Indian Institute of Technology Madras（印度理工学院马德拉斯分校）；Robert Bosch Center for Data Science and Artificial Intelligence（罗伯特·博世数据科学与人工智能中心）；Facebook Inc（脸书公司）；Intel Corporation（英特尔公司）
Ensemble learning is a very prevalent method employed in machine learning. The relative success of ensemble methods is attributed to their ability to tackle a wide range of instances and complex problems that require different low-level approaches. However, ensemble methods are relatively less popular in reinforcement learning owing to the high sample complexity and computational expense involved in obtaining a diverse ensemble. We present a novel training and model selection framework for model-free reinforcement algorithms that use ensembles of policies obtained from a single training run. These policies are diverse in nature and are learned through directed perturbation of the model parameters at regular intervals. We show that learning and selecting an adequately diverse set of policies is required for a good ensemble while extreme diversity can prove detrimental to overall performance. Selection of an adequately diverse set of policies is done through our novel policy selection framework. We evaluate our approach on challenging discrete and continuous control tasks and also discuss various ensembling strategies. Our framework is substantially sample efficient, computationally inexpensive and is seen to outperform state-of-the-art (SOTA) scores in Atari 2600 and Mujoco.
We propose to use boosted regression trees as a way to compute human-interpretable solutions to reinforcement learning problems. Boosting combines several regression trees to improve their accuracy without significantly reducing their inherent interpretability. Prior work has focused independently on reinforcement learning and on interpretable machine learning, but there has been little progress in interpretable reinforcement learning. Our experimental results show that boosted regression trees compute solutions that are both interpretable and match the quality of leading reinforcement learnin…
University of West Georgia（西佐治亚大学）；Icahn School of Medicine at Mount Sinai（西奈山伊坎医学院）
Heterogeneous ensembles built from the predictions of a wide variety and large number of diverse base predictors represent a potent approach to building predictive models for problems where the ideal base/individual predictor may not be obvious. Ensemble selection is an especially promising approach here, not only for improving prediction performance, but also because of its ability to select a collectively predictive subset, often a relatively small one, of the base predictors. In this paper, we present a set of algorithms that explicitly incorporate ensemble diversity, a known factor influen…
Department of Mathematics, Linn us University, 351 95 Växjö, Sweden
It is well known that ensemble methods often provide enhanced performance in reinforcement learning. In this paper, we explore this concept further by using group-aided training within the distributional reinforcement learning paradigm. Specifically, we propose an extension to categorical reinforcement learning, where distributional learning targets are implicitly based on the total information gathered by an ensemble. We empirically show that this may lead to much more robust initial learning, a stronger individual performance level, and good efficiency on a per-sample basis.
Recently deep reinforcement learning (DRL) has achieved outstanding success on solving many difficult and large-scale RL problems. However the high sample cost required for effective learning often makes DRL unaffordable in resource-limited applications. With the aim of improving sample efficiency and learning performance, we will develop a new DRL algorithm in this paper that seamless integrates entropy-induced and bootstrap-induced techniques for efficient and deep exploration of the learning environment. Specifically, a general form of Tsallis entropy regularizer will be utilized to drive e…
University of Cambridge（剑桥大学）；Alan Turing Institute（艾伦·图灵研究所）；University College London（伦敦大学学院）
The use of ensembles of neural networks (NNs) for the quantification of predictive uncertainty is widespread. However, the current justification is intuitive rather than analytical. This work proposes one minor modification to the normal ensembling methodology, which we prove allows the ensemble to perform Bayesian inference, hence converging to the corresponding Gaussian Process as both the total number of NNs, and the size of each, tend to infinity. This working paper provides early-stage results in a reinforcement learning setting, analysing the practicality of the technique for an ensemble…
Heterogeneous ensembles that can aggregate an unrestricted number and variety of base predictors can effectively address challenging prediction problems. In particular, accurate ensembles that are also parsimonious, i.e., consist of as few base predictors as possible, can help reveal potentially useful knowledge about the target problem domain. Although ensemble selection offers a potential approach to achieving these goals, the currently available algorithms are limited in their abilities. In this paper, we present several algorithms that incorporate ensemble diversity into a reinforcement le…
