English
Related papers

Related papers: Off-Policy Actor-Critic with Emphatic Weightings

200 papers

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…

Machine Learning · Computer Science 2021-12-22 Zhenyang Shi , Surya P. N. Singh

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…

Machine Learning · Computer Science 2021-10-06 Lingwei Zhu , Toshinori Kitamura , Takamitsu Matsubara

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…

Machine Learning · Computer Science 2021-09-27 Chayan Banerjee , Zhiyong Chen , Nasimul Noman

We study off-policy evaluation (OPE) of contextual bandit policies for large discrete action spaces where conventional importance-weighting approaches suffer from excessive variance. To circumvent this variance issue, we propose a new…

Machine Learning · Statistics 2023-06-12 Yuta Saito , Qingyang Ren , Thorsten Joachims

We consider an improper reinforcement learning setting where a learner is given $M$ base controllers for an unknown Markov decision process, and wishes to combine them optimally to produce a potentially new controller that can outperform…

Machine Learning · Computer Science 2022-07-20 Mohammadi Zaki , Avinash Mohan , Aditya Gopalan , Shie Mannor

Off-policy reinforcement learning (RL) is concerned with learning a rewarding policy by executing another policy that gathers samples of experience. While the former policy (i.e. target policy) is rewarding but in-expressive (in most cases,…

Machine Learning · Computer Science 2020-03-02 Anji Liu , Yitao Liang , Guy Van den Broeck

Multi-agent policy gradient (MAPG) methods recently witness vigorous progress. However, there is a significant performance discrepancy between MAPG methods and state-of-the-art multi-agent value-based approaches. In this paper, we…

Machine Learning · Computer Science 2020-10-06 Yihan Wang , Beining Han , Tonghan Wang , Heng Dong , Chongjie Zhang

Policy gradient methods are widely adopted reinforcement learning algorithms for tasks with continuous action spaces. These methods succeeded in many application domains, however, because of their notorious sample inefficiency their use…

Machine Learning · Statistics 2024-02-20 Davide Mambelli , Stephan Bongers , Onno Zoeter , Matthijs T. J. Spaan , Frans A. Oliehoek

Off-policy evaluation (OPE) in contextual bandits has seen rapid adoption in real-world systems, since it enables offline evaluation of new policies using only historic log data. Unfortunately, when the number of actions is large, existing…

Machine Learning · Computer Science 2022-06-17 Yuta Saito , Thorsten Joachims

While on-policy algorithms are known for their stability, they often demand a substantial number of samples. In contrast, off-policy algorithms, which leverage past experiences, are considered sample-efficient but tend to exhibit…

Machine Learning · Computer Science 2023-09-28 Jianfei Ma

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,…

Artificial Intelligence · Computer Science 2021-06-15 Junfeng Wen , Saurabh Kumar , Ramki Gummadi , Dale Schuurmans

Policy gradient algorithms typically combine discounted future rewards with an estimated value function, to compute the direction and magnitude of parameter updates. However, for most Reinforcement Learning tasks, humans can provide…

Machine Learning · Computer Science 2019-04-09 Ishan Durugkar , Matthew Hausknecht , Adith Swaminathan , Patrick MacAlpine

We identify two issues with the family of algorithms based on the Adversarial Imitation Learning framework. The first problem is implicit bias present in the reward functions used in these algorithms. While these biases might work well for…

Machine Learning · Computer Science 2018-10-16 Ilya Kostrikov , Kumar Krishna Agrawal , Debidatta Dwibedi , Sergey Levine , Jonathan Tompson

We identify a fundamental problem in policy gradient-based methods in continuous control. As policy gradient methods require the agent's underlying probability distribution, they limit policy representation to parametric distribution…

Machine Learning · Computer Science 2019-11-26 Chen Tessler , Guy Tennenholtz , Shie Mannor

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…

Machine Learning · Computer Science 2021-04-12 Ammar Fayad , Majd Ibrahim

The varying significance of distinct primitive behaviors during the policy learning process has been overlooked by prior model-free RL algorithms. Leveraging this insight, we explore the causal relationship between different action…

Machine Learning · Computer Science 2024-11-05 Tianying Ji , Yongyuan Liang , Yan Zeng , Yu Luo , Guowei Xu , Jiawei Guo , Ruijie Zheng , Furong Huang , Fuchun Sun , Huazhe Xu

Model-free deep reinforcement learning has achieved great success in many domains, such as video games, recommendation systems and robotic control tasks. In continuous control tasks, widely used policies with Gaussian distributions results…

Machine Learning · Computer Science 2023-06-05 Lingwei Peng , Hui Qian , Zhebang Shen , Chao Zhang , Fei Li

To learn approximately optimal acting policies for decision problems, modern Actor Critic algorithms rely on deep Neural Networks (DNNs) to parameterize the acting policy and greedification operators to iteratively improve it. The reliance…

Many policy gradient methods are variants of Actor-Critic (AC), where a value function (critic) is learned to facilitate updating the parameterized policy (actor). The update to the actor involves a log-likelihood update weighted by the…

Machine Learning · Computer Science 2023-03-02 Samuel Neumann , Sungsu Lim , Ajin Joseph , Yangchen Pan , Adam White , Martha White

In this paper, we discuss the deterministic policy gradient using the Actor-Critic methods based on the linear compatible advantage function approximator, where the input spaces are continuous. When the policy is restricted by hard…

Systems and Control · Electrical Eng. & Systems 2021-04-07 Arash Bahari Kordabad , Hossein Nejatbakhsh Esfahani , Sebastien Gros