diff --git a/spinup/examples/pytorch/Hybrid_SAC.py b/spinup/examples/pytorch/Hybrid_SAC.py index 91809ab34..4e59f247e 100644 --- a/spinup/examples/pytorch/Hybrid_SAC.py +++ b/spinup/examples/pytorch/Hybrid_SAC.py @@ -9,7 +9,7 @@ TRAIN=1 env_fn = lambda: gym.make('Fep-v0') -exp_name = "TEST_Slurm" +exp_name = "Fepv0_15_lr0002_3000epochs_lp130_separated_pose_errors" if __name__ == '__main__': if TRAIN: # train @@ -17,7 +17,7 @@ if not os.path.exists(output_dir): os.makedirs(output_dir) logger_kwargs = dict(output_dir=output_dir, exp_name=exp_name) - sac(env_fn, ac_kwargs={}, seed=0, steps_per_epoch=100, epochs=200, replay_size=1000000, gamma=0.99, polyak=0.995, + sac(env_fn, ac_kwargs={}, seed=0, steps_per_epoch=100, epochs=3000, replay_size=1000000, gamma=0.99, polyak=0.995, lr=0.002, alpha_init=0.001, batch_size=100, start_steps=10000, update_after=10000, update_every=100, num_test_episodes=2, max_ep_len=np.inf, logger_kwargs=logger_kwargs, save_freq=1, initial_actions="random", save_buffer=True, sample_mode = 1, automatic_entropy_tuning=True) else: