Recent work on policy learning from observational data has highlighted the importance of efficient policy evaluation and has proposed reductions to weighted (cost-sensitive) classification. But, efficient policy evaluation need not yield efficient estimation of policy parameters. We consider the estimation problem given by a weighted surrogate-loss classification reduction of policy learning with any score function, either direct, inverse-propensity weighted, or doubly robust. We show that, under a correct specification assumption, the weighted classification formulation need not be efficient for policy parameters. We draw a contrast to actual (possibly weighted) binary classification, where correct specification implies a parametric model, while for policy learning it only implies a semiparametric model. In light of this, we instead propose an estimation approach based on generalized method of moments, which is efficient for the policy parameters. We propose a particular method based on recent developments on solving moment problems using neural networks and demonstrate the efficiency and regret benefits of this method empirically.
Indiana University Bloomington（印第安纳大学伯明顿分校）；Northwestern University（西北大学）；The University of Texas at Austin（德克萨斯大学奥斯汀分校）；University of Illinois at Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校）
When learning from a batch of logged bandit feedback, the discrepancy between the policy to be learned and the off-policy training data imposes statistical and computational challenges. Unlike classical supervised learning and online learning settings, in batch contextual bandit learning, one only has access to a collection of logged feedback from the actions taken by a historical policy, and expect to learn a policy that takes good actions in possibly unseen contexts. Such a batch learning setting is ubiquitous in online and interactive systems, such as ad platforms and recommendation systems…
In this paper, we propose surrogate agent-environment interface (SAEI) in reinforcement learning. We also state that learning based on probability surrogate agent-environment interface provides optimal policy of task agent-environment interface. We introduce surrogate probability action and develop the probability surrogate action deterministic policy gradient (PSADPG) algorithm based on SAEI. This algorithm enables continuous control of discrete action. The experiments show PSADPG achieves the performance of DQN in certain tasks with the stochastic optimal policy nature in the initial trainin…
Robotics Innovation Center, DFKI GmbH（德国人工智能研究中心有限公司机器人创新中心）
Contextual policy search (CPS) is a class of multi-task reinforcement learning algorithms that is particularly useful for robotic applications. A recent state-of-the-art method is Contextual Covariance Matrix Adaptation Evolution Strategies (C-CMA-ES). It is based on the standard black-box optimization algorithm CMA-ES. There are two useful extensions of CMA-ES that we will transfer to C-CMA-ES and evaluate empirically: ACM-ES, which uses a comparison-based surrogate model, and aCMA-ES, which uses an active update of the covariance matrix. We will show that improvements with these methods can …
Thanks to their versatility, ease of deployment and high-performance, surrogate models have become staple tools in the arsenal of uncertainty quantification (UQ). From local interpolants to global spectral decompositions, surrogates are characterised by their ability to efficiently emulate complex computational models based on a small set of model runs used for training. An inherent limitation of many surrogate models is their susceptibility to the curse of dimensionality, which traditionally limits their applicability to a maximum of $\mathcal{O}(10^2)$ input dimensions. We present a novel ap…
High-dimensional policies, such as those represented by neural networks, cannot be reasonably interpreted by humans. This lack of interpretability reduces the trust users have in policy behavior, limiting their use to low-impact tasks such as video games. Unfortunately, many methods rely on neural network representations for effective learning. In this work, we propose a method to build predictable policy trees as surrogates for policies such as neural networks. The policy trees are easily human interpretable and provide quantitative predictions of future behavior. We demonstrate the performan…
Meta-materials are an important emerging class of engineered materials in which complex macroscopic behaviour--whether electromagnetic, thermal, or mechanical--arises from modular substructure. Simulation and optimization of these materials are computationally challenging, as rich substructures necessitate high-fidelity finite element meshes to solve the governing PDEs. To address this, we leverage parametric modular structure to learn component-level surrogates, enabling cheaper high-fidelity simulation. We use a neural network to model the stored potential energy in a component given boundar…
A general class of surrogate functions for stable and efficient reinforcement learning
