Most reinforcement learning (RL) algorithms assume online access to the environment, in which one may readily interleave updates to the policy with experience collection using that policy. However, in many real-world applications such as health, education, dialogue agents, and robotics, the cost or potential risk of deploying a new data-collection policy is high, to the point that it can become prohibitive to update the data-collection policy more than a few times during learning. With this view, we propose a novel concept of deployment efficiency, measuring the number of distinct data-collection policies that are used during policy learning. We observe that na\"{i}vely applying existing model-free offline RL algorithms recursively does not lead to a practical deployment-efficient and sample-efficient algorithm. We propose a novel model-based algorithm, Behavior-Regularized Model-ENsemble (BREMEN) that can effectively optimize a policy offline using 10-20 times fewer data than prior works. Furthermore, the recursive application of BREMEN is able to achieve impressive deployment efficiency while maintaining the same or better sample efficiency, learning successful policies from scratch on simulated robotic environments with only 5-10 deployments, compared to typical values of hundreds to millions in standard RL baselines. Codes and pre-trained models are available at https://github.com/matsuolab/BREMEN .
The offline reinforcement learning (RL) problem, also referred to as batch RL, refers to the setting where a policy must be learned from a dataset of previously collected data, without additional online data collection. In supervised learning, large datasets and complex deep neural networks have fueled impressive progress, but in contrast, conventional RL algorithms must collect large amounts of on-policy data and have had little success leveraging previously collected datasets. As a result, existing RL benchmarks are not well-suited for the offline setting, making progress in this area difficult to measure. To design a benchmark tailored to offline RL, we start by outlining key properties of datasets relevant to applications of offline RL. Based on these properties, we design a set of benchmark tasks and datasets that evaluate offline RL algorithms under these conditions. Examples of such properties include: datasets generated via hand-designed controllers and human demonstrators, multi-objective datasets, where an agent can perform different tasks in the same environment, and datasets consisting of a heterogeneous mix of high-quality and low-quality trajectories. By designing the benchmark tasks and datasets to reflect properties of real-world offline RL problems, our benchmark will focus research effort on methods that drive substantial improvements not just on simulated benchmarks, but ultimately on the kinds of real-world problems where offline RL will have the largest impact.
The offline reinforcement learning (RL) problem, also referred to as batch RL, refers to the setting where a policy must be learned from a dataset of previously collected data, without additional online data collection. In supervised learning, large datasets and complex deep neural networks have fueled impressive progress, but in contrast, conventional RL algorithms must collect large amounts of on-policy data and have had little success leveraging previously collected datasets. As a result, existing RL benchmarks are not well-suited for the offline setting, making progress in this area difficult to measure. To design a benchmark tailored to offline RL, we start by outlining key properties of datasets relevant to applications of offline RL. Based on these properties, we design a set of benchmark tasks and datasets that evaluate offline RL algorithms under these conditions. Examples of such properties include: datasets generated via hand-designed controllers and human demonstrators, multi-objective datasets, where an agent can perform different tasks in the same environment, and datasets consisting of a heterogeneous mix of high-quality and low-quality trajectories. By designing the benchmark tasks and datasets to reflect properties of real-world offline RL problems, our benchmark will focus research effort on methods that drive substantial improvements not just on simulated benchmarks, but ultimately on the kinds of real-world problems where offline RL will have the largest impact.
In batch reinforcement learning (RL), one often constrains a learned policy to be close to the behavior (data-generating) policy, e.g., by constraining the learned action distribution to differ from the behavior policy by some maximum degree that is the same at each state. This can cause batch RL to be overly conservative, unable to exploit large policy changes at frequently-visited, high-confidence states without risking poor performance at sparsely-visited states. To remedy this, we propose residual policies, where the allowable deviation of the learned policy is state-action-dependent. We derive a new for RL method, BRPO, which learns both the policy and allowable deviation that jointly maximize a lower bound on policy performance. We show that BRPO achieves the state-of-the-art performance in a number of tasks.
We review basic concepts of convex duality, focusing on the very general and supremely useful Fenchel-Rockafellar duality. We summarize how this duality may be applied to a variety of reinforcement learning (RL) settings, including policy evaluation or optimization, online or offline learning, and discounted or undiscounted rewards. The derivations yield a number of intriguing results, including the ability to perform policy evaluation and on-policy policy gradient with behavior-agnostic offline data and methods to learn a policy via max-likelihood optimization. Although many of these results have appeared previously in various forms, we provide a unified treatment and perspective on these results, which we hope will enable researchers to better use and apply the tools of convex duality to make further progress in RL.
When performing imitation learning from expert demonstrations, distribution matching is a popular approach, in which one alternates between estimating distribution ratios and then using these ratios as rewards in a standard reinforcement learning (RL) algorithm. Traditionally, estimation of the distribution ratio requires on-policy data, which has caused previous work to either be exorbitantly data-inefficient or alter the original objective in a manner that can drastically change its optimum. In this work, we show how the original distribution ratio estimation objective may be transformed in a principled manner to yield a completely off-policy objective. In addition to the data-efficiency that this provides, we are able to show that this objective also renders the use of a separate RL optimization unnecessary.Rather, an imitation policy may be learned directly from this objective without the use of explicit rewards. We call the resulting algorithm ValueDICE and evaluate it on a suite of popular imitation learning benchmarks, finding that it can achieve state-of-the-art sample efficiency and performance.
In many real-world applications of reinforcement learning (RL), interactions with the environment are limited due to cost or feasibility. This presents a challenge to traditional RL algorithms since the max-return objective involves an expectation over on-policy samples. We introduce a new formulation of max-return optimization that allows the problem to be re-expressed by an expectation over an arbitrary behavior-agnostic and off-policy data distribution. We first derive this result by considering a regularized version of the dual max-return objective before extending our findings to unregularized objectives through the use of a Lagrangian formulation of the linear programming characterization of Q-values. We show that, if auxiliary dual variables of the objective are optimized, then the gradient of the off-policy objective is exactly the on-policy policy gradient, without any use of importance weighting. In addition to revealing the appealing theoretical properties of this approach, we also show that it delivers good practical performance.
In reinforcement learning (RL) research, it is common to assume access to direct online interactions with the environment. However in many real-world applications, access to the environment is limited to a fixed offline dataset of logged experience. In such settings, standard RL algorithms have been shown to diverge or otherwise yield poor performance. Accordingly, recent work has suggested a number of remedies to these issues. In this work, we introduce a general framework, behavior regularized actor critic (BRAC), to empirically evaluate recently proposed methods as well as a number of simple baselines across a variety of offline continuous control tasks. Surprisingly, we find that many of the technical complexities introduced in recent methods are unnecessary to achieve strong performance. Additional ablations provide insights into which design choices matter most in the offline RL setting.