The concept of utilizing multi-step returns for updating value functions has been adopted in deep reinforcement learning (DRL) for a number of years. Updating value functions with different backup lengths provides advantages in different aspects, including bias and variance of value estimates, convergence speed, and exploration behavior of the agent. Conventional methods such as TD-lambda leverage these advantages by using a target value equivalent to an exponential average of different step returns. Nevertheless, integrating step returns into a single target sacrifices the diversity of the advantages offered by different step return targets. To address this issue, we propose Mixture Bootstrapped DQN (MB-DQN) built on top of bootstrapped DQN, and uses different backup lengths for different bootstrapped heads. MB-DQN enables heterogeneity of the target values that is unavailable in approaches relying only on a single target value. As a result, it is able to maintain the advantages offered by different backup lengths. In this paper, we first discuss the motivational insights through a simple maze environment. In order to validate the effectiveness of MB-DQN, we perform experiments on the Atari 2600 benchmark environments, and demonstrate the performance improvement of MB-DQN over a number of baseline methods. We further provide a set of ablation studies to examine the impacts of different design configurations of MB-DQN.
Improving the Diversity of Bootstrapped DQN by Replacing Priors With Noise
University of Oslo（奥斯陆大学）；University of Agder（阿格德大学）；Oslo Metropolitan University（奥斯陆城市大学）；Norwegian University of Science and Technology（挪威科技大学）；Oslo University Hospital（奥斯陆大学医院）
The deep Q-network (DQN) and return-based reinforcement learning are two promising algorithms proposed in recent years. DQN brings advances to complex sequential decision problems, while return-based algorithms have advantages in making use of sample trajectories. In this paper, we propose a general framework to combine DQN and most of the return-based reinforcement learning algorithms, named R-DQN. We show the performance of traditional DQN can be improved effectively by introducing return-based reinforcement learning. In order to further improve the R-DQN, we design a strategy with two measu…
National Taiwan University（国立台湾大学）；RIKEN Center for Advanced Intelligence Project（理化学研究所先进智能项目中心）；The University of Tokyo（东京大学）
Recent research has shown that although Reinforcement Learning (RL) can benefit from expert demonstration, it usually takes considerable efforts to obtain enough demonstration. The efforts prevent training decent RL agents with expert demonstration in practice. In this work, we propose Active Reinforcement Learning with Demonstration (ARLD), a new framework to streamline RL in terms of demonstration efforts by allowing the RL agent to query for demonstration actively during training. Under the framework, we propose Active Deep Q-Network, a novel query strategy which adapts to the dynamically-c…
The goal of reinforcement learning algorithms is to estimate and/or optimise the value function. However, unlike supervised learning, no teacher or oracle is available to provide the true value function. Instead, the majority of reinforcement learning algorithms estimate and/or optimise a proxy for the value function. This proxy is typically based on a sampled and bootstrapped approximation to the true value function, known as a return. The particular choice of return is one of the chief components determining the nature of the algorithm: the rate at which future rewards are discounted; when a…
We propose a method for meta-learning reinforcement learning algorithms by searching over the space of computational graphs which compute the loss function for a value-based model-free RL agent to optimize. The learned algorithms are domain-agnostic and can generalize to new environments not seen during training. Our method can both learn from scratch and bootstrap off known existing algorithms, like DQN, enabling interpretable modifications which improve performance. Learning from scratch on simple classical control and gridworld tasks, our method rediscovers the temporal-difference (TD) algo…
In this work, we build on recent advances in distributional reinforcement learning to give a generally applicable, flexible, and state-of-the-art distributional variant of DQN. We achieve this by using quantile regression to approximate the full quantile function for the state-action return distribution. By reparameterizing a distribution over the sample space, this yields an implicitly defined return distribution and gives rise to a large class of risk-sensitive policies. We demonstrate improved performance on the 57 Atari 2600 games in the ALE, and use our algorithm's implicitly defined dist…
