ElegantRL
Deep-Reinforcement-Learning-Algorithms
Our great sponsors
| ElegantRL | Deep-Reinforcement-Learning-Algorithms | |
|---|---|---|
| 6 | 3 | |
| 3,436 | 580 | |
| 3.2% | - | |
| 7.4 | 3.6 | |
| 7 days ago | almost 3 years ago | |
| Python | Jupyter Notebook | |
| GNU General Public License v3.0 or later | - |
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
ElegantRL
- Does “massively parallel simulation” help advance Reinforcement Learning?
- ElegantRL: Cloud-Native Deep Reinforcement Learning
- ElegantRL: A Lightweight and Stable Deep Reinforcement Learning Library
-
[R] ElegantRL: A Lightweight and Stable Deep Reinforcement Learning Library
The ElegantRL library is featured with “elegant” in the following aspects:
- Lightweight, Efficient and Stable DRL Library
- Lightweight, Efficient and Stable DRL Implementation Using PyTorch
Deep-Reinforcement-Learning-Algorithms
-
Is there a canonical simple "helloworld" neural network design? Something beyond AND/OR logic, a handful of nodes that does something mildly "useful"?
I guess the most spectacular in terms of performance/"brain size" ratio is a 2 neuron, 8 weights network https://github.com/Rafael1s/Deep-Reinforcement-Learning-Algorithms/tree/master/CartPole-Policy-Based-Hill-Climbing
-
Training time of CartPole is way to long
It can be solved in 113 episodes by Hill Climbing algorithm, https://github.com/Rafael1s/Deep-Reinforcement-Learning-Algorithms/tree/master/CartPole-Policy-Based-Hill-Climbingor by Double Deep Q-Learning in 612 episodes, https://github.com/Rafael1s/Deep-Reinforcement-Learning-Algorithms/tree/master/Cartpole-Double-Deep-Q-Learning
-
Need help with PyTorch script for Actor_Critic implementation of MountainCar env.
You can find the solution for MountainCar env here: https://github.com/Rafael1s/Deep-Reinforcement-Learning-Algorithms/tree/master/MountainCarContinuous-TD3This solution implemented using PyTorch. The TD3 model is the successor to DDPG algorithm using the Actor-Critic model.
What are some alternatives?
stable-baselines3 - PyTorch version of Stable Baselines, reliable implementations of reinforcement learning algorithms.
Deep-Reinforcement-Learning-for-Automated-Stock-Trading-Ensemble-Strategy-ICAIF-2020 - Deep Reinforcement Learning for Automated Stock Trading: An Ensemble Strategy. ICAIF 2020. Please star. [Moved to: https://github.com/AI4Finance-Foundation/Deep-Reinforcement-Learning-for-Automated-Stock-Trading-Ensemble-Strategy-ICAIF-2020]
Ray - Ray is a unified framework for scaling AI and Python applications. Ray consists of a core distributed runtime and a set of AI Libraries for accelerating ML workloads.
Popular-RL-Algorithms - PyTorch implementation of Soft Actor-Critic (SAC), Twin Delayed DDPG (TD3), Actor-Critic (AC/A2C), Proximal Policy Optimization (PPO), QT-Opt, PointNet..
tianshou - An elegant PyTorch deep reinforcement learning library.
DeepRL-TensorFlow2 - 🐋 Simple implementations of various popular Deep Reinforcement Learning algorithms using TensorFlow2
minimalRL - Implementations of basic RL algorithms with minimal lines of codes! (pytorch based)
pytorch-ddpg - Deep deterministic policy gradient (DDPG) in PyTorch 🚀
rl_lib - Series of deep reinforcement learning algorithms 🤖
machin - Reinforcement learning library(framework) designed for PyTorch, implements DQN, DDPG, A2C, PPO, SAC, MADDPG, A3C, APEX, IMPALA ...
pomdp-baselines - Simple (but often Strong) Baselines for POMDPs in PyTorch, ICML 2022