We propose a new policy iteration theory as an important extension of soft policy iteration and Soft Actor-Critic (SAC), one of the most efficient model free algorithms for deep reinforcement learning. Supported by the new theory, arbitrary entropy measures that generalize Shannon entropy, such as Tsallis entropy and Renyi entropy, can be utilized to properly randomize action selection while fulfilling the goal of maximizing expected long-term rewards. Our theory gives birth to two new algorithms, i.e., Tsallis entropy Actor-Critic (TAC) and Renyi entropy Actor-Critic (RAC). Theoretical analys…
Recent advances of gradient temporal-difference methods allow to learn off-policy multiple value functions in parallel with- out sacrificing convergence guarantees or computational efficiency. This opens up new possibilities for sound ensemble techniques in reinforcement learning. In this work we propose learning an ensemble of policies related through potential-based shaping rewards. The ensemble induces a combination policy by using a voting mechanism on its components. Learning happens in real time, and we empirically show the combination policy to outperform the individual policies of the …
Off-policy deep reinforcement learning (RL) has been successful in a range of challenging domains. However, standard off-policy RL algorithms can suffer from several issues, such as instability in Q-learning and balancing exploration and exploitation. To mitigate these issues, we present SUNRISE, a simple unified ensemble method, which is compatible with various off-policy RL algorithms. SUNRISE integrates two key ingredients: (a) ensemble-based weighted Bellman backups, which re-weight target Q-values based on uncertainty estimates from a Q-ensemble, and (b) an inference method that selects a…
National Tsing Hua University（国立清华大学）；Preferred Networks（优选网络）
Off-policy ensemble reinforcement learning (RL) methods have demonstrated impressive results across a range of RL benchmark tasks. Recent works suggest that directly imitating experts' policies in a supervised manner before or during the course of training enables faster policy improvement for an RL agent. Motivated by these recent insights, we propose Periodic Intra-Ensemble Knowledge Distillation (PIEKD). PIEKD is a learning framework that uses an ensemble of policies to act in the environment while periodically sharing knowledge amongst policies in the ensemble through knowledge distillatio…
Application of ensemble of neural networks is becoming an imminent tool for advancing the state-of-the-art in deep reinforcement learning algorithms. However, training these large numbers of neural networks in the ensemble has an exceedingly high computation cost which may become a hindrance in training large-scale systems. In this paper, we propose DNS: a Determinantal Point Process based Neural Network Sampler that specifically uses k-dpp to sample a subset of neural networks for backpropagation at every training step thus significantly reducing the training time and computation cost. We int…
University of Michigan Ann Arbor（密歇根大学安娜堡分校）；University of Illinois at Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校）
Reinforcement learning (RL) methods have been shown to be capable of learning intelligent behavior in rich domains. However, this has largely been done in simulated domains without adequate focus on the process of building the simulator. In this paper, we consider a setting where we have access to an ensemble of pre-trained and possibly inaccurate simulators (models). We approximate the real environment using a state-dependent linear combination of the ensemble, where the coefficients are determined by the given state features and some unknown parameters. Our proposed algorithm provably learns…
Warwick Medical School, University of Warwick（华威大学华威医学院）；WMG, University of Warwick（华威大学华威制造集团）；Department of Statistics, University of Warwick（华威大学统计系）；Alan Turing Institute（艾伦·图灵研究所）
Offline reinforcement learning agents seek optimal policies from fixed data sets. With environmental interaction prohibited, agents face significant challenges in preventing errors in value estimates from compounding and subsequently causing the learning process to collapse. Uncertainty estimation using ensembles compensates for this by penalising high-variance value estimates, allowing agents to learn robust policies based on data-driven actions. However, the requirement for large ensembles to facilitate sufficient penalisation results in significant computational overhead. In this work, we e…