This paper introduces a method for constructing an upper bound for exploration policy using either the weighted variance of return sequences or the weighted temporal difference (TD) error. We demonstrate that the variance of the return sequence for a specific state-action pair is an important information source that can be leveraged to guide exploration in reinforcement learning. The intuition is that fluctuation in the return sequence indicates greater uncertainty in the near future returns. This divergence occurs because of the cyclic nature of value-based reinforcement learning; the evolvin…
Indian Institute of Technology, Madras（印度理工学院马德拉斯分校）
Reinforcement Learning (RL) can model complex behavior policies for goal-directed sequential decision making tasks. A hallmark of RL algorithms is Temporal Difference (TD) learning: value function for the current state is moved towards a bootstrapped target that is estimated using next state's value function. $λ$-returns generalize beyond 1-step returns and strike a balance between Monte Carlo and TD learning methods. While lambda-returns have been extensively studied in RL, they haven't been explored a lot in Deep RL. This paper's first contribution is an exhaustive benchmarking of lambda-ret…
The University of Hong Kong（香港大学）；University of Ioannina（约阿尼纳大学）；Tsinghua University（清华大学）；Tencent Inc.（腾讯公司）
In this paper, we propose a Deep Reinforcement Learning (RL) framework for task arrangement, which is a critical problem for the success of crowdsourcing platforms. Previous works conduct the personalized recommendation of tasks to workers via supervised learning methods. However, the majority of them only consider the benefit of either workers or requesters independently. In addition, they cannot handle the dynamic environment and may produce sub-optimal results. To address these issues, we utilize Deep Q-Network (DQN), an RL-based method combined with a neural network to estimate the expecte…
We present a unifying framework for designing and analysing distributional reinforcement learning (DRL) algorithms in terms of recursively estimating statistics of the return distribution. Our key insight is that DRL algorithms can be decomposed as the combination of some statistical estimator and a method for imputing a return distribution consistent with that set of statistics. With this new understanding, we are able to provide improved analyses of existing DRL algorithms as well as construct a new algorithm (EDRL) based upon estimation of the expectiles of the return distribution. We compa…
We study reinforcement learning (RL) in high dimensional episodic Markov decision processes (MDP). We consider value-based RL when the optimal Q-value is a linear function of d-dimensional state-action feature representation. For instance, in deep-Q networks (DQN), the Q-value is a linear function of the feature representation layer (output layer). We propose two algorithms, one based on optimism, LINUCB, and another based on posterior sampling, LINPSRL. We guarantee frequentist and Bayesian regret upper bounds of O(d sqrt{T}) for these two algorithms, where T is the number of episodes. We ext…
DeepMind；University of Cambridge（剑桥大学）；Google Brain（谷歌大脑）
In reinforcement learning an agent interacts with the environment by taking actions and observing the next state and reward. When sampled probabilistically, these state transitions, rewards, and actions can all induce randomness in the observed long-term return. Traditionally, reinforcement learning algorithms average over this randomness to estimate the value function. In this paper, we build on recent work advocating a distributional approach to reinforcement learning in which the distribution over returns is modeled explicitly instead of only estimating the mean. That is, we examine methods…
Khoury College of Computer Sciences, Northeastern University（东北大学库里计算机科学学院）
Return caching is a recent strategy that enables efficient minibatch training with multistep estimators (e.g. the λ-return) for deep reinforcement learning. By precomputing return estimates in sequential batches and then storing the results in an auxiliary data structure for later sampling, the average computation spent per estimate can be greatly reduced. Still, the efficiency of return caching could be improved, particularly with regard to its large memory usage and repetitive data copies. We propose a new data structure, the Virtual Replay Cache (VRC), to address these shortcomings. When le…
