In this work we present a new agent architecture, called Reactor, which combines multiple algorithmic and architectural contributions to produce an agent with higher sample-efficiency than Prioritized Dueling DQN (Wang et al., 2016) and Categorical DQN (Bellemare et al., 2017), while giving better run-time performance than A3C (Mnih et al., 2016). Our first contribution is a new policy evaluation algorithm called Distributional Retrace, which brings multi-step off-policy updates to the distributional reinforcement learning setting. The same approach can be used to convert several classes of multi-step policy evaluation algorithms designed for expected value evaluation into distributional ones. Next, we introduce the \b{eta}-leave-one-out policy gradient algorithm which improves the trade-off between variance and bias by using action values as a baseline. Our final algorithmic contribution is a new prioritized replay algorithm for sequences, which exploits the temporal locality of neighboring observations for more efficient replay prioritization. Using the Atari 2600 benchmarks, we show that each of these innovations contribute to both the sample efficiency and final agent performance. Finally, we demonstrate that Reactor reaches state-of-the-art performance after 200 million frames and less than a day of training.
We present the first class of policy-gradient algorithms that work with both state-value and policy function-approximation, and are guaranteed to converge under off-policy training. Our solution targets problems in reinforcement learning where the action representation adds to the-curse-of-dimensionality; that is, with continuous or large action sets, thus making it infeasible to estimate state-action value functions (Q functions). Using state-value functions helps to lift the curse and as a result naturally turn our policy-gradient solution into classical Actor-Critic architecture whose Actor…
LLC Innodata（因诺数据有限责任公司）；Innopolis University（因诺波利斯大学）；Dublin Institute of Technology（都柏林理工学院）
Catastrophic forgetting has a significant negative impact in reinforcement learning. The purpose of this study is to investigate how pseudorehearsal can change performance of an actor-critic agent with neural-network function approximation. We tested agent in a pole balancing task and compared different pseudorehearsal approaches. We have found that pseudorehearsal can assist learning and decrease forgetting.
Catastrophic forgetting has a serious impact in reinforcement learning, as the data distribution is generally sparse and non-stationary over time. The purpose of this study is to investigate whether pseudorehearsal can increase performance of an actor-critic agent with neural-network based policy selection and function approximation in a pole balancing task and compare different pseudorehearsal approaches. We expect that pseudorehearsal assists learning even in such very simple problems, given proper initialization of the rehearsal parameters.
Deep reinforcement learning, and especially the Asynchronous Advantage Actor-Critic algorithm, has been successfully used to achieve super-human performance in a variety of video games. Starcraft II is a new challenge for the reinforcement learning community with the release of pysc2 learning environment proposed by Google Deepmind and Blizzard Entertainment. Despite being a target for several AI developers, few have achieved human level performance. In this project we explain the complexities of this environment and discuss the results from our experiments on the environment. We have compared…
Actor-Critic based approaches were among the first to address reinforcement learning in a general setting. Recently, these algorithms have gained renewed interest due to their generality, good convergence properties, and possible biological relevance. In this paper, we introduce an online temporal difference based actor-critic algorithm which is proved to converge to a neighborhood of a local maximum of the average reward. Linear function approximation is used by the critic in order estimate the value function, and the temporal difference signal, which is passed from the critic to the actor. T…
University of Alberta（阿尔伯塔大学）；Stanford University（斯坦福大学）；Google Brain（谷歌大脑）
Actor-critic (AC) methods are ubiquitous in reinforcement learning. Although it is understood that AC methods are closely related to policy gradient (PG), their precise connection has not been fully characterized previously. In this paper, we explain the gap between AC and PG methods by identifying the exact adjustment to the AC objective/gradient that recovers the true policy gradient of the cumulative reward objective (PG). Furthermore, by viewing the AC method as a two-player Stackelberg game between the actor and critic, we show that the Stackelberg policy gradient can be recovered as a sp…
In this paper we propose a hybrid architecture of actor-critic algorithms for reinforcement learning in parameterized action space, which consists of multiple parallel sub-actor networks to decompose the structured action space into simpler action spaces along with a critic network to guide the training of all sub-actor networks. While this paper is mainly focused on parameterized action space, the proposed architecture, which we call hybrid actor-critic, can be extended for more general action spaces which has a hierarchical structure. We present an instance of the hybrid actor-critic archite…
Soft Actor-Critic is a state-of-the-art reinforcement learning algorithm for continuous action settings that is not applicable to discrete action settings. Many important settings involve discrete actions, however, and so here we derive an alternative version of the Soft Actor-Critic algorithm that is applicable to discrete action settings. We then show that, even without any hyperparameter tuning, it is competitive with the tuned model-free state-of-the-art on a selection of games from the Atari suite.
