Skip to main content
openrlbenchmark
Projects
sb3
Reports
Open RL Benchmark Prototype

Open RL Benchmark Prototype

Costa Huang
Created on March 4|Last edited on April 27

Computing group metrics from first 10 groups
50M100M150M200M250MStep0200040006000Episodic Return
CleanRL , env_id: CartPole-v1, exp_name: dqn
CleanRL , env_id: CartPole-v1, exp_name: ppo
SB3 , env: Walker2DBulletEnv-v0, algo: ppo
SB3 , env: HumanoidBulletEnv-v0, algo: sac
SB3 , env: FetchPush-v1, algo: tqc
SB3 , env: FetchSlide-v1, algo: tqc
SB3 , env: Humanoid-v3, algo: ars
SB3 , env: BipedalWalkerHardcore-v3, algo: td3
SB3 , env: Walker2d-v3, algo: ars
SB3 , env: EnduroNoFrameskip-v4, algo: ppo_lstm
SB3
2249
CleanRL
10



CleanRL
3
Tianshou
1
SB3
49



Run set
105
Run set 2
0


Created with ❤️ on Weights & Biases.

https://wandb.ai/openrlbenchmark/sb3/reports/Open-RL-Benchmark-Prototype--VmlldzoxNjQ2NDkx
Made with Weights & Biases. Sign up or log in to create reports like this one.