diff --git a/out/gail/expA/loc_r0t0/policy_seed1_tseed0_comparison.pkl b/out/gail/expA/loc_r0t0/policy_seed1_tseed0_comparison.pkl index 29bedc8..97a3947 100644 Binary files a/out/gail/expA/loc_r0t0/policy_seed1_tseed0_comparison.pkl and b/out/gail/expA/loc_r0t0/policy_seed1_tseed0_comparison.pkl differ diff --git a/out/gail/expA/loc_r0t0/policy_seed1_tseed0_summary.pkl b/out/gail/expA/loc_r0t0/policy_seed1_tseed0_summary.pkl index ecec438..5ed53a8 100644 Binary files a/out/gail/expA/loc_r0t0/policy_seed1_tseed0_summary.pkl and b/out/gail/expA/loc_r0t0/policy_seed1_tseed0_summary.pkl differ diff --git a/out/gail/expA/loc_r0t0/policy_seed2_tseed0_comparison.pkl b/out/gail/expA/loc_r0t0/policy_seed2_tseed0_comparison.pkl index c753646..54ef594 100644 Binary files a/out/gail/expA/loc_r0t0/policy_seed2_tseed0_comparison.pkl and b/out/gail/expA/loc_r0t0/policy_seed2_tseed0_comparison.pkl differ diff --git a/out/gail/expA/loc_r0t0/policy_seed2_tseed0_summary.pkl b/out/gail/expA/loc_r0t0/policy_seed2_tseed0_summary.pkl index 5ebcb8b..9587401 100644 Binary files a/out/gail/expA/loc_r0t0/policy_seed2_tseed0_summary.pkl and b/out/gail/expA/loc_r0t0/policy_seed2_tseed0_summary.pkl differ diff --git a/out/gail/expA/loc_r0t0/policy_seed3_tseed0_comparison.pkl b/out/gail/expA/loc_r0t0/policy_seed3_tseed0_comparison.pkl index 18d1dbb..f0bbd04 100644 Binary files a/out/gail/expA/loc_r0t0/policy_seed3_tseed0_comparison.pkl and b/out/gail/expA/loc_r0t0/policy_seed3_tseed0_comparison.pkl differ diff --git a/out/gail/expA/loc_r0t0/policy_seed3_tseed0_summary.pkl b/out/gail/expA/loc_r0t0/policy_seed3_tseed0_summary.pkl index 899041d..727ab01 100644 Binary files a/out/gail/expA/loc_r0t0/policy_seed3_tseed0_summary.pkl and b/out/gail/expA/loc_r0t0/policy_seed3_tseed0_summary.pkl differ diff --git a/out/gail/expA/loc_r0t0/policy_seed4_tseed0_comparison.pkl b/out/gail/expA/loc_r0t0/policy_seed4_tseed0_comparison.pkl index 77f1b42..71956a8 100644 Binary files a/out/gail/expA/loc_r0t0/policy_seed4_tseed0_comparison.pkl and b/out/gail/expA/loc_r0t0/policy_seed4_tseed0_comparison.pkl differ diff --git a/out/gail/expA/loc_r0t0/policy_seed4_tseed0_summary.pkl b/out/gail/expA/loc_r0t0/policy_seed4_tseed0_summary.pkl index fc71fc9..9807193 100644 Binary files a/out/gail/expA/loc_r0t0/policy_seed4_tseed0_summary.pkl and b/out/gail/expA/loc_r0t0/policy_seed4_tseed0_summary.pkl differ diff --git a/out/gail/expA/loc_r0t0/policy_seed5_tseed0_comparison.pkl b/out/gail/expA/loc_r0t0/policy_seed5_tseed0_comparison.pkl index 8ac190a..023a738 100644 Binary files a/out/gail/expA/loc_r0t0/policy_seed5_tseed0_comparison.pkl and b/out/gail/expA/loc_r0t0/policy_seed5_tseed0_comparison.pkl differ diff --git a/out/gail/expA/loc_r0t0/policy_seed5_tseed0_summary.pkl b/out/gail/expA/loc_r0t0/policy_seed5_tseed0_summary.pkl index e21d0ae..da38427 100644 Binary files a/out/gail/expA/loc_r0t0/policy_seed5_tseed0_summary.pkl and b/out/gail/expA/loc_r0t0/policy_seed5_tseed0_summary.pkl differ diff --git a/out/gail/expB/loc_r0t4/policy_seed1_tseed0_comparison.pkl b/out/gail/expB/loc_r0t4/policy_seed1_tseed0_comparison.pkl index 038fa25..01c1e67 100644 Binary files a/out/gail/expB/loc_r0t4/policy_seed1_tseed0_comparison.pkl and