The Chinese University of Hong Kong（香港中文大学）；Tencent Inc.（腾讯公司）
We present a training framework for neural abstractive summarization based on actor-critic approaches from reinforcement learning. In the traditional neural network based methods, the objective is only to maximize the likelihood of the predicted summaries, no other assessment constraints are considered, which may generate low-quality summaries or even incorrect sentences. To alleviate this problem, we employ an actor-critic framework to enhance the training procedure. For the actor, we employ the typical attention based sequence-to-sequence (seq2seq) framework as the policy network for summary…
Despite definite success in deep reinforcement learning problems, actor-critic algorithms are still confronted with sample inefficiency in complex environments, particularly in tasks where efficient exploration is a bottleneck. These methods consider a policy (the actor) and a value function (the critic) whose respective losses are built using different motivations and approaches. This paper introduces a third protagonist: the adversary. While the adversary mimics the actor by minimizing the KL-divergence between their respective action distributions, the actor, in addition to learning to solv…
Zhejiang University of Science and Technology（浙江科技大学）
Hyper-parameter optimization is a crucial problem in machine learning as it aims to achieve the state-of-the-art performance in any model. Great efforts have been made in this field, such as random search, grid search, Bayesian optimization. In this paper, we model hyper-parameter optimization process as a Markov decision process, and tackle it with reinforcement learning. A novel hyper-parameter optimization method based on soft actor critic and hierarchical mixture regularization has been proposed. Experiments show that the proposed method can obtain better hyper-parameters in a shorter time…
We reformulate the option framework as two parallel augmented MDPs. Under this novel formulation, all policy optimization algorithms can be used off the shelf to learn intra-option policies, option termination conditions, and a master policy over options. We apply an actor-critic algorithm on each augmented MDP, yielding the Double Actor-Critic (DAC) architecture. Furthermore, we show that, when state-value functions are used as critics, one critic can be expressed in terms of the other, and hence only one critic is necessary. We conduct an empirical study on challenging robot simulation tasks…
Berkeley Artificial Intelligence Research, University of California, Berkeley（加州大学伯克利分校伯克利人工智能研究中心）
Model-free deep reinforcement learning (RL) algorithms have been demonstrated on a range of challenging decision making and control tasks. However, these methods typically suffer from two major challenges: very high sample complexity and brittle convergence properties, which necessitate meticulous hyperparameter tuning. Both of these challenges severely limit the applicability of such methods to complex, real-world domains. In this paper, we propose soft actor-critic, an off-policy actor-critic deep RL algorithm based on the maximum entropy reinforcement learning framework. In this framework, …
We propose a new algorithm, Mean Actor-Critic (MAC), for discrete-action continuous-state reinforcement learning. MAC is a policy gradient algorithm that uses the agent's explicit representation of all action values to estimate the gradient of the policy, rather than using only the actions that were actually executed. We prove that this approach reduces variance in the policy gradient estimate relative to traditional actor-critic methods. We show empirical results on two control domains and on six Atari games, where MAC is competitive with state-of-the-art policy search algorithms.
