Select runs that logged charts/episode_reward
to visualize data in this line chart.
to visualize data in this line chart.
Carey debugging
Created on March 26|Last edited on March 26
Comment
Interactive RL Benchmark by CleanRL
The code is available at https://github.com/vwxyzjn/cleanrl, and this file benchmark.sh produced the runs that are used in this report.
In this page, we showed the performances of various DRL algorithms in diverse game environments. It gives us important information regarding the learnability and generality of algorithms. The charts are interactive. Feel free to add different visualization and click on a specific run to see its hyper-parameters.
CartPole-v0
Select runs that logged video.0 to visualize data here.
Run set
0
MountainCar-v0
MountainCarContinuous-v0
Walker2DBulletEnv-v0
Run set
8
HumanoidBulletEnv-v0
ReacherBulletEnv-v0
BipedalWalker-v2
Pendulum-v0
HopperBulletEnv-v0
InvertedPendulumBulletEnv-v0
LunarLander-v2
Run set
4
Taxi-v3
Run set
0
Add a comment