Off-policy Maximum Entropy Reinforcement Learning : Soft Actor-Critic with Advantage Weighted Mixture Policy(SAC-AWMP)
Department of Mechanical and Energy Engineering, Southern University of Science and Technology（南方科技大学机械与能源工程系）；Reinforcement Learning and Artificial Intelligence Laboratory, University of Alberta（阿尔伯塔大学强化学习与人工智能实验室）；Department of Biomedical Engineering, National University of Singapore（新加坡国立大学生物医学工程系）
The optimal policy of a reinforcement learning problem is often discontinuous and non-smooth. I.e., for two states with similar representations, their optimal policies can be significantly different. In this case, representing the entire policy with a function approximator (FA) with shared parameters for all states maybe not desirable, as the generalization ability of parameters sharing makes representing discontinuous, non-smooth policies difficult. A common way to solve this problem, known as Mixture-of-Experts, is to represent the policy as the weighted sum of multiple components, where different components perform well on different parts of the state space. Following this idea and inspired by a recent work called advantage-weighted information maximization, we propose to learn for each state weights of these components, so that they entail the information of the state itself and also the preferred action learned so far for the state. The action preference is characterized via the advantage function. In this case, the weight of each component would only be large for certain groups of states whose representations are similar and preferred action representations are also similar. Therefore each component is easy to be represented. We call a policy parameterized in this way an Advantage Weighted Mixture Policy (AWMP) and apply this idea to improve soft-actor-critic (SAC), one of the most competitive continuous control algorithm. Experimental results demonstrate that SAC with AWMP clearly outperforms SAC in four commonly used continuous control tasks and achieve stable performance across different random seeds.
Soft Actor-Critic (SAC) is an off-policy actor-critic deep reinforcement learning (DRL) algorithm based on maximum entropy reinforcement learning. By combining off-policy updates with an actor-critic formulation, SAC achieves state-of-the-art performance on a range of continuous-action benchmark tasks, outperforming prior on-policy and off-policy methods. The off-policy method employed by SAC samples data uniformly from past experience when performing parameter updates. We propose Emphasizing Recent Experience (ERE), a simple but powerful off-policy sampling technique, which emphasizes recentl…
Soft Actor Critic (SAC) algorithms show remarkable performance in complex simulated environments. A key element of SAC networks is entropy regularization, which prevents the SAC actor from optimizing against fine grained features, oftentimes transient, of the state-action value function. This results in better sample efficiency during early training. We take this idea one step further by artificially bandlimiting the target critic spatial resolution through the addition of a convolutional filter. We derive the closed form solution in the linear case and show that bandlimiting reduces the inter…
Exploration-exploitation dilemma has long been a crucial issue in reinforcement learning. In this paper, we propose a new approach to automatically balance between these two. Our method is built upon the Soft Actor-Critic (SAC) algorithm, which uses an "entropy temperature" that balances the original task reward and the policy entropy, and hence controls the trade-off between exploitation and exploration. It is empirically shown that SAC is very sensitive to this hyperparameter, and the follow-up work (SAC-v2), which uses constrained optimization for automatic adjustment, has some limitations.…
University of California, Irvine（加州大学尔湾分校）；University of California, Berkeley（加州大学伯克利分校）
Soft Actor-Critic (SAC) is considered the state-of-the-art algorithm in continuous action space settings. It uses the maximum entropy framework for efficiency and stability, and applies a heuristic temperature Lagrange term to tune the temperature $α$, which determines how "soft" the policy should be. It is counter-intuitive that empirical evidence shows SAC does not perform well in discrete domains. In this paper we investigate the possible explanations for this phenomenon and propose Target Entropy Scheduled SAC (TES-SAC), an annealing method for the target entropy parameter applied on SAC. …
University of Science and Technology of China（中国科学技术大学）
The performance of deep reinforcement learning methods prone to degenerate when applied to environments with non-stationary dynamics. In this paper, we utilize the latent context recurrent encoders motivated by recent Meta-RL materials, and propose the Latent Context-based Soft Actor Critic (LC-SAC) method to address aforementioned issues. By minimizing the contrastive prediction loss function, the learned context variables capture the information of the environment dynamics and the recent behavior of the agent. Then combined with the soft policy iteration paradigm, the LC-SAC method alternate…
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…
Research Institute of Electrical and Computer Engineering, Hanyang University（汉阳大学电气与计算机工程研究所）；Hanyang University（汉阳大学）
