We study off-policy evaluation (OPE) of contextual bandit policies for large discrete action spaces where conventional importance-weighting approaches suffer from excessive variance. To circumvent this variance issue, we propose a new estimator, called OffCEM, that is based on the conjunct effect model (CEM), a novel decomposition of the causal effect into a cluster effect and a residual effect. OffCEM applies importance weighting only to action clusters and addresses the residual causal effect through model-based reward estimation. We show that the proposed estimator is unbiased under a new condition, called local correctness, which only requires that the residual-effect model preserves the relative expected reward differences of the actions within each cluster. To best leverage the CEM and local correctness, we also propose a new two-step procedure for performing model-based estimation that minimizes bias in the first step and variance in the second step. We find that the resulting OffCEM estimator substantially improves bias and variance compared to a range of conventional estimators. Experiments demonstrate that OffCEM provides substantial improvements in OPE especially in the presence of many actions.
Stony Brook University（石溪大学）；Princeton University（普林斯顿大学）；University of Illinois at Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校）；Northwestern University（西北大学）
This paper extends off-policy reinforcement learning to the multi-agent case in which a set of networked agents communicating with their neighbors according to a time-varying graph collaboratively evaluates and improves a target policy while following a distinct behavior policy. To this end, the paper develops a multi-agent version of emphatic temporal difference learning for off-policy policy evaluation, and proves convergence under linear function approximation. The paper then leverages this result, in conjunction with a novel multi-agent off-policy policy gradient theorem and recent work in…
Monotonic policy improvement and off-policy learning are two main desirable properties for reinforcement learning algorithms. In this paper, by lower bounding the performance difference of two policies, we show that the monotonic policy improvement is guaranteed from on- and off-policy mixture samples. An optimization procedure which applies the proposed bound can be regarded as an off-policy natural policy gradient method. In order to support the theoretical result, we provide a trust region policy optimization method using experience replay as a naive application of our bound, and evaluate i…
We study the problem of off-policy policy optimization in Markov decision processes, and develop a novel off-policy policy gradient method. Prior off-policy policy gradient approaches have generally ignored the mismatch between the distribution of states visited under the behavior policy used to collect data, and what would be the distribution of states under the learned policy. Here we build on recent progress for estimating the ratio of the state distributions under behavior and evaluation policies for policy evaluation, and present an off-policy policy gradient optimization technique that c…
Facebook AI Research（脸书人工智能研究院）；McGill University（麦吉尔大学）
Off-policy deep reinforcement learning (RL) algorithms are incapable of learning solely from batch offline data without online interactions with the environment, due to the phenomenon known as \textit{extrapolation error}. This is often due to past data available in the replay buffer that may be quite different from the data distribution under the current policy. We argue that most off-policy learning methods fundamentally suffer from a \textit{state distribution shift} due to the mismatch between the state visitation distribution of the data collected by the behavior and target policies. This…
We propose and analyze an alternate approach to off-policy multi-step temporal difference learning, in which off-policy returns are corrected with the current Q-function in terms of rewards, rather than with the target policy in terms of transition probabilities. We prove that such approximate corrections are sufficient for off-policy convergence both in policy evaluation and control, provided certain conditions. These conditions relate the distance between the target and behavior policies, the eligibility trace parameter and the discount factor, and formalize an underlying tradeoff in off-pol…
We propose a new objective, the counterfactual objective, unifying existing objectives for off-policy policy gradient algorithms in the continuing reinforcement learning (RL) setting. Compared to the commonly used excursion objective, which can be misleading about the performance of the target policy when deployed, our new objective better predicts such performance. We prove the Generalized Off-Policy Policy Gradient Theorem to compute the policy gradient of the counterfactual objective and use an emphatic approach to get an unbiased sample from this policy gradient, yielding the Generalized O…
Multi-Agent RL or MARL is one of the complex problems in Autonomous Driving literature that hampers the release of fully-autonomous vehicles today. Several simulators have been in iteration after their inception to mitigate the problem of complex scenarios with multiple agents in Autonomous Driving. One such simulator--SMARTS, discusses the importance of cooperative multi-agent learning. For this problem, we discuss two approaches--MAPPO and MADDPG, which are based on-policy and off-policy RL approaches. We compare our results with the state-of-the-art results for this challenge and discuss th…
To accumulate knowledge and improve its policy of behaviour, a reinforcement learning agent can learn `off-policy' about policies that differ from the policy used to generate its experience. This is important to learn counterfactuals, or because the experience was generated out of its own control. However, off-policy learning is non-trivial, and standard reinforcement-learning algorithms can be unstable and divergent. In this paper we discuss a novel family of off-policy prediction algorithms which are convergent by construction. The idea is to first learn on-policy about the data-generating b…
Stanford University（斯坦福大学）；Harvard University（哈佛大学）；Cambridge University（剑桥大学）；Imperial College London（帝国理工学院）
We study the problem of off-policy policy evaluation (OPPE) in RL. In contrast to prior work, we consider how to estimate both the individual policy value and average policy value accurately. We draw inspiration from recent work in causal reasoning, and propose a new finite sample generalization error bound for value estimates from MDP models. Using this upper bound as an objective, we develop a learning algorithm of an MDP model with a balanced representation, and show that our approach can yield substantially lower MSE in common synthetic benchmarks and a HIV treatment simulation domain.
