English
Related papers

Related papers: Better Exploration with Optimistic Actor-Critic

200 papers

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…

Artificial Intelligence · Computer Science 2018-02-23 Hamid Reza Maei

Off-policy reinforcement learning enables near-optimal policy from suboptimal experience, thereby provisions opportunity for artificial intelligence applications in healthcare. Previous works have mainly framed patient-clinician…

Artificial Intelligence · Computer Science 2018-06-05 Luchen Li , Matthieu Komorowski , Aldo A. Faisal

We discuss the relative merits of optimistic and randomized approaches to exploration in reinforcement learning. Optimistic approaches presented in the literature apply an optimistic boost to the value estimate at each state-action pair and…

Machine Learning · Statistics 2017-06-15 Ian Osband , Benjamin Van Roy

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

Exploration in reinforcement learning (RL) remains an open challenge. RL algorithms rely on observing rewards to train the agent, and if informative rewards are sparse the agent learns slowly or may not learn at all. To improve exploration…

Machine Learning · Computer Science 2024-11-12 Simone Parisi , Alireza Kazemipour , Michael Bowling

Risk-aware Reinforcement Learning (RL) algorithms like SAC and TD3 were shown empirically to outperform their risk-neutral counterparts in a variety of continuous-action tasks. However, the theoretical basis for the pessimistic objectives…

Machine Learning · Computer Science 2024-05-27 Michal Nauman , Marek Cygan

How to obtain good value estimation is one of the key problems in Reinforcement Learning (RL). Current value estimation methods, such as DDPG and TD3, suffer from unnecessary over- or underestimation bias. In this paper, we explore the…

Machine Learning · Computer Science 2021-06-08 Jiafei Lyu , Xiaoteng Ma , Jiangpeng Yan , Xiu Li

Model-based reinforcement learning algorithms, which aim to learn a model of the environment to make decisions, are more sample efficient than their model-free counterparts. The sample efficiency of model-based approaches relies on whether…

Machine Learning · Computer Science 2021-12-21 Zhihai Wang , Jie Wang , Qi Zhou , Bin Li , Houqiang Li

Real-world applications require RL algorithms to act safely. During learning process, it is likely that the agent executes sub-optimal actions that may lead to unsafe/poor states of the system. Exploration is particularly brittle in…

Machine Learning · Statistics 2019-06-17 Elena Smirnova , Elvis Dohmatob , Jérémie Mary

Actor-critic methods can achieve incredible performance on difficult reinforcement learning problems, but they are also prone to instability. This is partly due to the interaction between the actor and critic during learning, e.g., an…

Machine Learning · Computer Science 2019-02-26 Simone Parisi , Voot Tangkaratt , Jan Peters , Mohammad Emtiyaz Khan

We propose A-Crab (Actor-Critic Regularized by Average Bellman error), a new practical algorithm for offline reinforcement learning (RL) in complex environments with insufficient data coverage. Our algorithm combines the marginalized…

Machine Learning · Computer Science 2023-10-10 Hanlin Zhu , Paria Rashidinejad , Jiantao Jiao

Several recent works have focused on carrying out non-asymptotic convergence analyses for AC algorithms. Recently, a two-timescale critic-actor algorithm has been presented for the discounted cost setting in the look-up table case where the…

Machine Learning · Computer Science 2025-09-01 Prashansa Panda , Shalabh Bhatnagar

The class of deep deterministic off-policy algorithms is effectively applied to solve challenging continuous control problems. Current approaches commonly utilize random noise as an exploration method, which has several drawbacks, including…

Machine Learning · Computer Science 2024-05-07 Igor Kuznetsov

The multi-agent setting is intricate and unpredictable since the behaviors of multiple agents influence one another. To address this environmental uncertainty, distributional reinforcement learning algorithms that incorporate uncertainty…

Machine Learning · Computer Science 2023-03-06 Jihwan Oh , Joonkee Kim , Minchan Jeong , Se-Young Yun

One of the bottlenecks preventing Deep Reinforcement Learning algorithms (DRL) from real-world applications is how to explore the environment and collect informative transitions efficiently. The present paper describes bounded exploration,…

Machine Learning · Computer Science 2024-12-10 Ting Qiao , Henry Williams , David Valencia , Bruce MacDonald

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

Human-computer interactive systems that rely on machine learning are becoming paramount to the lives of millions of people who use digital assistants on a daily basis. Yet, further advances are limited by the availability of data and the…

Machine Learning · Computer Science 2020-04-29 Katya Kudashkina , Valliappa Chockalingam , Graham W. Taylor , Michael Bowling

In this paper, we propose actor-director-critic, a new framework for deep reinforcement learning. Compared with the actor-critic framework, the director role is added, and action classification and action evaluation are applied…

Machine Learning · Computer Science 2023-01-11 Zongwei Liu , Yonghong Song , Yuanlin Zhang

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…

Machine Learning · Computer Science 2021-06-10 Seungyul Han , Youngchul Sung

We show that the simplest actor-critic method -- a linear softmax policy updated with TD through interaction with a linear MDP, but featuring no explicit regularization or exploration -- does not merely find an optimal policy, but moreover…

Machine Learning · Computer Science 2022-03-15 Yuzheng Hu , Ziwei Ji , Matus Telgarsky
‹ Prev 1 3 4 5 6 7 10 Next ›