DDPG Explained | Papers With Code

Deep Deterministic Policy Gradient

Introduced by Lillicrap et al. in Continuous control with deep reinforcement learning

DDPG, or Deep Deterministic Policy Gradient, is an actor-critic, model-free algorithm based on the deterministic policy gradient that can operate over continuous action spaces. It combines the actor-critic approach with insights from DQNs: in particular, the insights that 1) the network is trained off-policy with samples from a replay buffer to minimize correlations between samples, and 2) the network is trained with a target Q network to give consistent targets during temporal difference backups. DDPG makes use of the same ideas along with batch normalization.

Source: Continuous control with deep reinforcement learning

Paper

Latest Papers

PAPER	DATE
Truly Deterministic Policy Optimization Anonymous	2021-01-01
Reinforcement Learning for Control of Valves \| Rajesh Siraskar	2020-12-29
Policy Gradient RL Algorithms as Directed Acyclic Graphs \| Juan Jose Garau Luis	2020-12-14
Efficient Reservoir Management through Deep Reinforcement Learning Xinrun Wang • Tarun Nair • Haoyang Li • Yuh Sheng Reuben Wong • Nachiket Kelkar • Srinivas Vaidyanathan • Rajat Nayak • Bo An • Jagdish Krishnaswamy • Milind Tambe	2020-12-07
FinRL: A Deep Reinforcement Learning Library for Automated Stock Trading in Quantitative Finance \| Xiao-Yang Liu • Hongyang Yang • Qian Chen • Runjia Zhang • Liuqing Yang • Bowen Xiao • Christina Dan Wang	2020-11-19
Tonic: A Deep Reinforcement Learning Library for Fast Prototyping and Benchmarking \| Fabio Pardo	2020-11-15
Recurrent Distributed Reinforcement Learning for Partially Observable Robotic Assembly Jieliang Luo • Hui Li	2020-10-15
Hindsight Experience Replay with Kronecker Product Approximate Curvature Dhuruva Priyan G M • Abhik Singla • Shalabh Bhatnagar	2020-10-09
Knowledge-Assisted Deep Reinforcement Learning in 5G Scheduler Design: From Theoretical Framework to Implementation Zhouyou Gu • Changyang She • Wibowo Hardjawana • Simon Lumb • David McKechnie • Todd Essery • Branka Vucetic	2020-09-17
Human-like Energy Management Based on Deep Reinforcement Learning and Historical Driving Experiences Teng Liu • Xiaolin Tang • Xiaosong Hu • Wenhao Tan • Jinwei Zhang	2020-07-16
Regularly Updated Deterministic Policy Gradient Algorithm Shuai Han • Wenbo Zhou • Shuai Lü • Jiayu Yu	2020-07-01
Distributed Uplink Beamforming in Cell-Free Networks Using Deep Reinforcement Learning Firas Fredj • Yasser Al-Eryani • Setareh Maghsudi • Mohamed Akrout • Ekram Hossain	2020-06-26
Noise, overestimation and exploration in Deep Reinforcement Learning Rafael Stekolshchik	2020-06-25
The Effect of Multi-step Methods on Overestimation in Deep Reinforcement Learning Lingheng Meng • Rob Gorbet • Dana Kulić	2020-06-23
Reducing Estimation Bias via Weighted Delayed Deep Deterministic Policy Gradient Qiang He • Xinwen Hou	2020-06-18
An online evolving framework for advancing reinforcement-learning based automated vehicle control Teawon Han • Subramanya Nageshrao • Dimitar P. Filev • Umit Ozguner	2020-06-15
Optimization-driven Deep Reinforcement Learning for Robust Beamforming in IRS-assisted Wireless Communications Jiaye Lin • Yuze Zou • Xiaoru Dong • Shimin Gong • Dinh Thai Hoang • Dusit Niyato	2020-05-25
PBCS : Efficient Exploration and Exploitation Using a Synergy between Reinforcement Learning and Motion Planning Guillaume Matheron • Nicolas Perrin • Olivier Sigaud	2020-04-24
Model-based actor-critic: GAN + DRL (actor-critic) => AGI Aras Dargazany	2020-04-04
Obstacle Avoidance and Navigation Utilizing Reinforcement Learning with Reward Shaping Daniel Zhang • Colleen P. Bailey	2020-03-28
Accelerating Deep Reinforcement Learning With the Aid of Partial Model: Energy-Efficient Predictive Video Streaming Dong Liu • Jianyu Zhao • Chenyang Yang • Lajos Hanzo	2020-03-21
Robust Deep Reinforcement Learning against Adversarial Perturbations on State Observations \| Huan Zhang • Hongge Chen • Chaowei Xiao • Bo Li • Mingyan Liu • Duane Boning • Cho-Jui Hsieh	2020-03-19
Adaptive Discretization for Continuous Control using Particle Filtering Policy Network \| Pei Xu • Ioannis Karamouzas	2020-03-16
Online Meta-Critic Learning for Off-Policy Actor-Critic Methods Wei Zhou • Yiying Li • Yongxin Yang • Huaimin Wang • Timothy M. Hospedales	2020-03-11
Dynamic Experience Replay Jieliang Luo • Hui Li	2020-03-04

Tasks

TASK	PAPERS	SHARE
Continuous Control	20	40.82%
Autonomous Driving	4	8.16%
Decision Making	3	6.12%
Imitation Learning	3	6.12%
Efficient Exploration	2	4.08%
Motion Planning	2	4.08%
adversarial training	2	4.08%
Meta-Learning	2	4.08%
Hypothesis Testing	1	2.04%

Usage Over Time

This feature is experimental; we are continuously improving our matching algorithm.

Components

COMPONENT	TYPE	Add Remove
Adam	Stochastic Optimization
Batch Normalization	Normalization
Convolution	Convolutions
Dense Connections	Feedforward Networks
Experience Replay	Replay Memory
ReLU	Activation Functions
Weight Decay	Regularization

Categories

Add Remove

Policy Gradient Methods