stevenpjg / Ddpg Aigym
Licence: mit
Continuous control with deep reinforcement learning - Deep Deterministic Policy Gradient (DDPG) algorithm implemented in OpenAI Gym environments
Stars: ✭ 225
Programming Languages
python
139335 projects - #7 most used programming language
Projects that are alternatives of or similar to Ddpg Aigym
Epg
Code for the paper "Evolved Policy Gradients"
Stars: ✭ 204 (-9.33%)
Mutual labels: reinforcement-learning
Reinforcement Learning An Introduction Chinese
《Reinforcement Learning: An Introduction》（第二版）中文翻译
Stars: ✭ 210 (-6.67%)
Mutual labels: reinforcement-learning
Rl trading
An environment to high-frequency trading agents under reinforcement learning
Stars: ✭ 205 (-8.89%)
Mutual labels: reinforcement-learning
Alphazero gomoku
An implementation of the AlphaZero algorithm for Gomoku (also called Gobang or Five in a Row)
Stars: ✭ 2,570 (+1042.22%)
Mutual labels: reinforcement-learning
Awesome Deeplearning Resources
Deep Learning and deep reinforcement learning research papers and some codes
Stars: ✭ 2,483 (+1003.56%)
Mutual labels: reinforcement-learning
Gym Unrealcv
Unreal environments for reinforcement learning
Stars: ✭ 202 (-10.22%)
Mutual labels: reinforcement-learning
Pilco
Bayesian Reinforcement Learning in Tensorflow
Stars: ✭ 222 (-1.33%)
Mutual labels: reinforcement-learning
Gymfc
A universal flight control tuning framework
Stars: ✭ 210 (-6.67%)
Mutual labels: reinforcement-learning
Autodrome
Framework and OpenAI Gym Environment for Autonomous Vehicle Development
Stars: ✭ 214 (-4.89%)
Mutual labels: reinforcement-learning
Rl Tutorial Jnrr19
Stable-Baselines tutorial for Journées Nationales de la Recherche en Robotique 2019
Stars: ✭ 204 (-9.33%)
Mutual labels: reinforcement-learning
Pytorch A2c Ppo Acktr Gail
PyTorch implementation of Advantage Actor Critic (A2C), Proximal Policy Optimization (PPO), Scalable trust-region method for deep reinforcement learning using Kronecker-factored approximation (ACKTR) and Generative Adversarial Imitation Learning (GAIL).
Stars: ✭ 2,632 (+1069.78%)
Mutual labels: reinforcement-learning
Reco Papers
Classic papers and resources on recommendation
Stars: ✭ 2,804 (+1146.22%)
Mutual labels: reinforcement-learning
Minerva
Meandering In Networks of Entities to Reach Verisimilar Answers
Stars: ✭ 205 (-8.89%)
Mutual labels: reinforcement-learning
Multihopkg
Multi-hop knowledge graph reasoning learned via policy gradient with reward shaping and action dropout
Stars: ✭ 202 (-10.22%)
Mutual labels: reinforcement-learning
Pytorch Reinforce
PyTorch Implementation of REINFORCE for both discrete & continuous control
Stars: ✭ 212 (-5.78%)
Mutual labels: reinforcement-learning
Machine Learning Notebooks
Machine Learning notebooks for refreshing concepts.
Stars: ✭ 222 (-1.33%)
Mutual labels: reinforcement-learning
Ns3 Gym
ns3-gym - The Playground for Reinforcement Learning in Networking Research
Stars: ✭ 221 (-1.78%)
Mutual labels: reinforcement-learning
Pokerrl
Framework for Multi-Agent Deep Reinforcement Learning in Poker
Stars: ✭ 214 (-4.89%)
Mutual labels: reinforcement-learning
ddpg-aigym
Deep Deterministic Policy Gradient
Implementation of Deep Deterministic Policy Gradiet Algorithm (Lillicrap et al.arXiv:1509.02971.) in Tensorflow
How to use
git clone https://github.com/stevenpjg/ddpg-aigym.git
cd ddpg-aigym
python main.py
During training
Once trained
Learning Curve
The learning curve for InvertedPendulum-v1 environment.
Dependencies
- Tensorflow (Developed in tensorflow version 0.11.0rc0 [CPU version] [GPU version])
- OpenAi gym
- Mujoco
Features
- Batch Normalization (improvement in learning speed)
- Grad-inverter (given in arXiv: arXiv:1511.04143)
Note
To use different environment
experiment= 'InvertedPendulum-v1' #specify environments here
To use batch normalization
is_batch_norm = True #batch normalization switch
Let me know if there are any issues and clarifications regarding hyperparameter tuning.
Note that the project description data, including the texts, logos, images, and/or trademarks,
for each open source project belongs to its rightful owner.
If you wish to add or remove any projects, please contact us at [email protected].