ZSC-Eval-policy_pool / random3_m /fcp /s2 /train-s24-sp-2.yml
leo98xh's picture
feat: :white_check_mark: update new hsp models and all random3_m models
5ebb1c6
fcp_adaptive:
policy_config_path: random3_m/policy_config/rnn_policy_config.pkl
featurize_type: ppo
train: True
sp1_1:
policy_config_path: random3_m/policy_config/mlp_policy_config.pkl
featurize_type: ppo
train: False
model_path:
actor: random3_m/fcp/s1/sp/sp3_init_actor.pt
sp1_2:
policy_config_path: random3_m/policy_config/mlp_policy_config.pkl
featurize_type: ppo
train: False
model_path:
actor: random3_m/fcp/s1/sp/sp3_mid_actor.pt
sp1_3:
policy_config_path: random3_m/policy_config/mlp_policy_config.pkl
featurize_type: ppo
train: False
model_path:
actor: random3_m/fcp/s1/sp/sp3_final_actor.pt
sp2_1:
policy_config_path: random3_m/policy_config/mlp_policy_config.pkl
featurize_type: ppo
train: False
model_path:
actor: random3_m/fcp/s1/sp/sp4_init_actor.pt
sp2_2:
policy_config_path: random3_m/policy_config/mlp_policy_config.pkl
featurize_type: ppo
train: False
model_path:
actor: random3_m/fcp/s1/sp/sp4_mid_actor.pt
sp2_3:
policy_config_path: random3_m/policy_config/mlp_policy_config.pkl
featurize_type: ppo
train: False
model_path:
actor: random3_m/fcp/s1/sp/sp4_final_actor.pt
sp3_1:
policy_config_path: random3_m/policy_config/mlp_policy_config.pkl
featurize_type: ppo
train: False
model_path:
actor: random3_m/fcp/s1/sp/sp5_init_actor.pt
sp3_2:
policy_config_path: random3_m/policy_config/mlp_policy_config.pkl
featurize_type: ppo
train: False
model_path:
actor: random3_m/fcp/s1/sp/sp5_mid_actor.pt
sp3_3:
policy_config_path: random3_m/policy_config/mlp_policy_config.pkl
featurize_type: ppo
train: False
model_path:
actor: random3_m/fcp/s1/sp/sp5_final_actor.pt
sp4_1:
policy_config_path: random3_m/policy_config/mlp_policy_config.pkl
featurize_type: ppo
train: False
model_path:
actor: random3_m/fcp/s1/sp/sp6_init_actor.pt
sp4_2:
policy_config_path: random3_m/policy_config/mlp_policy_config.pkl
featurize_type: ppo
train: False
model_path:
actor: random3_m/fcp/s1/sp/sp6_mid_actor.pt
sp4_3:
policy_config_path: random3_m/policy_config/mlp_policy_config.pkl
featurize_type: ppo
train: False
model_path:
actor: random3_m/fcp/s1/sp/sp6_final_actor.pt
sp5_1:
policy_config_path: random3_m/policy_config/mlp_policy_config.pkl
featurize_type: ppo
train: False
model_path:
actor: random3_m/fcp/s1/sp/sp7_init_actor.pt
sp5_2:
policy_config_path: random3_m/policy_config/mlp_policy_config.pkl
featurize_type: ppo
train: False
model_path:
actor: random3_m/fcp/s1/sp/sp7_mid_actor.pt
sp5_3:
policy_config_path: random3_m/policy_config/mlp_policy_config.pkl
featurize_type: ppo
train: False
model_path:
actor: random3_m/fcp/s1/sp/sp7_final_actor.pt
sp6_1:
policy_config_path: random3_m/policy_config/mlp_policy_config.pkl
featurize_type: ppo
train: False
model_path:
actor: random3_m/fcp/s1/sp/sp8_init_actor.pt
sp6_2:
policy_config_path: random3_m/policy_config/mlp_policy_config.pkl
featurize_type: ppo
train: False
model_path:
actor: random3_m/fcp/s1/sp/sp8_mid_actor.pt
sp6_3:
policy_config_path: random3_m/policy_config/mlp_policy_config.pkl
featurize_type: ppo
train: False
model_path:
actor: random3_m/fcp/s1/sp/sp8_final_actor.pt
sp7_1:
policy_config_path: random3_m/policy_config/mlp_policy_config.pkl
featurize_type: ppo
train: False
model_path:
actor: random3_m/fcp/s1/sp/sp9_init_actor.pt
sp7_2:
policy_config_path: random3_m/policy_config/mlp_policy_config.pkl
featurize_type: ppo
train: False
model_path:
actor: random3_m/fcp/s1/sp/sp9_mid_actor.pt
sp7_3:
policy_config_path: random3_m/policy_config/mlp_policy_config.pkl
featurize_type: ppo
train: False
model_path:
actor: random3_m/fcp/s1/sp/sp9_final_actor.pt
sp8_1:
policy_config_path: random3_m/policy_config/mlp_policy_config.pkl
featurize_type: ppo
train: False
model_path:
actor: random3_m/fcp/s1/sp/sp10_init_actor.pt
sp8_2:
policy_config_path: random3_m/policy_config/mlp_policy_config.pkl
featurize_type: ppo
train: False
model_path:
actor: random3_m/fcp/s1/sp/sp10_mid_actor.pt
sp8_3:
policy_config_path: random3_m/policy_config/mlp_policy_config.pkl
featurize_type: ppo
train: False
model_path:
actor: random3_m/fcp/s1/sp/sp10_final_actor.pt