Skip to main content

Regression Report: sac_continuous_action

[['?we=openrlbenchmark&wpn=sb3&ceik=env&cen=algo&metric=rollout/ep_rew_mean', 'a2c', 'ddpg', 'ppo_lstm?cl=PPO w/ LSTM', 'sac', 'td3', 'ppo', 'trpo'], ['?we=openrlbenchmark&wpn=cleanrl&ceik=env_id&cen=exp_name&metric=charts/episodic_return', 'sac_continuous_action?tag=rlops-pilot&cl=SAC']]
Created on May 5|Last edited on May 5

500k1M1.5M2MSteps-1000010002000Episodic Return
100200300400500Time (minutes)-10000100020003000Episodic Return
openrlbenchmark/sb3/a2c ({})
10
openrlbenchmark/sb3/ddpg ({})
11
PPO w/ LSTM
10
openrlbenchmark/sb3/sac ({})
11
openrlbenchmark/sb3/td3 ({})
11
openrlbenchmark/sb3/ppo ({})
27
openrlbenchmark/sb3/trpo ({})
10
SAC
3