Classic Control Environments Benchmarks

Run Parameters

n_runs

25

n_epochs

100

n_episodes

10

n_episodes_test

5

InvertedPendulum

COPDAC_Q:
  alpha_omega: 0.5
  alpha_theta: 0.005
  alpha_v: 0.5
  n_tiles: 11
  n_tilings: 10
  std_eval: 0.001
  std_exp: 0.1
StochasticAC:
  alpha_theta: 0.001
  alpha_v: 0.1
  lambda_par: 0.9
  n_tiles: 11
  n_tilings: 10
  std_0: 1.0
../../../_images/J4.png ../../../_images/R4.png