Google DeepMind（谷歌DeepMind）；Vrije Universiteit Brussel（布鲁塞尔自由大学）
In this work, we take a fresh look at some old and new algorithms for off-policy, return-based reinforcement learning. Expressing these in a common form, we derive a novel algorithm, Retrace($λ$), with three desired properties: (1) it has low variance; (2) it safely uses samples collected from any behaviour policy, whatever its degree of "off-policyness"; and (3) it is efficient as it makes the best use of samples collected from near on-policy behaviour policies. We analyze the contractive nature of the related operator under both off-policy policy evaluation and control settings and derive on…
We consider the problem of off-policy evaluation in Markov decision processes. Off-policy evaluation is the task of evaluating the expected return of one policy with data generated by a different, behavior policy. Importance sampling is a technique for off-policy evaluation that re-weights off-policy returns to account for differences in the likelihood of the returns between the two policies. In this paper, we study importance sampling with an estimated behavior policy where the behavior policy estimate comes from the same set of data used to compute the importance sampling estimate. We find t…
Off-policy learning is a framework for evaluating and optimizing policies without deploying them, from data collected by another policy. Real-world environments are typically non-stationary and the offline learned policies should adapt to these changes. To address this challenge, we study the novel problem of off-policy optimization in piecewise-stationary contextual bandits. Our proposed solution has two phases. In the offline learning phase, we partition logged data into categorical latent states and learn a near-optimal sub-policy for each state. In the online deployment phase, we adaptivel…
UC Santa Barbara（加州大学圣巴巴拉分校）；Salesforce Research（赛富时研究院）
The problem of Offline Policy Evaluation (OPE) in Reinforcement Learning (RL) is a critical step towards applying RL in real-life applications. Existing work on OPE mostly focus on evaluating a fixed target policy $π$, which does not provide useful bounds for offline policy learning as $π$ will then be data-dependent. We address this problem by simultaneously evaluating all policies in a policy class $Π$ -- uniform convergence in OPE -- and obtain nearly optimal error bounds for a number of global / local policy classes. Our results imply that the model-based planning achieves an optimal episo…
McGill University（麦吉尔大学）；Mila Québec AI Institute（米拉魁北克人工智能研究所）
Many practical applications of reinforcement learning constrain agents to learn from a fixed batch of data which has already been gathered, without offering further possibility for data collection. In this paper, we demonstrate that due to errors introduced by extrapolation, standard off-policy deep reinforcement learning algorithms, such as DQN and DDPG, are incapable of learning with data uncorrelated to the distribution under the current policy, making them ineffective for this fixed batch setting. We introduce a novel class of off-policy algorithms, batch-constrained reinforcement learning…
In real-world decision making tasks, it is critical for data-driven reinforcement learning methods to be both stable and sample efficient. On-policy methods typically generate reliable policy improvement throughout training, while off-policy methods make more efficient use of data through sample reuse. In this work, we combine the theoretically supported stability benefits of on-policy algorithms with the sample efficiency of off-policy algorithms. We develop policy improvement guarantees that are suitable for the off-policy setting, and connect these bounds to the clipping mechanism used in P…
This paper addresses the problem of policy selection in domains with abundant logged data, but with a restricted interaction budget. Solving this problem would enable safe evaluation and deployment of offline reinforcement learning policies in industry, robotics, and recommendation domains among others. Several off-policy evaluation (OPE) techniques have been proposed to assess the value of policies using only logged data. However, there is still a big gap between the evaluation by OPE and the full online evaluation. Yet, large amounts of online interactions are often not possible in practice.…