Massachusetts Institute of Technology（麻省理工学院）；Higher Institute for Applied Sciences and Technology（应用科学与技术高等学院）
In this work, we propose Behavior-Guided Actor-Critic (BAC), an off-policy actor-critic deep RL algorithm. BAC mathematically formulates the behavior of the policy through autoencoders by providing an accurate estimation of how frequently each state-action pair was visited while taking into consideration state dynamics that play a crucial role in determining the trajectories produced by the policy. The agent is encouraged to change its behavior consistently towards less-visited state-action pairs while attaining good performance by maximizing the expected discounted sum of rewards, resulting i…
In this paper, we describe NeurIPS 2019 Learning to Move - Walk Around challenge physics-based environment and present our solution to this competition which scored 1303.727 mean reward points and took 3rd place. Our method combines recent advances from both continuous- and discrete-action space reinforcement learning, such as Soft Actor-Critic and Recurrent Experience Replay in Distributed Reinforcement Learning. We trained our agent in two stages: to move somewhere at the first stage and to follow the target velocity field at the second stage. We also introduce novel Q-function split techniq…
Ramakrishna Mission Vivekananda Educational and Research Institute (RKMVERI)（罗摩克里希纳传道会维韦卡南达教育与研究所（RKMVERI））
Actor-critic methods, a type of model-free reinforcement learning (RL), have achieved state-of-the-art performances in many real-world domains in continuous control. Despite their success, the wide-scale deployment of these models is still a far cry. The main problems in these actor-critic methods are inefficient exploration and sub-optimal policies. Soft Actor-Critic (SAC) and Twin Delayed Deep Deterministic Policy Gradient (TD3), two cutting edge such algorithms, suffer from these issues. SAC effectively addressed the problems of sample complexity and convergence brittleness to hyper-paramet…
Institute of Advanced Research in Artificial Intelligence (IARAI)（人工智能高级研究院（IARAI））
We prove under commonly used assumptions the convergence of actor-critic reinforcement learning algorithms, which simultaneously learn a policy function, the actor, and a value function, the critic. Both functions can be deep neural networks of arbitrary complexity. Our framework allows showing convergence of the well known Proximal Policy Optimization (PPO) and of the recently introduced RUDDER. For the convergence proof we employ recently introduced techniques from the two time-scale stochastic approximation theory. Our results are valid for actor-critic methods that use episodic samples and…
University of Science and Technology of China（中国科学技术大学）；Hefei Comprehensive National Science Center（合肥综合性国家科学中心）
Actor-critic Reinforcement Learning (RL) algorithms have achieved impressive performance in continuous control tasks. However, they still suffer two nontrivial obstacles, i.e., low sample efficiency and overestimation bias. To this end, we propose Simultaneous Double Q-learning with Conservative Advantage Learning (SDQ-CAL). Our SDQ-CAL boosts the Double Q-learning for off-policy actor-critic RL based on a modification of the Bellman optimality operator with Advantage Learning. Specifically, SDQ-CAL improves sample efficiency by modifying the reward to facilitate the distinction from experienc…
Reinforcement learning is well-studied under discrete actions. Integer actions setting is popular in the industry yet still challenging due to its high dimensionality. To this end, we study reinforcement learning under integer actions by incorporating the Soft Actor-Critic (SAC) algorithm with an integer reparameterization. Our key observation for integer actions is that their discrete structure can be simplified using their comparability property. Hence, the proposed integer reparameterization does not need one-hot encoding and is of low dimensionality. Experiments show that the proposed SAC …
McGill University（麦吉尔大学）；University of Amsterdam（阿姆斯特丹大学）
In value-based reinforcement learning methods such as deep Q-learning, function approximation errors are known to lead to overestimated value estimates and suboptimal policies. We show that this problem persists in an actor-critic setting and propose novel mechanisms to minimize its effects on both the actor and the critic. Our algorithm builds on Double Q-learning, by taking the minimum value between a pair of critics to limit overestimation. We draw the connection between target networks and overestimation bias, and suggest delaying policy updates to reduce per-update error and further impro…
