paper-with-me

Papers

Efficient Continuous Control with Double Actors and Regularized Critics

2021-06-06 · Jiafei Lyu, Xiaoteng Ma, Jiangpeng Yan, Xiu Li

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 potential of double actors, which has been neglected for a long time, for better value function estimation in continuous setting. First, we uncover and demonstrate the bias alleviation property of double actors by building double actors upon single critic and double critics to handle overestimation bias in DDPG and underestimation bias in TD3 respectively. Next, we interestingly find that double actors help improve the exploration ability of the agent. Finally, to mitigate the uncertainty of value estimate from double critics, we further propose to regularize the critic networks under double actors architecture, which gives rise to Double Actors Regularized Critics (DARC) algorithm. Extensive experimental results on challenging continuous control tasks show that DARC significantly outperforms state-of-the-art methods with higher sample efficiency.

📄 PDF Abstract BibTeX arXiv:2106.03050

Code (1)

dmksjfl/DARC 공식 구현 pytorch

Tasks

continuous-controlContinuous ControlReinforcement Learning (RL)

Methods 이 논문이 사용한 방법론

ReLU How Do I Communicate to Expedia? How Do I Communicate to Expedia? – Call ☎️ +1-(888) 829 (0881) or +1-805-330-4056 or +1-805-330-4056 for Live Support & Special Travel…
Weight Decay 설명 없음
Batch Normalization 설명 없음
Convolution A convolution is a type of matrix operation, consisting of a kernel, a small matrix of weights, that slides over input data performing element-wise multiplication with the…
Clipped Double Q-learning 설명 없음
Experience Replay Experience Replay is a replay memory technique used in reinforcement learning where we store the agent’s experiences at each time-step, $e\_{t} = \left(s\_{t}, a\_{t}, r\_{t},…
Target Policy Smoothing Target Policy Smoothing is a regularization strategy for the value function in reinforcement learning. Deterministic policies can overfit to narrow peaks in the value…
Dense Connections Dense Connections, or Fully Connected Connections, are a type of layer in a deep neural network that use a linear operation where every input is connected to every output…

Similar Papers 제목 키워드 기반

Mitigating Estimation Bias with Representation Learning in TD Error-Driven Regularization

2025-11-20 · Haohui Chen, Zhiyong Chen, Aoxiang Liu, Wentuo Fang arxiv

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 un…

Representation LearningContinuous Control

Double Actor-Critic with TD Error-Driven Regularization in Reinforcement Learning

2024-09-28 · Haohui Chen, Zhiyong Chen, Aoxiang Liu, Wentuo Fang

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…

continuous-controlContinuous Control

Reinforcement Learning for Predicting Traffic Accidents

2022-12-09 · Injoon Cho, Praveen Kumar Rajendran, TaeYoung Kim, Dongsoo Har

As the demand for autonomous driving increases, it is paramount to ensure safety. Early accident prediction using deep learning methods for driving safety has recently gained much attention. In this task, early accident …

Accident AnticipationAutonomous DrivingPredictionreinforcement-learning+2

D2C-HRHR: Discrete Actions with Double Distributional Critics for High-Risk-High-Return Tasks

2025-10-20 · Jundong Zhang, Yuhui Situ, Fanji Zhang, Rongji Deng 외 arxiv

Tasks involving high-risk-high-return (HRHR) actions, such as obstacle crossing, often exhibit multimodal action distributions and stochastic returns. Most reinforcement learning (RL) methods assume unimodal Gaussian pol…

Reinforcement Learning

Double Gumbel Q-Learning

2023-09-21 · NeurIPS 2023 11

We show that Deep Neural Networks introduce two heteroscedastic Gumbel noise sources into Q-Learning. To account for these noise sources, we propose Double Gumbel Q-Learning, a Deep Q-Learning algorithm applicable for b…