For an autonomous agent, executing a poor policy may be costly or even dangerous. For such agents, it is desirable to determine confidence interval lower bounds on the performance of any given policy without executing said policy. Current methods for exact high confidence off-policy evaluation that use importance sampling require a substantial amount of data to achieve a tight lower bound. Existing model-based methods only address the problem in discrete state spaces. Since exact bounds are intractable for many domains we trade off strict guarantees of safety for more data-efficient approximat…
The pandemic caused by the SARS-CoV-2 virus has exposed many flaws in the decision-making strategies used to distribute resources to combat global health crises. In this paper, we leverage reinforcement learning and optimization to improve upon the allocation strategies for various resources. In particular, we consider a problem where a central controller must decide where to send testing kits to learn about the uncertain states of the world (active learning); then, use the new information to construct beliefs about the states and decide where to allocate resources. We propose a general model …
Off-OAB: Off-Policy Policy Gradient Method with Optimal Action-Dependent Baseline
School of Software, Shandong University（山东大学软件学院）；School of Artificial Intelligence, Peking University（北京大学人工智能学院）；College of Computer Science and Technology, Zhejiang University（浙江大学计算机科学与技术学院）
We study the problem of off-policy critic evaluation in several variants of value-based off-policy actor-critic algorithms. Off-policy actor-critic algorithms require an off-policy critic evaluation step, to estimate the value of the new policy after every policy gradient update. Despite enormous success of off-policy policy gradients on control tasks, existing general methods suffer from high variance and instability, partly because the policy improvement depends on gradient of the estimated value function. In this work, we present a new way of off-policy policy evaluation in actor-critic, ba…
On-policy reinforcement learning (RL) algorithms have high sample complexity while off-policy algorithms are difficult to tune. Merging the two holds the promise to develop efficient algorithms that generalize across diverse environments. It is however challenging in practice to find suitable hyper-parameters that govern this trade off. This paper develops a simple algorithm named P3O that interleaves off-policy updates with on-policy updates. P3O uses the effective sample size between the behavior policy and the target policy to control how far they can be from each other and does not introdu…
Auburn University（奥本大学）；University of Iowa（爱荷华大学）；Facebook AI Research（Facebook 人工智能研究院）；Huawei Inc.（华为公司）
Off-policy policy optimization is a challenging problem in reinforcement learning (RL). The algorithms designed for this problem often suffer from high variance in their estimators, which results in poor sample efficiency, and have issues with convergence. A few variance-reduced on-policy policy gradient algorithms have been recently proposed that use methods from stochastic optimization to reduce the variance of the gradient estimate in the REINFORCE algorithm. However, these algorithms are not designed for the off-policy setting and are memory-inefficient, since they need to collect and stor…
Policy gradient methods are widely used for control in reinforcement learning, particularly for the continuous action setting. There have been a host of theoretically sound algorithms proposed for the on-policy setting, due to the existence of the policy gradient theorem which provides a simplified form for the gradient. In off-policy learning, however, where the behaviour policy is not necessarily attempting to learn and follow the optimal policy for the given task, the existence of such a theorem has been elusive. In this work, we solve this open problem by providing the first off-policy pol…
Off-policy learning refers to the problem of learning the value function of a way of behaving, or policy, while following a different policy. Gradient-based off-policy learning algorithms, such as GTD and TDC/GQ, converge even when using function approximation and incremental updates. However, they have been developed for the case of a fixed behavior policy. In control problems, one would like to adapt the behavior policy over time to become more greedy with respect to the existing value function. In this paper, we present the first gradient-based learning algorithms for this problem, which re…