Khoury College of Computer Sciences（胡里计算机学院）；Northeastern University（东北大学）
Modern deep reinforcement learning methods have departed from the incremental learning required for eligibility traces, rendering the implementation of the $λ$-return difficult in this context. In particular, off-policy methods that utilize experience replay remain problematic because their random sampling of minibatches is not conducive to the efficient calculation of $λ$-returns. Yet replay-based methods are often the most sample efficient, and incorporating $λ$-returns into them is a viable way to achieve new state-of-the-art performance. Towards this, we propose the first method to enable …
Averaging $n$-step Returns Reduces Variance in Reinforcement Learning
Department of Computing Science, University of Alberta, Edmonton, AB, Canada（阿尔伯塔大学计算机科学系）；Alberta Machine Intelligence Institute（阿尔伯塔机器智能研究所）；Canada CIFAR AI Chair（加拿大CIFAR人工智能主席）
UC San Diego（加州大学圣迭戈分校）；Microsoft Research（微软研究院）；Tsinghua University（清华大学）
Distributional Reinforcement Learning (RL) differs from traditional RL in that, rather than the expectation of total returns, it estimates distributions and has achieved state-of-the-art performance on Atari Games. The key challenge in practical distributional RL algorithms lies in how to parameterize estimated distributions so as to better approximate the true continuous distribution. Existing distributional RL algorithms parameterize either the probability side or the return value side of the distribution function, leaving the other side uniformly fixed as in C51, QR-DQN or randomly sampled …
Tsinghua University（清华大学）；Microsoft Research Asia（微软亚洲研究院）
A growing trend for value-based reinforcement learning (RL) algorithms is to capture more information than scalar value functions in the value network. One of the most well-known methods in this branch is distributional RL, which models return distribution instead of scalar value. In another line of work, hybrid reward architectures (HRA) in RL have studied to model source-specific value functions for each source of reward, which is also shown to be beneficial in performance. To fully inherit the benefits of distributional RL and hybrid reward architectures, we introduce Multi-Dimensional Dist…
This paper explores the problem of simultaneously learning a value function and policy in deep actor-critic reinforcement learning models. We find that the common practice of learning these functions jointly is sub-optimal, due to an order-of-magnitude difference in noise levels between these two tasks. Instead, we show that learning these tasks independently, but with a constrained distillation phase, significantly improves performance. Furthermore, we find that the policy gradient noise levels can be decreased by using a lower \textit{variance} return estimate. Whereas, the value learning no…
Google Research, Brain Team（谷歌研究，大脑团队）；Université de Lorraine, CNRS, Inria, IECL（洛林大学，法国国家科学研究中心，法国国家信息与自动化研究所，洛林高等计算机研究所）
Bootstrapping is a core mechanism in Reinforcement Learning (RL). Most algorithms, based on temporal differences, replace the true value of a transiting state by their current estimate of this value. Yet, another estimate could be leveraged to bootstrap RL: the current policy. Our core contribution stands in a very simple idea: adding the scaled log-policy to the immediate reward. We show that slightly modifying Deep Q-Network (DQN) in that way provides an agent that is competitive with distributional methods on Atari games, without making use of distributional RL, n-step returns or prioritize…
Boosting Transferable Adversarial Attacks against Deep Reinforcement Learning
Nanyang Technological University（南洋理工大学）；University of California, Riverside（加利福尼亚大学河滨分校）；University of Connecticut（康涅狄格大学）；The Chinese University of Hong Kong, Shenzhen（香港中文大学（深圳））
Extending NGU to Multi-Agent RL: A Preliminary Study
Department of Computer Science, Pontifical Catholic University of Chile（天主教智利大学计算机科学系）；Millennium Institute for Intelligent Healthcare Engineering (iHEALTH)（智能医疗工程研究院）；National Center for Artificial Intelligence (CENIA)（人工智能国家中心）
Ensemble Value Functions for Efficient Exploration in Multi-Agent Reinforcement Learning
University of Edinburgh（爱丁堡大学）；University College London（伦敦大学学院）；Carnegie Mellon University（卡内基梅隆大学）；King’s College London（伦敦国王学院）；Queen Mary University London（伦敦玛丽女王大学）；Microsoft Research Cambridge（微软研究院剑桥分部）
