Reinforcement learning 11 Try OpenAI acrobot with ChainerRL.

It is assumed that you have achieved reinforcement learning up to 10. If you google with openai acrobot, Acrobot-v1 will come out. I'm not sure about v1 or v0, so I'll investigate before remodeling. userfolder/anaconda3/envs/chainer/lib/python3.7/site-packages/gym Open in VS Code. A full search on CartPole found CartPole-v0 and CartPole-v1. Hmmm? In acrobot, only Acrobot-v1. I tried running CartPole-v0 instead of CartPole-v1 with the CartPole I made earlier. It seems that the difficulty level is increasing.

I replaced it as it was, but something was different. .. .. .. Acrobot is a pendulum movement, and you can get a reward for success by bringing it to a certain height. Let's set it so that the value in the future is not discounted so much. I set gamma to 0.99 and it seems to be working.

I am using DQN (Deep Q Network). There are many explanations, so it's a good idea to google.

Recommended Posts

Reinforcement learning 11 Try OpenAI acrobot with ChainerRL.
Reinforcement learning 13 Try Mountain_car with ChainerRL.
Reinforcement learning 28 colaboratory + OpenAI + chainerRL
Reinforcement learning 3 OpenAI installation
[Mac] I tried reinforcement learning with OpenAI Baselines
Reinforcement learning 18 Colaboratory + Acrobat + ChainerRL
Play with reinforcement learning with MuZero
Reinforcement learning 17 Colaboratory + CartPole + ChainerRL
Reinforcement learning 19 Colaboratory + Mountain_car + ChainerRL
Reinforcement learning 2 Installation of chainerrl
Try running CNN with ChainerRL
Try Deep Learning with FPGA
Reinforcement learning 5 Try programming CartPole?
Reinforcement learning 9 ChainerRL magic remodeling
Try machine learning with Kaggle
Reinforcement learning in the shortest time with Keras with OpenAI Gym
Reinforcement learning 21 Colaboratory + Pendulum + ChainerRL + A2C
Try deep learning with TensorFlow Part 2
Reinforcement learning 22 Colaboratory + CartPole + ChainerRL + A3C
Explore the maze with reinforcement learning
Try machine learning with scikit-learn SVM
Reinforcement learning 8 Try using Chainer UI
Reinforcement learning 24 Colaboratory + CartPole + ChainerRL + ACER
Try Common Representation Learning with chainer
I tried deep reinforcement learning (Double DQN) for tic-tac-toe with ChainerRL
[Reinforcement learning] DQN with your own library
Try Bitcoin Price Forecasting with Deep Learning
Try with Chainer Deep Q Learning --Launch
Try deep learning of genomics with Kipoi
Reinforcement learning 14 Pendulum was done at ChainerRL.
[Python] Easy Reinforcement Learning (DQN) with Keras-RL
[Introduction] Reinforcement learning
Reinforcement learning 10 Try using a trained neural network.
See the behavior of drunkenness with reinforcement learning
[Reinforcement learning] Experience Replay is easy with cpprb!
Reinforcement learning 12 ChainerRL quick start guide windows version
Future reinforcement learning_2
Future reinforcement learning_1
Reinforcement learning 27 colaboratory 90-minute rule measures chainerRL (+ chokozainerRL)
Challenge block breaking with Actor-Critic model reinforcement learning
I want to climb a mountain with reinforcement learning
Reinforcement learning 37 Make an automatic start with Atari's wrapper
Try scraping with Python.
Learning Python with ChemTHEATER 03
"Object-oriented" learning with python
Reinforcement learning 1 Python installation
Learning Python with ChemTHEATER 05-1
Reinforcement learning for tic-tac-toe
Learning Python with ChemTHEATER 02
Learning Python with ChemTHEATER 01
Try SNN with BindsNET
Python + Unity Reinforcement Learning (Learning)
Try to make a blackjack strategy by reinforcement learning (③ Reinforcement learning in your own OpenAI Gym environment)
Try regression with TensorFlow
[Machine learning] Start Spark with iPython Notebook and try MLlib
Try to build a deep learning / neural network with scratch
[Evangelion] Try to automatically generate Asuka-like lines with Deep Learning
Try to predict if tweets will burn with machine learning
[Introduction to Reinforcement Learning] Reinforcement learning to try moving for the time being
Try Q-learning in Dragon Quest-style battle [Introduction to Reinforcement Learning]
Reinforcement learning 23 Create and use your own module with Colaboratory