Off-policy stochastic actor-critic methods rely on approximating the stochastic policy gradient in order to derive an optimal policy. One may also derive the optimal policy by approximating the action-value gradient. The use of action-value gradients is desirable as policy improvement occurs along the direction of steepest ascent. This has been studied extensively within the context of natural gradient actor-critic algorithms and more recently within the context of deterministic policy gradients. In this paper we briefly discuss the off-policy stochastic counterpart to deterministic action-val…
The Chinese University of Hong Kong, Shenzhen（香港中文大学（深圳））；East China Normal University（华东师范大学）；University of Science and Technology of China（中国科学技术大学）；Shandong University（山东大学）；Georgia Institute of Technology（佐治亚理工学院）
We consider off-policy policy evaluation when the trajectory data are generated by multiple behavior policies. Recent work has shown the key role played by the state or state-action stationary distribution corrections in the infinite horizon context for off-policy policy evaluation. We propose estimated mixture policy (EMP), a novel class of partially policy-agnostic methods to accurately estimate those quantities. With careful analysis, we show that EMP gives rise to estimates with reduced variance for estimating the state stationary distribution correction while it also offers a useful induc…
Department of Mechanical Engineering and Materials Science, Duke University（杜克大学机械工程与材料科学系）；Duke University（杜克大学）
In this paper, we propose a distributed off-policy actor critic method to solve multi-agent reinforcement learning problems. Specifically, we assume that all agents keep local estimates of the global optimal policy parameter and update their local value function estimates independently. Then, we introduce an additional consensus step to let all the agents asymptotically achieve agreement on the global optimal policy function. The convergence analysis of the proposed algorithm is provided and the effectiveness of the proposed algorithm is validated using a distributed resource allocation exampl…
This work studies the problem of batch off-policy evaluation for Reinforcement Learning in partially observable environments. Off-policy evaluation under partial observability is inherently prone to bias, with risk of arbitrarily large errors. We define the problem of off-policy evaluation for Partially Observable Markov Decision Processes (POMDPs) and establish what we believe is the first off-policy evaluation result for POMDPs. In addition, we formulate a model in which observed and unobserved variables are decoupled into two dynamic processes, called a Decoupled POMDP. We show how off-poli…
We offer an experimental benchmark and empirical study for off-policy policy evaluation (OPE) in reinforcement learning, which is a key problem in many safety critical applications. Given the increasing interest in deploying learning-based methods, there has been a flurry of recent proposals for OPE method, leading to a need for standardized empirical analyses. Our work takes a strong focus on diversity of experimental design to enable stress testing of OPE methods. We provide a comprehensive benchmarking suite to study the interplay of different attributes on method performance. We distill th…
University of Oxford（牛津大学）；University of Alberta（阿尔伯塔大学）
We consider off-policy policy evaluation with function approximation (FA) in average-reward MDPs, where the goal is to estimate both the reward rate and the differential value function. For this problem, bootstrapping is necessary and, along with off-policy learning and FA, results in the deadly triad (Sutton & Barto, 2018). To address the deadly triad, we propose two novel algorithms, reproducing the celebrated success of Gradient TD algorithms in the average-reward setting. In terms of estimating the differential value function, the algorithms are the first convergent off-policy linear funct…
Most prior approaches to offline reinforcement learning (RL) have taken an iterative actor-critic approach involving off-policy evaluation. In this paper we show that simply doing one step of constrained/regularized policy improvement using an on-policy Q estimate of the behavior policy performs surprisingly well. This one-step algorithm beats the previously reported results of iterative algorithms on a large portion of the D4RL benchmark. The one-step baseline achieves this strong performance while being notably simpler and more robust to hyperparameters than previously proposed iterative alg…
Cambridge University（剑桥大学）；Harvard University（哈佛大学）；Stanford University（斯坦福大学）；Imperial College London（帝国理工学院）
