search

TianhongDai / reinforcement-learning-algorithms

This repository contains most of pytorch implementation based classic deep reinforcement learning algorithms, including - DQN, DDQN, Dueling Network, DDPG, SAC, A2C, PPO, TRPO. (More algorithms are still in progress)
666 stars 110 forks source link

How to visualize reward-epoch? #1

Open ShaoyuanLi opened 6 years ago

ShaoyuanLi commented 6 years ago

How to visualize reward-epoch? Does It need extra code for post-processing(post-process print infomation) or is there some tools for visualization? I cound not find the extra code in github project.

TianhongDai commented 6 years ago

@ShaoyuanLi Hi, for most algorithms in my repository, I record the log information by using python -u train.py 2>&1 | tee loginfo.log. Then, I write a python script to extract the information from it and plot the reward curve. For a2c, I use the scripts of openai-baselines. You could check the code here: https://github.com/openai/baselines/blob/master/baselines/results_plotter.py

TianhongDai commented 6 years ago

@ShaoyuanLi And thanks for reminding me, I will update the reward visualising function in the future.