The current work on reinforcement learning (RL) from demonstrations often assumes the demonstrations are samples from an optimal policy, an unrealistic assumption in practice. When demonstrations are generated by sub-optimal policies or have sparse state-action pairs, policy learned from sub-optimal demonstrations may mislead an agent with incorrect or non-local action decisions. We propose a new method called Local Ensemble and Reparameterization with Split and Merge of expert policies (LEARN-SAM) to improve efficiency and make better use of the sub-optimal demonstrations. First, LEARN-SAM em…
Ensemble and auxiliary tasks are both well known to improve the performance of machine learning models when data is limited. However, the interaction between these two methods is not well studied, particularly in the context of deep reinforcement learning. In this paper, we study the effects of ensemble and auxiliary tasks when combined with the deep Q-learning algorithm. We perform a case study on ATARI games under limited data constraint. Moreover, we derive a refined bias-variance-covariance decomposition to analyze the different ways of learning ensembles and using auxiliary tasks, and use…
Pavlov Institute of Physiology RAS（俄罗斯科学院巴甫洛夫生理学研究所）；State University of Aerospace Instrumentation（国立航空航天仪器大学）
We consider convolutional neural network (CNN) ensemble learning with the objective function inspired by least action principle; it includes resource consumption component. We teach an agent to perceive images through the set of pre-trained classifiers and want the resulting dynamically configured system to unfold the computational graph with the trajectory that refers to the minimal number of operations and maximal expected accuracy. The proposed agent's architecture implicitly approximates the required classifier selection function with the help of reinforcement learning. Our experimental re…
Inverse reinforcement learning (IRL) is the task of finding a reward function that generates a desired optimal policy for a given Markov Decision Process (MDP). This paper develops an information-theoretic lower bound for the sample complexity of the finite state, finite action IRL problem. A geometric construction of $β$-strict separable IRL problems using spherical codes is considered. Properties of the ensemble size as well as the Kullback-Leibler divergence between the generated trajectories are derived. The resulting ensemble is then used along with Fano's inequality to derive a sample co…
University of Lille（里尔大学）；CNRS（法国国家科学研究中心）；TotalEnergies SE（道达尔能源公司）
Deep Reinforcement Learning (or just "RL") is gaining popularity for industrial and research applications. However, it still suffers from some key limits slowing down its widespread adoption. Its performance is sensitive to initial conditions and non-determinism. To unlock those challenges, we propose a procedure for building ensembles of RL agents to efficiently build better local decisions toward long-term cumulated rewards. For the first time, hundreds of experiments have been done to compare different ensemble constructions procedures in 2 electricity control environments. We discovered an…
Integrating model-free and model-based approaches in reinforcement learning has the potential to achieve the high performance of model-free algorithms with low sample complexity. However, this is difficult because an imperfect dynamics model can degrade the performance of the learning algorithm, and in sufficiently complex environments, the dynamics model will almost always be imperfect. As a result, a key challenge is to combine model-based approaches with model-free learning in such a way that errors in the model do not degrade performance. We propose stochastic ensemble value expansion (STE…
Pontifical Catholic University of Rio de Janeiro（里约热内卢天主教大学）
Reinforcement learning is a promising paradigm for learning robot control, allowing complex control policies to be learned without requiring a dynamics model. However, even state of the art algorithms can be difficult to tune for optimum performance. We propose employing an ensemble of multiple reinforcement learning agents, each with a different set of hyperparameters, along with a mechanism for choosing the best performing set(s) on-line. In the literature, the ensemble technique is used to improve performance in general, but the current work specifically addresses decreasing the hyperparame…
Mila（米拉研究所）；Université de Montréal（蒙特利尔大学）；University of California, Berkeley（加州大学伯克利分校）
Reinforcement learning agents that operate in diverse and complex environments can benefit from the structured decomposition of their behavior. Often, this is addressed in the context of hierarchical reinforcement learning, where the aim is to decompose a policy into lower-level primitives or options, and a higher-level meta-policy that triggers the appropriate behaviors for a given situation. However, the meta-policy must still produce appropriate decisions in all states. In this work, we propose a policy design that decomposes into primitives, similarly to hierarchical reinforcement learning…