In this work, we consider the problem of estimating a behaviour policy for use in Off-Policy Policy Evaluation (OPE) when the true behaviour policy is unknown. Via a series of empirical studies, we demonstrate how accurate OPE is strongly dependent on the calibration of estimated behaviour policy models: how precisely the behaviour policy is estimated from data. We show how powerful parametric models such as neural networks can result in highly uncalibrated behaviour policy models on a real-world medical dataset, and illustrate how a simple, non-parametric, k-nearest neighbours model produces …
Offline-Boosted Actor-Critic: Adaptively Blending Optimal Historical Behaviors in Deep Off-Policy RL
Tsinghua University（清华大学）；University of Hamburg（汉堡大学）；Shanghai Artificial Intelligence Laboratory（上海人工智能实验室）；Shanghai Qi Zhi Institute（上海期智研究院）；Institute for AI Industry Research, Tsinghua University（清华大学人工智能产业研究院）
Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）；School of Artificial Intelligence, University of Chinese Academy of Sciences（中国科学院大学人工智能学院）
Offline reinforcement learning (RL), also known as batch RL, aims to optimize policy from a large pre-recorded dataset without interaction with the environment. This setting offers the promise of utilizing diverse, pre-collected datasets to obtain policies without costly, risky, active exploration. However, commonly used off-policy algorithms based on Q-learning or actor-critic perform poorly when learning from a static dataset. In this work, we study why off-policy RL methods fail to learn in offline setting from the value function view, and we propose a novel offline RL algorithm that we cal…
Indian Institute of Science（印度科学学院）；Indian Institute of Technology Dharwad（印度理工学院达拉瓦德分校）
Learning optimal behavior from existing data is one of the most important problems in Reinforcement Learning (RL). This is known as "off-policy control" in RL where an agent's objective is to compute an optimal policy based on the data obtained from the given policy (known as the behavior policy). As the optimal policy can be very different from the behavior policy, learning optimal behavior is very hard in the "off-policy" setting compared to the "on-policy" setting where new data from the policy updates will be utilized in learning. This work proposes an off-policy natural actor-critic algor…
Learning the value function of a given policy (target policy) from the data samples obtained from a different policy (behavior policy) is an important problem in Reinforcement Learning (RL). This problem is studied under the setting of off-policy prediction. Temporal Difference (TD) learning algorithms are a popular class of algorithms for solving the prediction problem. TD algorithms with linear function approximation are shown to be convergent when the samples are generated from the target policy (known as on-policy prediction). However, it has been well established in the literature that of…
Policy constraint methods to offline reinforcement learning (RL) typically utilize parameterization or regularization that constrains the policy to perform actions within the support set of the behavior policy. The elaborative designs of parameterization methods usually intrude into the policy networks, which may bring extra inference cost and cannot take full advantage of well-established online methods. Regularization methods reduce the divergence between the learned policy and the behavior policy, which may mismatch the inherent density-based definition of support set thereby failing to avo…
Amazon Web Services（亚马逊云科技）；University of Pennsylvania（宾夕法尼亚大学）
This paper prescribes a suite of techniques for off-policy Reinforcement Learning (RL) that simplify the training process and reduce the sample complexity. First, we show that simple Deterministic Policy Gradient works remarkably well as long as the overestimation bias is controlled. This is contrast to existing literature which creates sophisticated off-policy techniques. Second, we pinpoint training instabilities, typical of off-policy algorithms, to the greedy policy update step; existing solutions such as delayed policy updates do not mitigate this issue. Third, we show that ideas in the p…
The principal contribution of this paper is a conceptual framework for off-policy reinforcement learning, based on conditional expectations of importance sampling ratios. This framework yields new perspectives and understanding of existing off-policy algorithms, and reveals a broad space of unexplored algorithms. We theoretically analyse this space, and concretely investigate several algorithms that arise from this framework.
