inferences. Some ML models like the decision tree possess inherent interpretability that can be directly comprehended by humans. Others like artificial neural networks (ANN), however, rely on external methods to uncover the deduction mechanism. SHapley Additive exPlanations (SHAP) is one of such external methods, which requires a background dataset when interpreting ANNs. Generally, a background dataset consists of instances randomly sampled from the training dataset. However, the sampling size and its effect on SHAP remain to be unexplored. In our empirical study on the MIMIC-III dataset, we show that the two core explanations - SHAP values and variable rankings fluctuate when using different background datasets acquired from random sampling, indicating that users cannot unquestioningly trust the one-shot interpretation from SHAP. Luckily, such fluctuation decreases with the increase of the background dataset size. Also, we notice an U-shape in the stability assessment of SHAP variable rankings, demonstrating that SHAP is more reliable in ranking the most and least important variables compared to moderately important ones. Overall, our results suggest that users should take into account how background data affects SHAP results, with improved SHAP stability as the background sample size increases.
In this work, Bayesian inversion with global-local forwards models is used to identify the parameters based on hydraulic fractures in porous media. It is well-known that using Bayesian inversion to identify material parameters is computationally expensive. Although each sampling may take more than one hour, thousands of samples are required to capture the target density. Thus, instead of using fine-scale high-fidelity simulations, we use a non-intrusive global-local (GL) approach for the forward model. We further extend prior work to a large deformation setting based on the Neo-Hookean strain energy function. The resulting framework is described in detail and substantiated with some numerical tests.
Although the population size is an important parameter in evolutionary multi-objective optimization (EMO), little is known about its influence on preference-based EMO (PBEMO). The effectiveness of an unbounded external archive (UA) in PBEMO is also poorly understood, where the UA maintains all non-dominated solutions found so far. In addition, existing methods for postprocessing the UA cannot handle the decision maker's preference information. In this context, first, this paper proposes a preference-based postprocessing method for selecting representative solutions from the UA. Then, we investigate the influence of the UA and population size on the performance of PBEMO algorithms. Our results show that the performance of PBEMO algorithms (e.g., R-NSGA-II) can be significantly improved by using the UA and the proposed method. We demonstrate that a smaller population size than commonly used is effective in most PBEMO algorithms for a small budget of function evaluations, even for many objectives. We found that the size of the region of interest is a less important factor in selecting the population size of the PBEMO algorithms on real-world problems.
Multi-agent Reinforcement Learning (MARL) based traffic signal control becomes a popular research topic in recent years. Most existing MARL approaches tend to learn the optimum control strategies in a decentralised manner by considering communication among neighbouring intersections. However, the non-stationary property in MARL may lead to extremely slow or even failure of convergence, especially when the number of intersections becomes large. One of the existing methods is to partition the whole network into several regions, each of which utilizes a centralized RL framework to speed up the convergence rate. However, there are two challenges for this strategy: the first one is how to get a flexible partition and the second one is how to search for the optimal joint actions for a region of intersections. In this paper, we propose a novel training framework where our region partitioning rule is based on the adjacency between the intersections and propose Dynamic Branching Dueling Q-Network (DBDQ) to search for optimal joint action efficiently and to maximize the regional reward. The experimental results with both real datasets and synthetic datasets demonstrate the superiority of our framework over other existing frameworks.
Bid optimization for online advertising from single advertiser's perspective has been thoroughly investigated in both academic research and industrial practice. However, existing work typically assume competitors do not change their bids, i.e., the wining price is fixed, leading to poor performance of the derived solution. Although a few studies use multi-agent reinforcement learning to set up a cooperative game, they still suffer the following drawbacks: (1) They fail to avoid collusion solutions where all the advertisers involved in an auction collude to bid an extremely low price on purpose. (2) Previous works cannot well handle the underlying complex bidding environment, leading to poor model convergence. This problem could be amplified when handling multiple objectives of advertisers which are practical demands but not considered by previous work. In this paper, we propose a novel multi-objective cooperative bid optimization formulation called Multi-Agent Cooperative bidding Games (MACG). MACG sets up a carefully designed multi-objective optimization framework where different objectives of advertisers are incorporated. A global objective to maximize the overall profit of all advertisements is added in order to encourage better cooperation and also to protect self-bidding advertisers. To avoid collusion, we also introduce an extra platform revenue constraint. We analyze the optimal functional form of the bidding formula theoretically and design a policy network accordingly to generate auction-level bids. Then we design an efficient multi-agent evolutionary strategy for model optimization. Offline experiments and online A/B tests conducted on the Taobao platform indicate both single advertiser's objective and global profit have been significantly improved compared to state-of-art methods.
This paper presents a new multi-objective deep reinforcement learning (MODRL) framework based on deep Q-networks. We propose the use of linear and non-linear methods to develop the MODRL framework that includes both single-policy and multi-policy strategies. The experimental results on two benchmark problems including the two-objective deep sea treasure environment and the three-objective mountain car problem indicate that the proposed framework is able to converge to the optimal Pareto solutions effectively. The proposed framework is generic, which allows implementation of different deep reinforcement learning algorithms in different complex environments. This therefore overcomes many difficulties involved with standard multi-objective reinforcement learning (MORL) methods existing in the current literature. The framework creates a platform as a testbed environment to develop methods for solving various problems associated with the current MORL. Details of the framework implementation can be referred to //www.deakin.edu.au/~thanhthi/drl.htm.
小貼士
登錄享
相關主題
注冊地址： 北京市海淀區羊坊店路18號2幢3層301-191