Simon Fraser University（西蒙弗雷泽大学）；Google Brain（谷歌大脑）；Mila, Université de Montréal（米拉-蒙特利尔大学）；TU Munich（慕尼黑工业大学）；Amii, University of Alberta（阿尔伯塔大学人工智能机器智能研究所）；DeepMind（深度思维）；Microsoft Research（微软研究院）；Mila, McGill（米拉-麦吉尔大学）
University of Oxford（牛津大学）；Microsoft Research（微软研究院）
Trust Region Policy Optimization (TRPO) is an iterative method that simultaneously maximizes a surrogate objective and enforces a trust region constraint over consecutive policies in each iteration. The combination of the surrogate objective maximization and the trust region enforcement has been shown to be crucial to guarantee a monotonic policy improvement. However, solving a trust-region-constrained optimization problem can be computationally intensive as it requires many steps of conjugate gradient and a large number of on-policy samples. In this paper, we show that the trust region constr…
The study of decentralized learning or independent learning in cooperative multi-agent reinforcement learning has a history of decades. Recently empirical studies show that independent PPO (IPPO) can obtain good performance, close to or even better than the methods of centralized training with decentralized execution, in several benchmarks. However, decentralized actor-critic with convergence guarantee is still open. In this paper, we propose \textit{decentralized policy optimization} (DPO), a decentralized actor-critic algorithm with monotonic improvement and convergence guarantee. We derive …
Reinforcement learning is a promising paradigm for solving sequential decision-making problems, but low data efficiency and weak generalization across tasks are bottlenecks in real-world applications. Model-based meta reinforcement learning addresses these issues by learning dynamics and leveraging knowledge from prior experience. In this paper, we take a closer look at this framework, and propose a new Thompson-sampling based approach that consists of a new model to identify task dynamics together with an amortized policy optimization step. We show that our model, called a graph structured su…
Recent policy optimization approaches have achieved substantial empirical success by constructing surrogate optimization objectives. The Approximate Policy Iteration objective (Schulman et al., 2015a; Kakade and Langford, 2002) has become a standard optimization target for reinforcement learning problems. Using this objective in practice requires an estimator of the advantage function. Policy optimization methods such as those proposed in Schulman et al. (2015b) estimate the advantages using a parametric critic. In this work we establish conditions under which the parametric approximation of t…
Peking University（北京大学）；Zhejiang University（浙江大学）；Tsinghua University（清华大学）；Netease Games AI Lab（网易游戏人工智能实验室）
Safe reinforcement learning (RL) is still very challenging since it requires the agent to consider both return maximization and safe exploration. In this paper, we propose CUP, a Conservative Update Policy algorithm with a theoretical safety guarantee. We derive the CUP based on the new proposed performance bounds and surrogate functions. Although using bounds as surrogate functions to design safe RL algorithms have appeared in some existing works, we develop them at least three aspects: (i) We provide a rigorous theoretical analysis to extend the surrogate functions to generalized advantage e…
Physics-Informed Geometric Operators to Support Surrogate, Dimension Reduction and Generative Models for Engineering Design
BAR Technologies（BAR科技公司）；Nazarbayev University（纳扎尔巴耶夫大学）；University of Strathclyde（斯特拉斯克莱德大学）；Foundation for Research & Technology Hellas (FORTH)（希腊研究与技术基金会）；Texas A&M University（德克萨斯农工大学）
Department of Computer Science, University of Oxford（牛津大学计算机科学系）；Microsoft Research（微软研究院）
Proximal Policy Optimization (PPO) methods learn a policy by iteratively performing multiple mini-batch optimization epochs of a surrogate objective with one set of sampled data. Ratio clipping PPO is a popular variant that clips the probability ratios between the target policy and the policy used to collect samples. Ratio clipping yields a pessimistic estimate of the original surrogate objective, and has been shown to be crucial for strong performance. We show in this paper that such ratio clipping may not be a good option as it can fail to effectively bound the ratios. Instead, one can direc…
As the scales of neural networks increase, techniques that enable them to run with low computational cost and energy efficiency are required. From such demands, various efficient neural network paradigms, such as spiking neural networks (SNNs) or binary neural networks (BNNs), have been proposed. However, they have sticky drawbacks, such as degraded inference accuracy and latency. To solve these problems, we propose a single-step spiking neural network (S$^3$NN), an energy-efficient neural network with low computational cost and high precision. The proposed S$^3$NN processes the information be…