Resolving the exploration-exploitation trade-off remains a fundamental problem in the design and implementation of reinforcement learning (RL) algorithms. In this paper, we focus on model-free RL using the epsilon-greedy exploration policy, which despite its simplicity, remains one of the most frequently used forms of exploration. However, a key limitation of this policy is the specification of $\varepsilon$. In this paper, we provide a novel Bayesian perspective of $\varepsilon$ as a measure of the uniformity of the Q-value function. We introduce a closed-form Bayesian model update based on B…
University of Massachusetts Amherst（马萨诸塞大学阿默斯特分校）；Indian Institute of Technology Madras（印度理工学院马德拉斯分校）
Deep Reinforcement Learning has been able to achieve amazing successes in a variety of domains from video games to continuous control by trying to maximize the cumulative reward. However, most of these successes rely on algorithms that require a large amount of data to train in order to obtain results on par with human-level performance. This is not feasible if we are to deploy these systems on real world tasks and hence there has been an increased thrust in exploring data efficient algorithms. To this end, we propose the Shared Learning framework aimed at making $Q$-ensemble algorithms data-e…
Traffic signal control is a significant part of the construction of intelligent transportation. An efficient traffic signal control strategy can reduce traffic congestion, improve urban road traffic efficiency and facilitate people's lives. Existing reinforcement learning approaches for traffic signal control mainly focus on learning through a separate neural network. Such an independent neural network may fall into the local optimum of the training results. Worse more, the collected data can only be sampled once, so the data utilization rate is low. Therefore, we propose the Random Ensemble D…
OpenAI；University of California, Berkeley（加州大学伯克利分校）
We show how an ensemble of $Q^*$-functions can be leveraged for more effective exploration in deep reinforcement learning. We build on well established algorithms from the bandit setting, and adapt them to the $Q$-learning setting. We propose an exploration strategy based on upper-confidence bounds (UCB). Our experiments show significant gains on the Atari benchmark.
Deep ensembles have been shown to extend the positive effect seen in typical ensemble learning to neural networks and to reinforcement learning (RL). However, there is still much to be done to improve the efficiency of such ensemble models. In this work, we present Diverse Ensembles for Fast Transfer in RL (DEFT), a new ensemble-based method for reinforcement learning in highly multimodal environments and improved transfer to unseen environments. The algorithm is broken down into two main phases: training of ensemble members, and synthesis (or fine-tuning) of the ensemble members into a policy…
It is challenging for reinforcement learning (RL) algorithms to succeed in real-world applications like financial trading and logistic system due to the noisy observation and environment shifting between training and evaluation. Thus, it requires both high sample efficiency and generalization for resolving real-world tasks. However, directly applying typical RL algorithms can lead to poor performance in such scenarios. Considering the great performance of ensemble methods on both accuracy and generalization in supervised learning (SL), we design a robust and applicable method named Ensemble Pr…
Zenseact AB（Zenseact公司）；Chalmers University of Technology（查尔姆斯理工大学）；Scool INRIA Lille-Nord Europe（法国国家信息与自动化研究所里尔-北欧洲Scool团队）；CRIStAL, CNRS（法国国家科学研究中心CRIStAL实验室）；University of Neuchatel（纳沙泰尔大学）；University of Oslo（奥斯陆大学）
In this paper, we consider risk-sensitive sequential decision-making in Reinforcement Learning (RL). Our contributions are two-fold. First, we introduce a novel and coherent quantification of risk, namely composite risk, which quantifies the joint effect of aleatory and epistemic risk during the learning process. Existing works considered either aleatory or epistemic risk individually, or as an additive combination. We prove that the additive formulation is a particular case of the composite risk when the epistemic risk measure is replaced with expectation. Thus, the composite risk is more sen…
Atlantic Technological University（大西洋理工大学）；Al Yamamah University（亚马玛大学）；Lahore Leads University（拉合尔利兹大学）；National University of Technology（国立理工大学）
Hybrid FSO/RF system requires an efficient FSO and RF link switching mechanism to improve the system capacity by realizing the complementary benefits of both the links. The dynamics of network conditions, such as fog, dust, and sand storms compound the link switching problem and control complexity. To address this problem, we initiate the study of deep reinforcement learning (DRL) for link switching of hybrid FSO/RF systems. Specifically, in this work, we focus on actor-critic called Actor/Critic-FSO/RF and Deep-Q network (DQN) called DQN-FSO/RF for FSO/RF link switching under atmospheric turb…
RLAE: Reinforcement Learning-Assisted Ensemble for LLMs
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）