In this paper, we propose SACHER (soft actor-critic (SAC) with hindsight experience replay (HER)), which constitutes a class of deep reinforcement learning (DRL) algorithms. SAC is known as an off-policy model-free DRL algorithm based on the maximum entropy framework, which outperforms earlier DRL algorithms in terms of exploration, robustness and learning performance. However, in SAC, maximizing the entropy-augmented objective may degrade the optimality of learning outcomes. HER is known as a sample-efficient replay method that enhances the performance of off-policy DRL algorithms by allowing…
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…
Robotics Design Laboratory, University of Queensland（昆士兰大学机器人设计实验室）
Soft Actor-Critic (SAC) is one of the state-of-the-art off-policy reinforcement learning (RL) algorithms that is within the maximum entropy based RL framework. SAC is demonstrated to perform very well in a list of continous control tasks with good stability and robustness. SAC learns a stochastic Gaussian policy that can maximize a trade-off between total expected reward and the policy entropy. To update the policy, SAC minimizes the KL-Divergence between the current policy density and the soft value function density. Reparameterization trick is then used to obtain the approximate gradient of …
Model-free deep reinforcement learning (RL) algorithms have been successfully applied to a range of challenging sequential decision making and control tasks. However, these methods typically suffer from two major challenges: high sample complexity and brittleness to hyperparameters. Both of these challenges limit the applicability of such methods to real-world domains. In this paper, we describe Soft Actor-Critic (SAC), our recently introduced off-policy actor-critic algorithm based on the maximum entropy RL framework. In this framework, the actor aims to simultaneously maximize expected retur…
National Institute of Informatics（国立信息学研究所）；The Graduate University for Advanced Studies（综合研究大学院大学）
Soft actor-critic (SAC) in reinforcement learning is expected to be one of the next-generation robot control schemes. Its ability to maximize policy entropy would make a robotic controller robust to noise and perturbation, which is useful for real-world robot applications. However, the priority of maximizing the policy entropy is automatically tuned in the current implementation, the rule of which can be interpreted as one for equality constraint, binding the policy entropy into its specified lower bound. The current SAC is therefore no longer maximize the policy entropy, contrary to our expec…
School of Engineering（工程学院）；School of Information and Physical Sciences, University of Newcastle（纽卡斯尔大学信息与物理科学学院）
Soft Actor-Critic (SAC) is an off-policy actor-critic reinforcement learning algorithm, essentially based on entropy regularization. SAC trains a policy by maximizing the trade-off between expected return and entropy (randomness in the policy). It has achieved state-of-the-art performance on a range of continuous-control benchmark tasks, outperforming prior on-policy and off-policy methods. SAC works in an off-policy fashion where data are sampled uniformly from past experiences (stored in a buffer) using which parameters of the policy and value function networks are updated. We propose certai…
Al-Balqa Applied University（巴尔卡应用大学）；Iowa State University（爱荷华州立大学）
The trend is to implement intelligent agents capable of analyzing available information and utilize it efficiently. This work presents a number of reinforcement learning (RL) architectures; one of them is designed for intelligent agents. The proposed architectures are called selector-actor-critic (SAC), tuner-actor-critic (TAC), and estimator-selector-actor-critic (ESAC). These architectures are improved models of a well known architecture in RL called actor-critic (AC). In AC, an actor optimizes the used policy, while a critic estimates a value function and evaluate the optimized policy by th…
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…
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…
A Geometric Approach to Soft Actor-Critic with Zonotopes for Locomotion Learning
Robotics Institute, Athena Research Center（雅典娜研究中心机器人研究所）；HERON - Hellenic Robotics Center of Excellence（希腊卓越机器人中心）；School of Electrical & Computer Engineering, NTUA（雅典国立技术大学电气与计算机工程学院）
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 …
Laboratory of Robotics and Cognitive Systems (LaRoCS)（机器人与认知系统实验室（LaRoCS））；Institute of Computing, Unicamp（坎皮纳斯州立大学计算研究所）
Unmanned Aerial Vehicles (UAVs), or drones, have recently been used in several civil application domains from organ delivery to remote locations to wireless network coverage. These platforms, however, are naturally unstable systems for which many different control approaches have been proposed. Generally based on classic and modern control, these algorithms require knowledge of the robot's dynamics. However, recently, model-free reinforcement learning has been successfully used for controlling drones without any prior knowledge of the robot model. In this work, we present a framework to train …
During recent years, deep reinforcement learning (DRL) has made successful incursions into complex decision-making applications such as robotics, autonomous driving or video games. Off-policy algorithms tend to be more sample-efficient than their on-policy counterparts, and can additionally benefit from any off-policy data stored in the replay buffer. Expert demonstrations are a popular source for such data: the agent is exposed to successful states and actions early on, which can accelerate the learning process and improve performance. In the past, multiple ideas have been proposed to make go…
