lufficc / Dqn
Implementation of q-learning using TensorFlow
Stars: ✭ 53
Programming Languages
python
139335 projects - #7 most used programming language
Projects that are alternatives of or similar to Dqn
Awesome Monte Carlo Tree Search Papers
A curated list of Monte Carlo tree search papers with implementations.
Stars: ✭ 387 (+630.19%)
Mutual labels: reinforcement-learning, q-learning
Deep traffic
MIT DeepTraffic top 2% solution (75.01 mph) 🚗.
Stars: ✭ 47 (-11.32%)
Mutual labels: reinforcement-learning, q-learning
Reinforcement learning tutorial with demo
Reinforcement Learning Tutorial with Demo: DP (Policy and Value Iteration), Monte Carlo, TD Learning (SARSA, QLearning), Function Approximation, Policy Gradient, DQN, Imitation, Meta Learning, Papers, Courses, etc..
Stars: ✭ 442 (+733.96%)
Mutual labels: reinforcement-learning, q-learning
Trading Bot
Stock Trading Bot using Deep Q-Learning
Stars: ✭ 273 (+415.09%)
Mutual labels: reinforcement-learning, q-learning
Basic reinforcement learning
An introductory series to Reinforcement Learning (RL) with comprehensive step-by-step tutorials.
Stars: ✭ 826 (+1458.49%)
Mutual labels: reinforcement-learning, q-learning
Dinoruntutorial
Accompanying code for Paperspace tutorial "Build an AI to play Dino Run"
Stars: ✭ 285 (+437.74%)
Mutual labels: reinforcement-learning, q-learning
Dissecting Reinforcement Learning
Python code, PDFs and resources for the series of posts on Reinforcement Learning which I published on my personal blog
Stars: ✭ 512 (+866.04%)
Mutual labels: reinforcement-learning, q-learning
Deep Rl Trading
playing idealized trading games with deep reinforcement learning
Stars: ✭ 228 (+330.19%)
Mutual labels: reinforcement-learning, q-learning
Reinforcement Learning With Tensorflow
Simple Reinforcement learning tutorials, 莫烦Python 中文AI教学
Stars: ✭ 6,948 (+13009.43%)
Mutual labels: reinforcement-learning, q-learning
Hands On Reinforcement Learning With Python
Master Reinforcement and Deep Reinforcement Learning using OpenAI Gym and TensorFlow
Stars: ✭ 640 (+1107.55%)
Mutual labels: reinforcement-learning, q-learning
Grid royale
A life simulation for exploring social dynamics
Stars: ✭ 252 (+375.47%)
Mutual labels: reinforcement-learning, q-learning
Async Deeprl
Playing Atari games with TensorFlow implementation of Asynchronous Deep Q-Learning
Stars: ✭ 44 (-16.98%)
Mutual labels: reinforcement-learning, q-learning
Learningx
Deep & Classical Reinforcement Learning + Machine Learning Examples in Python
Stars: ✭ 241 (+354.72%)
Mutual labels: reinforcement-learning, q-learning
Qtrader
Reinforcement Learning for Portfolio Management
Stars: ✭ 363 (+584.91%)
Mutual labels: reinforcement-learning, q-learning
Data Science Free
Free Resources For Data Science created by Shubham Kumar
Stars: ✭ 232 (+337.74%)
Mutual labels: reinforcement-learning, q-learning
2048 Deep Reinforcement Learning
Trained A Convolutional Neural Network To Play 2048 using Deep-Reinforcement Learning
Stars: ✭ 169 (+218.87%)
Mutual labels: reinforcement-learning, q-learning
Rl trading
An environment to high-frequency trading agents under reinforcement learning
Stars: ✭ 205 (+286.79%)
Mutual labels: reinforcement-learning, q-learning
Gym Anytrading
The most simple, flexible, and comprehensive OpenAI Gym trading environment (Approved by OpenAI Gym)
Stars: ✭ 627 (+1083.02%)
Mutual labels: reinforcement-learning, q-learning
Gym Alttp Gridworld
A gym environment for Stuart Armstrong's model of a treacherous turn.
Stars: ✭ 14 (-73.58%)
Mutual labels: reinforcement-learning, q-learning
Deep Q Network
An implementation of q algorithm of Reinforcement Learning.
Installation Dependencies:
- Python 3
- TensorFlow 1.0.1
- pygame
- gym
How to Run?
git clone https://github.com/lufficc/dqn.git
cd dqn
python run.py
Tricks for flappybird
resize and using binary image:
decayed ε-greedy exploration, and when exploration, 0.95 probability to do nothing(because in flappy bird, most time wo do nothing). This is very important. It makes model converge in less than 2 hours.
def egreedy_action(self, state):
#Exploration
if random.random() <= self.epsilon:
if random.random() < 0.95:
action_index = 0
else:
action_index = 1
# action_index = random.randint(0, self.num_actions - 1)
else:
#Exploitation
action_index = self.action(state)
if self.epsilon > self.final_epsilon:
self.epsilon *= self.decay_factor
return action_index
Thanks
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].