Pretraining with expert demonstrations have been found useful in speeding up the training process of deep reinforcement learning algorithms since less online simulation data is required. Some people use supervised learning to speed up the process of feature learning, others pretrain the policies by imitating expert demonstrations. However, these methods are unstable and not suitable for actor-critic reinforcement learning algorithms. Also, some existing methods rely on the global optimum assumption, which is not true in most scenarios. In this paper, we employ expert demonstrations in a actor-…
We investigate the combination of actor-critic reinforcement learning algorithms with uniform large-scale experience replay and propose solutions for two challenges: (a) efficient actor-critic learning with experience replay (b) stability of off-policy learning where agents learn from other agents behaviour. We employ those insights to accelerate hyper-parameter sweeps in which all participating agents run concurrently and share their experience via a common replay module. To this end we analyze the bias-variance tradeoffs in V-trace, a form of importance sampling for actor-critic methods. Bas…
When Does Critique Improve AI-Assisted Theoretical Physics? SCALAR: Structured Critic--Actor Loop for Agentic Reasoning
Department of Physics, CCTP；ITCP, University of Crete, 71303, Greece；Centre for Theoretical Physics, Department of Physics；Astronomy, Queen Mary University of London, London E1 4NS, United Kingdom；Theoretical Physics Department, CERN, Geneva, Switzerland
Artificial Intelligence Research Center of National Innovation Institute of Defense Technology（国防科技创新研究院人工智能研究中心）；Tianjin Artificial Intelligence Innovation Center（天津人工智能创新中心）
In this paper, we consider the problem of actor-critic reinforcement learning. Firstly, we extend the actor-critic architecture to actor-critic-N architecture by introducing more critics beyond rewards. Secondly, we combine the reward-based critic with a potential-field-based critic to formulate the proposed potential field guided actor-critic reinforcement learning approach (actor-critic-2). This can be seen as a combination of the model-based gradients and the model-free gradients in policy improvement. State with large potential field often contains a strong prior information, such as point…
Quantum computing has a superior advantage in tackling specific problems, such as integer factorization and Simon's problem. For more general tasks in machine learning, by applying variational quantum circuits, more and more quantum algorithms have been proposed recently, especially in supervised learning and unsupervised learning. However, little work has been done in reinforcement learning, arguably more important and challenging. Previous work in quantum reinforcement learning mainly focuses on discrete control tasks where the action space is discrete. In this work, we develop a quantum rei…
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…
In traditional reinforcement learning, an agent maximizes the reward collected during its interaction with the environment by approximating the optimal policy through the estimation of value functions. Typically, given a state s and action a, the corresponding value is the expected discounted sum of rewards. The optimal action is then chosen to be the action a with the largest value estimated by value function. However, recent developments have shown both theoretical and experimental evidence of superior performance when value function is replaced with value distribution in context of deep Q l…
Deep Reinforcement Learning (DRL) algorithms for continuous action spaces are known to be brittle toward hyperparameters as well as \cut{being}sample inefficient. Soft Actor Critic (SAC) proposes an off-policy deep actor critic algorithm within the maximum entropy RL framework which offers greater stability and empirical gains. The choice of policy distribution, a factored Gaussian, is motivated by \cut{chosen due}its easy re-parametrization rather than its modeling power. We introduce Normalizing Flow policies within the SAC framework that learn more expressive classes of policies than simple…
Korea Advanced Institute of Science and Technology（韩国科学技术院）
In this paper, sample-aware policy entropy regularization is proposed to enhance the conventional policy entropy regularization for better exploration. Exploiting the sample distribution obtainable from the replay buffer, the proposed sample-aware entropy regularization maximizes the entropy of the weighted sum of the policy action distribution and the sample action distribution from the replay buffer for sample-efficient exploration. A practical algorithm named diversity actor-critic (DAC) is developed by applying policy iteration to the objective function with the proposed sample-aware entro…
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…
Robust Reinforcement Learning aims to derive optimal behavior that accounts for model uncertainty in dynamical systems. However, previous studies have shown that by considering the worst case scenario, robust policies can be overly conservative. Our soft-robust framework is an attempt to overcome this issue. In this paper, we present a novel Soft-Robust Actor-Critic algorithm (SR-AC). It learns an optimal policy with respect to a distribution over an uncertainty set and stays robust to model uncertainty but avoids the conservativeness of robust strategies. We show the convergence of SR-AC and …
Actor-critic algorithms learn an explicit policy (actor), and an accompanying value function (critic). The actor performs actions in the environment, while the critic evaluates the actor's current policy. However, despite their stability and promising convergence properties, current actor-critic algorithms do not outperform critic-only ones in practice. We believe that the fact that the critic learns Q^pi, instead of the optimal Q-function Q*, prevents state-of-the-art robust and sample-efficient off-policy learning algorithms from being used. In this paper, we propose an elegant solution, the…
University of Oxford（牛津大学）；Microsoft Research Montreal（微软研究院蒙特利尔分院）
We investigate the discounting mismatch in actor-critic algorithm implementations from a representation learning perspective. Theoretically, actor-critic algorithms usually have discounting for both actor and critic, i.e., there is a $γ^t$ term in the actor update for the transition observed at time $t$ in a trajectory and the critic is a discounted value function. Practitioners, however, usually ignore the discounting ($γ^t$) for the actor while using a discounted critic. We investigate this mismatch in two scenarios. In the first scenario, we consider optimizing an undiscounted objective $(γ…
Carnegie Mellon University（卡内基梅隆大学）；MIT Media Lab（麻省理工学院媒体实验室）；Adobe（奥多比公司）
The two-time scale nature of SAC, which is an actor-critic algorithm, is characterised by the fact that the critic estimate has not converged for the actor at any given time, but since the critic learns faster than the actor, it ensures eventual consistency between the two. Various strategies have been introduced in literature to learn better gradient estimates to help achieve better convergence. Since gradient estimates depend upon the critic, we posit that improving the critic can provide a better gradient estimate for the actor at each time. Utilizing this, we propose Soft Actor Retrospecti…
Nara Institute of Science and Technology（奈良先端科学技术大学院大学）
The oscillating performance of off-policy learning and persisting errors in the actor-critic (AC) setting call for algorithms that can conservatively learn to suit the stability-critical applications better. In this paper, we propose a novel off-policy AC algorithm cautious actor-critic (CAC). The name cautious comes from the doubly conservative nature that we exploit the classic policy interpolation from conservative policy iteration for the actor and the entropy-regularization of conservative value iteration for the critic. Our key observation is the entropy-regularized critic facilitates an…
Our effort is toward unifying GAN and DRL algorithms into a unifying AI model (AGI or general-purpose AI or artificial general intelligence which has general-purpose applications to: (A) offline learning (of stored data) like GAN in (un/semi-/fully-)SL setting such as big data analytics (mining) and visualization; (B) online learning (of real or simulated devices) like DRL in RL setting (with/out environment reward) such as (real or simulated) robotics and control; Our core proposal is adding an (generative/predictive) environment model to the actor-critic (model-free) architecture which resul…
Department of Electrical and Computer Engineering, Princeton University（普林斯顿大学电气与计算机工程系）
Off-policy Actor-Critic algorithms have demonstrated phenomenal experimental performance but still require better explanations. To this end, we show its policy evaluation error on the distribution of transitions decomposes into: a Bellman error, a bias from policy mismatch, and a variance term from sampling. By comparing the magnitude of bias and variance, we explain the success of the Emphasizing Recent Experience sampling and 1/age weighted sampling. Both sampling strategies yield smaller bias and variance and are hence preferable to uniform sampling.
