Skip to content

Instantly share code, notes, and snippets.

@kengz

kengz/sac_benchmark.md

Last active August 11, 2019 18:22
Show Gist options
  • Save kengz/5bc352e18c24ce1fdb4a8679bbb1624a to your computer and use it in GitHub Desktop.
Save kengz/5bc352e18c24ce1fdb4a8679bbb1624a to your computer and use it in GitHub Desktop.
Download ZIP
SAC benchmark
Raw
sac_benchmark.md

Roboschool (continuous control) Benchmark

Note that the Roboschool reward scales are different from MuJoCo's. All results are ran with 4 sessions with distinct random seeds. mean_returns_ma is the returns moving-average over 100 checkpoints from the sessions averaged.

Env. \ SAC mean_returns_ma graph
RoboschoolAnt 2451.55 sac
RoboschoolHalfCheetah 2004.27 sac
RoboschoolHopper 2090.52 sac
RoboschoolWalker2d 1711.92 sac

LunarLander (discrete control) Benchmark
sac_lunar_t0_trial_graph_mean_returns_vs_frames sac_lunar_t0_trial_graph_mean_returns_ma_vs_frames
Trial graph Moving average
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment