English
Related papers

Related papers: ADER:Adapting between Exploration and Robustness f…

200 papers

The overestimation phenomenon caused by function approximation is a well-known issue in value-based reinforcement learning algorithms such as deep Q-networks and DDPG, which could lead to suboptimal policies. To address this issue, TD3…

Machine Learning · Computer Science 2023-11-07 Qiang He , Xinwen Hou

Actor-critic methods, a type of model-free Reinforcement Learning, have been successfully applied to challenging tasks in continuous control, often achieving state-of-the art performance. However, wide-scale adoption of these methods in…

Machine Learning · Statistics 2019-10-29 Kamil Ciosek , Quan Vuong , Robert Loftin , Katja Hofmann

Value-based deep Reinforcement Learning (RL) algorithms suffer from the estimation bias primarily caused by function approximation and temporal difference (TD) learning. This problem induces faulty state-action value estimates and therefore…

Machine Learning · Computer Science 2021-11-15 Dogan C. Cicek , Enes Duran , Baturay Saglam , Kagan Kaya , Furkan B. Mutlu , Suleyman S. Kozat

In actor-critic-based reinforcement learning algorithms such as Twin Delayed Deep Deterministic policy gradient (TD3), insufficient exploration of the spatial space can result in suboptimal policies when controlling 7-DOF robotic arms. To…

Robotics · Computer Science 2024-08-27 Wen-Han Hsieh , Jen-Yuan Chang

Exploration in environments with sparse feedback remains a challenging research problem in reinforcement learning (RL). When the RL agent explores the environment randomly, it results in low exploration efficiency, especially in robotic…

Robotics · Computer Science 2020-11-19 Boyao Li , Tao Lu , Jiayi Li , Ning Lu , Yinghao Cai , Shuo Wang

Actor learning and critic learning are two components of the outstanding and mostly used Deep Deterministic Policy Gradient (DDPG) reinforcement learning method. Since actor and critic learning plays a significant role in the overall…

Robotics · Computer Science 2022-10-25 Adarsh Sehgal , Muskan Sehgal , Hung Manh La

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

We address the issue of estimation bias in deep reinforcement learning (DRL) by introducing solution mechanisms that include a new, twin TD-regularized actor-critic (TDR) method. It aims at reducing both over and under-estimation errors.…

Machine Learning · Computer Science 2023-11-08 Junmin Zhong , Ruofan Wu , Jennie Si

An effective approach to exploration in reinforcement learning is to rely on an agent's uncertainty over the optimal policy, which can yield near-optimal exploration strategies in tabular settings. However, in non-tabular settings that…

In this work, we consider policy-based methods for solving the reinforcement learning problem, and establish the sample complexity guarantees. A policy-based algorithm typically consists of an actor and a critic. We consider using various…

Machine Learning · Computer Science 2023-01-16 Zaiwei Chen , Siva Theja Maguluri

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…

Artificial Intelligence · Computer Science 2018-10-23 Scott Fujimoto , Herke van Hoof , David Meger

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…

Machine Learning · Computer Science 2020-12-14 Srinjoy Roy , Saptam Bakshi , Tamal Maharaj

To obtain better value estimation in reinforcement learning, we propose a novel algorithm based on the double actor-critic framework with temporal difference error-driven regularization, abbreviated as TDDR. TDDR employs double actors, with…

Machine Learning · Computer Science 2024-10-01 Haohui Chen , Zhiyong Chen , Aoxiang Liu , Wentuo Fang

The imbalance of exploration and exploitation has long been a significant challenge in reinforcement learning. In policy optimization, excessive reliance on exploration reduces learning efficiency, while over-dependence on exploitation…

Machine Learning · Computer Science 2024-08-20 Renye Yan , Yaozhong Gan , You Wu , Ling Liang , Junliang Xing , Yimao Cai , Ru Huang

Deterministic policy gradient algorithms for continuous control suffer from value estimation biases that degrade performance. While double critics reduce such biases, the exploration potential of double actors remains underexplored.…

Machine Learning · Computer Science 2025-11-21 Haohui Chen , Zhiyong Chen , Aoxiang Liu , Wentuo Fang

In value-based deep reinforcement learning methods, approximation of value functions induces overestimation bias and leads to suboptimal policies. We show that in deep actor-critic methods that aim to overcome the overestimation bias, if…

Machine Learning · Computer Science 2021-12-28 Baturay Saglam , Enes Duran , Dogan C. Cicek , Furkan B. Mutlu , Suleyman S. Kozat

Robotic manipulation remains challenging for reinforcement learning due to contact-rich dynamics, long horizons, and training instability. Although off-policy actor-critic algorithms such as SAC and TD3 perform well in simulation, they…

Robotics · Computer Science 2026-04-03 Yu Zhang , Karl Mason

Approximate Dynamic Programming (ADP) is a methodology to solve multi-stage stochastic optimization problems in multi-dimensional discrete or continuous spaces. ADP approximates the optimal value function by adaptively sampling both action…

Optimization and Control · Mathematics 2021-07-02 Vijay Kumar , Mort Webster

Achieving efficient and scalable exploration in complex domains poses a major challenge in reinforcement learning. While Bayesian and PAC-MDP approaches to the exploration problem offer strong formal guarantees, they are often impractical…

Artificial Intelligence · Computer Science 2015-11-23 Bradly C. Stadie , Sergey Levine , Pieter Abbeel

This paper investigates whether learning contingency-awareness and controllable aspects of an environment can lead to better exploration in reinforcement learning. To investigate this question, we consider an instantiation of this…

Machine Learning · Computer Science 2019-03-05 Jongwook Choi , Yijie Guo , Marcin Moczulski , Junhyuk Oh , Neal Wu , Mohammad Norouzi , Honglak Lee
‹ Prev 1 2 3 10 Next ›