In this paper, we point out a fundamental property of the objective in reinforcement learning, with which we can reformulate the policy gradient objective into a perceptron-like loss function, removing the need to distinguish between on and off policy training. Namely, we posit that it is sufficient to only update a policy $π$ for cases that satisfy the condition $A(\fracπμ-1)\leq0$, where $A$ is the advantage, and $μ$ is another policy. Furthermore, we show via theoretic derivation that a perceptron-like loss function matches the clipped surrogate objective for PPO. With our new formulation, …
Imperial College London（帝国理工学院）；University of Oxford（牛津大学）；University of Copenhagen（哥本哈根大学）
Epidemic models are powerful tools in understanding infectious disease. However, as they increase in size and complexity, they can quickly become computationally intractable. Recent progress in modelling methodology has shown that surrogate models can be used to emulate complex epidemic models with a high-dimensional parameter space. We show that deep sequence-to-sequence (seq2seq) models can serve as accurate surrogates for complex epidemic models with sequence based model parameters, effectively replicating seasonal and long-term transmission dynamics. Once trained, our surrogate can predict…
In this paper, a new sequential surrogate-based optimization (SSBO) algorithm is developed, which aims to improve the global search ability and local search efficiency for the global optimization of expensive black-box models. The proposed method involves three basic sub-criteria to infill new samples asynchronously to balance the global exploration and local exploitation. First, to capture the promising possible global optimal region, searching for the global optimum with genetic algorithm (GA) based on the current surrogate models of the objective and constraint functions. Second, to infill …
Darden School of Business, University of Virginia（弗吉尼亚大学达顿商学院）
We study an off-policy contextual pricing problem where the seller has access to samples of prices that customers were previously offered, whether they purchased at that price, and auxiliary features describing the customer and/or item being sold. This is in contrast to the well-studied setting in which samples of the customer's valuation (willingness to pay) are observed. In our setting, the observed data is influenced by the previous pricing policy, and we do not know how customers would have responded to alternative prices. We introduce suitable loss functions for this setting that can be d…
We propose a novel actor-critic, model-free reinforcement learning algorithm which employs a Bayesian method of parameter space exploration to solve environments. A Gaussian process is used to learn the expected return of a policy given the policy's parameters. The system is trained by updating the parameters using gradient descent on a new surrogate loss function consisting of the Proximal Policy Optimization 'Clipped' loss function and a bonus term representing the expected improvement acquisition function given by the Gaussian process. This new method is shown to be comparable to and at tim…
RTL Nederland B.V.（RTL荷兰公司）；University of Amsterdam（阿姆斯特丹大学）
Multiclass multilabel classification is the task of attributing multiple labels to examples via predictions. Current models formulate a reduction of the multilabel setting into either multiple binary classifications or multiclass classification, allowing for the use of existing loss functions (sigmoid, cross-entropy, logistic, etc.). Multilabel classification reductions do not accommodate for the prediction of varying numbers of labels per example and the underlying losses are distant estimates of the performance metrics. We propose a loss function, sigmoidF1, which is an approximation of the …
Baidu Research（百度研究院）；Dartmouth College（达特茅斯学院）；University of Illinois at Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校）
Recent advances in policy gradient methods and deep learning have demonstrated their applicability for complex reinforcement learning problems. However, the variance of the performance gradient estimates obtained from the simulation is often excessive, leading to poor sample efficiency. In this paper, we apply the stochastic variance reduced gradient descent (SVRG) to model-free policy gradient to significantly improve the sample-efficiency. The SVRG estimation is incorporated into a trust-region Newton conjugate gradient framework for the policy optimization. On several Mujoco tasks, our meth…
For reinforcement learning on complex stochastic systems where many factors dynamically impact the output trajectories, it is desirable to effectively leverage the information from historical samples collected in previous iterations to accelerate policy optimization. Classical experience replay allows agents to remember by reusing historical observations. However, the uniform reuse strategy that treats all observations equally overlooks the relative importance of different samples. To overcome this limitation, we propose a general variance reduction based experience replay (VRER) framework tha…
Instituto de Física de Cantabria (CSIC-UC)（坎塔布里亚物理研究所（CSIC-UC））
