AI Rank
← 开源
floodsung

DDPG

Reimplementation of DDPG(Continuous Control with Deep Reinforcement Learning) based on OpenAI Gym + Tensorflow

Model DevelopmentReinforcement LearningPython
在 GitHub 打开
增长势头
+024 小时新增 Star0.0%
577
Star
177
Fork
+1
本周
0
贡献者
创建于 2016-05-13 · 更新于 2026-10-12 · 今日第 16693 名

floodsung/DDPG 排名第 16,693，有 577 个星标。

同类别比较

floodsung/DDPG 排名第 16,693，此处有 8 个同类条目；facebookresearch/vicreg 排名第 16,692。

同类别比较
名称排名指标
Mostafa-Samir/DNC-tensorflow16,688
语言:
Jupyter Notebook
星标数:
577
分叉数:
161
简介:
A TensorFlow implementation of DeepMind's Differential Neural Computers (DNC)
Scalsol/mega.pytorch16,689
语言:
Python
星标数:
577
分叉数:
121
简介:
Memory Enhanced Global-Local Aggregation for Video Object Detection, CVPR2020
benmoseley/FBPINNs16,690
语言:
Python
星标数:
577
分叉数:
117
简介:
Solve forward and inverse problems related to partial differential equations using finite basis physics-informed neural networks (FBPINNs)
facebookresearch/vicreg16,692
语言:
Python
星标数:
577
分叉数:
92
简介:
VICReg official code base
huggingface/cosmopedia16,694
语言:
Python
星标数:
577
分叉数:
49
minosvasilias/godot-dodo16,698
语言:
Python
星标数:
577
分叉数:
28
简介:
Finetuning large language models for GDScript generation.
salesforce/CodeRL16,700
语言:
Python
星标数:
577
分叉数:
69
简介:
This is the official code for the paper CodeRL: Mastering Code Generation through Pretrained Models and Deep Reinforcement Learning (NeurIPS22).
xuhongzuo/DeepOD16,703
语言:
Python
星标数:
577
分叉数:
70
简介:
Deep learning-based outlier/anomaly detection
关键参数与规格
关键参数与规格
参数值
语言Python
类别Model Development
子类别Reinforcement Learning
关键词RL
星标数577
分叉数177
贡献者0
创建日期2016-05-13
更新日期2026-10-12
1 天星标数0
7 天星标数1
排名16,693
上次排名16,480
排名变化-213
7 天星标排名11,286
上次 7 天星标排名11,346
7 天星标排名变化60
总星标排名17,305
上次总星标排名17,275
总星标排名变化-30
国家China
README 摘录

DDPG Reimplementing DDPG from Continuous Control with Deep Reinforcement Learning based on OpenAI Gym and Tensorflow It is still a problem to implement Batch Normalization on the critic network. However the actor network works well with Batch Normalization. Some Mujoco environments are still unsolved on OpenAI Gym. Some Evaluations 1 InvertedPendulum 2 InvertedDoublePendulum 3 Hopper unsolved How to use If you want to change the Gym environment, change ENV_NAME in gym_ddpg. If you want to change the Network

type, change import in ddpg.

常见问题

记录了多少星标和分叉？

floodsung/DDPG 有 577 个星标和 177 个分叉。

仓库排名是多少？

floodsung/DDPG 排名第 16,693。

记录的语言和类别是什么？

floodsung/DDPG 有 577 个星标，语言为 Python，类别为 Model Development。

哪个仓库排名最接近？

floodsung/DDPG 与 facebookresearch/vicreg 比较，后者排名第 16,692，有 577 个星标。

README

DDPG

Reimplementing DDPG from Continuous Control with Deep Reinforcement Learning based on OpenAI Gym and Tensorflow

http://arxiv.org/abs/1509.02971

It is still a problem to implement Batch Normalization on the critic network. However the actor network works well with Batch Normalization.

Some Mujoco environments are still unsolved on OpenAI Gym.

Some Evaluations

1 InvertedPendulum

2 InvertedDoublePendulum

3 Hopper unsolved

How to use

git clone https://github.com/songrotek/DDPG.git
cd DDPG
python gym_ddpg.py

If you want to change the Gym environment, change ENV_NAME in gym_ddpg.py.

If you want to change the Network type, change import in ddpg.py such as

from actor_network_bn import ActorNetwork
to
from actor_network import ActorNetwork

Reference

1 https://github.com/rllab/rllab

2 https://github.com/MOCR/DDPG

3 https://github.com/SimonRamstedt/ddpg

排名相邻
同类项目