This paper presents an algorithmic framework for learning robust policies in asymmetric imperfect-information games, where the joint reward could depend on the uncertain opponent type (a private information known only to the opponent itself and its ally). In order to maximize the reward, the protagonist agent has to infer the opponent type through agent modeling. We use multiagent reinforcement learning (MARL) to learn opponent models through self-play, which captures the full strategy interaction and reasoning between agents. However, agent policies learned from self-play can suffer from mutu…
Carnegie Mellon University（卡内基梅隆大学）；Georgia Institute of Technology（佐治亚理工学院）
The ability for an agent to continuously learn new skills without catastrophically forgetting existing knowledge is of critical importance for the development of generally intelligent agents. Most methods devised to address this problem depend heavily on well-defined task boundaries, and thus depend on human supervision. Our task-agnostic method, Self-Activating Neural Ensembles (SANE), uses a modular architecture designed to avoid catastrophic forgetting without making any such assumptions. At the beginning of each trajectory, a module in the SANE ensemble is activated to determine the agent'…
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）；School of Computer Science Carnegie Mellon University（卡内基梅隆大学计算机学院）
During the training of a reinforcement learning (RL) agent, the distribution of training data is non-stationary as the agent's behavior changes over time. Therefore, there is a risk that the agent is overspecialized to a particular distribution and its performance suffers in the larger picture. Ensemble RL can mitigate this issue by learning a robust policy. However, it suffers from heavy computational resource consumption due to the newly introduced value and policy functions. In this paper, to avoid the notorious resources consumption issue, we design a novel and simple ensemble deep RL fram…
Unit commitment (UC) is a fundamental problem in the day-ahead electricity market, and it is critical to solve UC problems efficiently. Mathematical optimization techniques like dynamic programming, Lagrangian relaxation, and mixed-integer quadratic programming (MIQP) are commonly adopted for UC problems. However, the calculation time of these methods increases at an exponential rate with the amount of generators and energy resources, which is still the main bottleneck in industry. Recent advances in artificial intelligence have demonstrated the capability of reinforcement learning (RL) to sol…
IBM Research AI（IBM研究AI）；Amazon Web Services（亚马逊云科技）
Air traffic control is an example of a highly challenging operational problem that is readily amenable to human expertise augmentation via decision support technologies. In this paper, we propose a new intelligent decision making framework that leverages multi-agent reinforcement learning (MARL) to dynamically suggest adjustments of aircraft speeds in real-time. The goal of the system is to enhance the ability of an air traffic controller to provide effective guidance to aircraft to avoid air traffic congestion, near-miss situations, and to improve arrival timeliness. We develop a novel deep e…
Uncertainty-Penalized Reinforcement Learning from Human Feedback with Diverse Reward LoRA Ensembles
National University of Defense Technology（国防科技大学）；State Key Laboratory of Complex & Critical Software Environment（复杂与关键软件环境国家重点实验室）；Harbin Institute of Technology (Shenzhen)（哈尔滨工业大学（深圳））；Peng Cheng Laboratory（鹏城实验室）
Advancing Robustness in Deep Reinforcement Learning with an Ensemble Defense Approach
AImotion Bavaria, Technische Hochschule Ingolstadt（巴伐利亚AImotion、英格尔施泰特技术大学）；School of Computation, Information and Technology, TU Munich（计算、信息与技术学院，慕尼黑技术大学）
Model-based Reinforcement Learning (MBRL) has been widely adapted due to its sample efficiency. However, existing worst-case regret analysis typically requires optimistic planning, which is not realistic in general. In contrast, motivated by the theory, empirical study utilizes ensemble of models, which achieve state-of-the-art performance on various testing environments. Such deviation between theory and empirical study leads us to question whether randomized model ensemble guarantee optimism, and hence the optimal worst-case regret? This paper partially answers such question from the perspec…
Tsinghua University（清华大学）；Tencent AI Lab（腾讯人工智能实验室）
Model-based deep reinforcement learning has achieved success in various domains that require high sample efficiencies, such as Go and robotics. However, there are some remaining issues, such as planning efficient explorations to learn more accurate dynamic models, evaluating the uncertainty of the learned models, and more rational utilization of models. To mitigate these issues, we present MEEE, a model-ensemble method that consists of optimistic exploration and weighted exploitation. During exploration, unlike prior methods directly selecting the optimal action that maximizes the expected acc…
