huangfu/InteractionImitation
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

adding final bc configs, updating experiment to validate in longer intervals

Browse Source
This commit is contained in:
Arec Jamgochian
2022-02-27 20:40:24 -08:00
parent 5f77398fd0
commit e110570092
5 changed files with 7 additions and 7 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
bc-experiment.py
View File

@@ -117,7 +117,7 @@ def training_function(config):
pi_opt.step() pi_opt.step()
pi_lr_scheduler.step() pi_lr_scheduler.step()
if epoch % 10 == 0: if epoch % 25 == 0:
gen_states, gen_actions, gen_rewards, gen_dones, gen_collisions = rollout(env_fn, policy.cpu(), n_episodes=60, max_steps_per_episode=200) gen_states, gen_actions, gen_rewards, gen_dones, gen_collisions = rollout(env_fn, policy.cpu(), n_episodes=60, max_steps_per_episode=200)
gen_mean_episode_length = (~gen_dones).sum() / gen_states.shape[0] gen_mean_episode_length = (~gen_dones).sum() / gen_states.shape[0]
gen_mean_reward_per_episode = gen_rewards[~gen_dones].sum() / gen_states.shape[0] gen_mean_reward_per_episode = gen_rewards[~gen_dones].sum() / gen_states.shape[0]

2
best_configs/bc_expA.json
View File

@@ -10,6 +10,6 @@
"n_hidden_layers": 2, "n_hidden_layers": 2,
"activation": 0 "activation": 0
}, },
"train_epochs": 1000, "train_epochs": 300,
"seed": 0 "seed": 0
} }

2
best_configs/bc_expB.json
View File

@@ -10,6 +10,6 @@
"n_hidden_layers": 2, "n_hidden_layers": 2,
"activation": 0 "activation": 0
}, },
"train_epochs": 1000, "train_epochs": 300,
"seed": 0 "seed": 0
} }

4
gail-experiment.py
View File

@@ -187,8 +187,8 @@ if __name__ == '__main__':
}, },
'discriminator': { 'discriminator': {
'learning_rate': 1e-3, 'learning_rate': 1e-3,
'weight_decay': 1e-4, # 1e-5 Fixme 'weight_decay': 1e-4,
'iterations_per_epoch': 100, # 500 Fixme 'iterations_per_epoch': 100,
'n_hidden_layers_element': tune.grid_search([3,4]), 'n_hidden_layers_element': tune.grid_search([3,4]),
'n_hidden_layers_global': tune.grid_search([1,2]), 'n_hidden_layers_global': tune.grid_search([1,2]),
'hidden_layer_size': 10, 'hidden_layer_size': 10,

4
gail-trpo-experiment.py
View File

@@ -184,8 +184,8 @@ if __name__ == '__main__':
}, },
'discriminator': { 'discriminator': {
'learning_rate': 1e-3, 'learning_rate': 1e-3,
'weight_decay': 1e-4, # 1e-5 Fixme 'weight_decay': 1e-4,
'iterations_per_epoch': 100, # 500 Fixme 'iterations_per_epoch': 100,
'n_hidden_layers_element': tune.grid_search([3,4]), 'n_hidden_layers_element': tune.grid_search([3,4]),
'n_hidden_layers_global': tune.grid_search([1,2]), 'n_hidden_layers_global': tune.grid_search([1,2]),
'hidden_layer_size': 10, 'hidden_layer_size': 10,