Google Research（谷歌研究院）；University of Michigan（密歇根大学）
The Predictive Information is the mutual information between the past and the future, I(X_past; X_future). We hypothesize that capturing the predictive information is useful in RL, since the ability to model what will happen next is necessary for success on many tasks. To test our hypothesis, we train Soft Actor-Critic (SAC) agents from pixels with an auxiliary task that learns a compressed representation of the predictive information of the RL environment dynamics using a contrastive version of the Conditional Entropy Bottleneck (CEB) objective. We refer to these as Predictive Information SAC…
While most current research in Reinforcement Learning (RL) focuses on improving the performance of the algorithms in controlled environments, the use of RL under constraints like those met in the video game industry is rarely studied. Operating under such constraints, we propose Hybrid SAC, an extension of the Soft Actor-Critic algorithm able to handle discrete, continuous and parameterized actions in a principled way. We show that Hybrid SAC can successfully solve a highspeed driving task in one of our games, and is competitive with the state-of-the-art on parameterized actions benchmark task…
Efficient Soft Actor-Critic with LLM-Based Action-Level Guidance for Continuous Control
School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China（中国科学院大学人工智能学院，北京，中国）；Institute of Automation, Chinese Academy of Sciences, Beijing 100190, China（中国科学院自动化研究所，北京100190，中国）
Cumulative entropy regularization introduces a regulatory signal to the reinforcement learning (RL) problem that encourages policies with high-entropy actions, which is equivalent to enforcing small deviations from a uniform reference marginal policy. This has been shown to improve exploration and robustness, and it tackles the value overestimation problem. It also leads to a significant performance increase in tabular and high-dimensional settings, as demonstrated via algorithms such as soft Q-learning (SQL) and soft actor-critic (SAC). Cumulative entropy regularization has been extended to o…
Hierarchical Soft Actor-Critic for Sparse-Reward Long-Horizon Reinforcement Learning
National Engineering School of Tunis, University of Tunis El Manar（突尼斯艾尔玛纳尔大学突尼斯国立工程师学校）；University of Tripoli（的黎波里大学）；University of Picardie Jules Verne Amiens（亚眠皮卡第朱尔斯·凡尔纳大学）
Sony AI（索尼AI）；The University of Texas at Austin（德克萨斯大学奥斯汀分校）
Designing reinforcement learning (RL) agents is typically a difficult process that requires numerous design iterations. Learning can fail for a multitude of reasons, and standard RL methods provide too few tools to provide insight into the exact cause. In this paper, we show how to integrate value decomposition into a broad class of actor-critic algorithms and use it to assist in the iterative agent-design process. Value decomposition separates a reward function into distinct components and learns value estimates for each. These value estimates provide insight into an agent's learning and deci…
This research is concerned with the novel application and investigation of `Soft Actor Critic' (SAC) based Deep Reinforcement Learning (DRL) to control the cooling setpoint (and hence cooling loads) of a large commercial building to harness energy flexibility. The research is motivated by the challenge associated with the development and application of conventional model-based control approaches at scale to the wider building stock. SAC is a model-free DRL technique that is able to handle continuous action spaces and which has seen limited application to real-life or high-fidelity simulation i…
New York University（纽约大学）；NYU Shanghai（上海纽约大学）；University of California San Diego（加州大学圣迭戈分校）
We aim to develop off-policy DRL algorithms that not only exceed state-of-the-art performance but are also simple and minimalistic. For standard continuous control benchmarks, Soft Actor-Critic (SAC), which employs entropy maximization, currently provides state-of-the-art performance. We first demonstrate that the entropy term in SAC addresses action saturation due to the bounded nature of the action spaces, with this insight, we propose a streamlined algorithm with a simple normalization scheme or with inverted gradients. We show that both approaches can match SAC's sample efficiency performa…
Low-precision training has become a popular approach to reduce compute requirements, memory footprint, and energy consumption in supervised learning. In contrast, this promising approach has not yet enjoyed similarly widespread adoption within the reinforcement learning (RL) community, partly because RL agents can be notoriously hard to train even in full precision. In this paper we consider continuous control with the state-of-the-art SAC agent and demonstrate that a naïve adaptation of low-precision methods from supervised learning fails. We propose a set of six modifications, all straightfo…
Adopting reasonable strategies is challenging but crucial for an intelligent agent with limited resources working in hazardous, unstructured, and dynamic environments to improve the system's utility, decrease the overall cost, and increase mission success probability. This paper proposes a novel hierarchical strategy decomposition approach based on the Bayesian chain rule to separate an intricate policy into several simple sub-policies and organize their relationships as Bayesian strategy networks (BSN). We integrate this approach into the state-of-the-art DRL method -- soft actor-critic (SAC)…