Continuous high frequency water quality monitoring is becoming a critical task to support water management. Despite the advancements in sensor technologies, certain variables cannot be easily and/or economically monitored in-situ and in real time. In these cases, surrogate measures can be used to make estimations by means of data-driven models. In this work, variables that are commonly measured in-situ are used as surrogates to estimate the concentrations of nutrients in a rural catchment and in an urban one, making use of machine learning models, specifically Random Forests. The results are c…
Off-policy reinforcement learning aims to leverage experience collected from prior policies for sample-efficient learning. However, in practice, commonly used off-policy approximate dynamic programming methods based on Q-learning and actor-critic methods are highly sensitive to the data distribution, and can make only limited progress without collecting additional on-policy data. As a step towards more robust off-policy algorithms, we study the setting where the off-policy experience is fixed and there is no further interaction with the environment. We identify bootstrapping error as a key sou…
The University of Tokyo（东京大学）；Technical University of Darmstadt（达姆施塔特工业大学）；RIKEN（日本理化学研究所）
Direct contextual policy search methods learn to improve policy parameters and simultaneously generalize these parameters to different context or task variables. However, learning from high-dimensional context variables, such as camera images, is still a prominent problem in many real-world tasks. A naive application of unsupervised dimensionality reduction methods to the context variables, such as principal component analysis, is insufficient as task-relevant input may be ignored. In this paper, we propose a contextual policy search method in the model-based relative entropy stochastic search…
Academy for Advanced Interdisciplinary Studies, Peking University（北京大学前沿交叉学科研究院）；School of Mathematical Sciences, Peking University（北京大学数学科学学院）
Regularized MDPs serve as a smooth version of original MDPs. However, biased optimal policy always exists for regularized MDPs. Instead of making the coefficientλof regularized term sufficiently small, we propose an adaptive reduction scheme for λ to approximate optimal policy of the original MDP. It is shown that the iteration complexity for obtaining anε-optimal policy could be reduced in comparison with setting sufficiently smallλ. In addition, there exists strong duality connection between the reduction method and solving the original MDP directly, from which we can derive more adaptive re…
University of Illinois Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校）
We show that on-policy policy gradient (PG) and its variance reduction variants can be derived by taking finite difference of function evaluations supplied by estimators from the importance sampling (IS) family for off-policy evaluation (OPE). Starting from the doubly robust (DR) estimator (Jiang & Li, 2016), we provide a simple derivation of a very general and flexible form of PG, which subsumes the state-of-the-art variance reduction technique (Cheng et al., 2019) as its special case and immediately hints at further variance reduction opportunities overlooked by existing literature. We analy…
Policy gradient methods have demonstrated success in reinforcement learning tasks that have high-dimensional continuous state and action spaces. However, policy gradient methods are also notoriously sample inefficient. This can be attributed, at least in part, to the high variance in estimating the gradient of the task objective with Monte Carlo methods. Previous research has endeavored to contend with this problem by studying control variates (CVs) that can reduce the variance of estimates without introducing bias, including the early use of baselines, state dependent CVs, and the more recent…
University of California, Los Angeles（加利福尼亚大学洛杉矶分校）
Improving the sample efficiency in reinforcement learning has been a long-standing research problem. In this work, we aim to reduce the sample complexity of existing policy gradient methods. We propose a novel policy gradient algorithm called SRVR-PG, which only requires $O(1/ε^{3/2})$ episodes to find an $ε$-approximate stationary point of the nonconcave performance function $J(\boldsymbolθ)$ (i.e., $\boldsymbolθ$ such that $\|\nabla J(\boldsymbolθ)\|_2^2\leqε$). This sample complexity improves the existing result $O(1/ε^{5/3})$ for stochastic variance reduced policy gradient algorithms by a …
UC Berkeley（加州大学伯克利分校）；University of Washington（华盛顿大学）；OpenAI（开放人工智能研究中心）
Policy gradient methods have enjoyed great success in deep reinforcement learning but suffer from high variance of gradient estimates. The high variance problem is particularly exasperated in problems with long horizons or high-dimensional action spaces. To mitigate this issue, we derive a bias-free action-dependent baseline for variance reduction which fully exploits the structural form of the stochastic policy itself and does not make any additional assumptions about the MDP. We demonstrate and quantify the benefit of the action-dependent baseline through both theoretical analysis as well as…