University of California Berkeley（加州大学伯克利分校）；Google Brain（谷歌大脑）；DeepMind（深度思维）
In this work, we consider the problem of model selection for deep reinforcement learning (RL) in real-world environments. Typically, the performance of deep RL algorithms is evaluated via on-policy interactions with the target environment. However, comparing models in a real-world environment for the purposes of early stopping or hyperparameter tuning is costly and often practically infeasible. This leads us to examine off-policy policy evaluation (OPE) in such settings. We focus on OPE for value-based methods, which are of particular interest in deep RL, with applications like robotics, where…
Mila（米拉研究所）；Université de Montréal（蒙特利尔大学）；McGill University（麦吉尔大学）；Facebook AI Research（脸书人工智能研究院）
Trust Region Policy Optimization (TRPO) and Proximal Policy Optimization (PPO) are among the most successful policy gradient approaches in deep reinforcement learning (RL). While these methods achieve state-of-the-art performance across a wide range of challenging tasks, there is room for improvement in the stabilization of the policy learning and how the off-policy data are used. In this paper we revisit the theoretical foundations of these algorithms and propose a new algorithm which stabilizes the policy improvement through a proximity term that constrains the discounted state-action visita…
Policy gradient (PG) estimation becomes a challenge when we are not allowed to sample with the target policy but only have access to a dataset generated by some unknown behavior policy. Conventional methods for off-policy PG estimation often suffer from either significant bias or exponentially large variance. In this paper, we propose the double Fitted PG estimation (FPG) algorithm. FPG can work with an arbitrary policy parameterization, assuming access to a Bellman-complete value function class. In the case of linear value function approximation, we provide a tight finite-sample upper bound o…
North Carolina State University（北卡罗来纳州立大学）；University of Alberta（阿尔伯塔大学）；University of New Mexico（新墨西哥大学）；University of Michigan（密歇根大学）
We develop an off-policy actor-critic algorithm for learning an optimal policy from a training set composed of data from multiple individuals. This algorithm is developed with a view towards its use in mobile health.
The policy gradient theorem states that the policy should only be updated in states that are visited by the current policy, which leads to insufficient planning in the off-policy states, and thus to convergence to suboptimal policies. We tackle this planning issue by extending the policy gradient theory to policy updates with respect to any state density. Under these generalized policy updates, we show convergence to optimality under a necessary and sufficient condition on the updates' state densities, and thereby solve the aforementioned planning issue. We also prove asymptotic convergence ra…
Natural policy gradient (NPG) methods are among the most widely used policy optimization algorithms in contemporary reinforcement learning. This class of methods is often applied in conjunction with entropy regularization -- an algorithmic scheme that encourages exploration -- and is closely related to soft policy iteration and trust region policy optimization. Despite the empirical success, the theoretical underpinnings for NPG methods remain limited even for the tabular setting. This paper develops $\textit{non-asymptotic}$ convergence guarantees for entropy-regularized NPG methods under sof…
FiveAI（FiveAI公司）；The University of Edinburgh（爱丁堡大学）
We propose a lifelong learning architecture, the Neural Computer Agent (NCA), where a Reinforcement Learning agent is paired with a predictive model of the environment learned by a Differentiable Neural Computer (DNC). The agent and DNC model are trained in conjunction iteratively. The agent improves its policy in simulations generated by the DNC model and rolls out the policy to the live environment, collecting experiences in new portions or tasks of the environment for further learning. Experiments in two synthetic environments show that DNC models can continually learn from pixels alone to …
Off-policy learning in dynamic decision problems is essential for providing strong evidence that a new policy is better than the one in use. But how can we prove superiority without testing the new policy? To answer this question, we introduce the G-SCOPE algorithm that evaluates a new policy based on data generated by the existing policy. Our algorithm is both computationally and sample efficient because it greedily learns to exploit factored structure in the dynamics of the environment. We present a finite sample analysis of our approach and show through experiments that the algorithm scales…
McCombs School of Business（麦库姆斯商学院）；The University of Texas at Austin（德克萨斯大学奥斯汀分校）
Offline reinforcement learning (RL) extends the paradigm of classical RL algorithms to purely learning from static datasets, without interacting with the underlying environment during the learning process. A key challenge of offline RL is the instability of policy training, caused by the mismatch between the distribution of the offline data and the undiscounted stationary state-action distribution of the learned policy. To avoid the detrimental impact of distribution mismatch, we regularize the undiscounted stationary distribution of the current policy towards the offline data during the polic…