b/out/gail/expB/loc_r0t4/policy_seed1_tseed0_comparison.pkl differ diff --git a/out/gail/expB/loc_r0t4/policy_seed1_tseed0_summary.pkl b/out/gail/expB/loc_r0t4/policy_seed1_tseed0_summary.pkl index 333c65b..908dbd6 100644 Binary files a/out/gail/expB/loc_r0t4/policy_seed1_tseed0_summary.pkl and b/out/gail/expB/loc_r0t4/policy_seed1_tseed0_summary.pkl differ diff --git a/out/gail/expB/loc_r0t4/policy_seed2_tseed0_comparison.pkl b/out/gail/expB/loc_r0t4/policy_seed2_tseed0_comparison.pkl index e5a394a..6871842 100644 Binary files a/out/gail/expB/loc_r0t4/policy_seed2_tseed0_comparison.pkl and b/out/gail/expB/loc_r0t4/policy_seed2_tseed0_comparison.pkl differ diff --git a/out/gail/expB/loc_r0t4/policy_seed2_tseed0_summary.pkl b/out/gail/expB/loc_r0t4/policy_seed2_tseed0_summary.pkl index a7f1fad..164b855 100644 Binary files a/out/gail/expB/loc_r0t4/policy_seed2_tseed0_summary.pkl and b/out/gail/expB/loc_r0t4/policy_seed2_tseed0_summary.pkl differ diff --git a/out/gail/expB/loc_r0t4/policy_seed3_tseed0_comparison.pkl b/out/gail/expB/loc_r0t4/policy_seed3_tseed0_comparison.pkl index 8fe2118..33ce257 100644 Binary files a/out/gail/expB/loc_r0t4/policy_seed3_tseed0_comparison.pkl and b/out/gail/expB/loc_r0t4/policy_seed3_tseed0_comparison.pkl differ diff --git a/out/gail/expB/loc_r0t4/policy_seed3_tseed0_summary.pkl b/out/gail/expB/loc_r0t4/policy_seed3_tseed0_summary.pkl index b0aa8bb..c97c831 100644 Binary files a/out/gail/expB/loc_r0t4/policy_seed3_tseed0_summary.pkl and b/out/gail/expB/loc_r0t4/policy_seed3_tseed0_summary.pkl differ diff --git a/out/gail/expB/loc_r0t4/policy_seed4_tseed0_comparison.pkl b/out/gail/expB/loc_r0t4/policy_seed4_tseed0_comparison.pkl index 68d863b..af5badf 100644 Binary files a/out/gail/expB/loc_r0t4/policy_seed4_tseed0_comparison.pkl and b/out/gail/expB/loc_r0t4/policy_seed4_tseed0_comparison.pkl differ diff --git a/out/gail/expB/loc_r0t4/policy_seed4_tseed0_summary.pkl b/out/gail/expB/loc_r0t4/policy_seed4_tseed0_summary.pkl index 95c2cf3..b309989 100644 Binary files a/out/gail/expB/loc_r0t4/policy_seed4_tseed0_summary.pkl and b/out/gail/expB/loc_r0t4/policy_seed4_tseed0_summary.pkl differ diff --git a/out/gail/expB/loc_r0t4/policy_seed5_tseed0_comparison.pkl b/out/gail/expB/loc_r0t4/policy_seed5_tseed0_comparison.pkl index ec42132..fce6b7f 100644 Binary files a/out/gail/expB/loc_r0t4/policy_seed5_tseed0_comparison.pkl and b/out/gail/expB/loc_r0t4/policy_seed5_tseed0_comparison.pkl differ diff --git a/out/gail/expB/loc_r0t4/policy_seed5_tseed0_summary.pkl b/out/gail/expB/loc_r0t4/policy_seed5_tseed0_summary.pkl index bf3855f..17efe68 100644 Binary files a/out/gail/expB/loc_r0t4/policy_seed5_tseed0_summary.pkl and b/out/gail/expB/loc_r0t4/policy_seed5_tseed0_summary.pkl differ diff --git a/out/idm/loc_r0t0/idm_tseed0_comparison.pkl b/out/idm/loc_r0t0/idm_tseed0_comparison.pkl index 0effd17..972d918 100644 Binary files a/out/idm/loc_r0t0/idm_tseed0_comparison.pkl and b/out/idm/loc_r0t0/idm_tseed0_comparison.pkl differ diff --git a/out/idm/loc_r0t0/idm_tseed0_summary.pkl b/out/idm/loc_r0t0/idm_tseed0_summary.pkl index bc1a4ca..d8496af 100644 Binary files a/out/idm/loc_r0t0/idm_tseed0_summary.pkl and b/out/idm/loc_r0t0/idm_tseed0_summary.pkl differ diff --git a/out/idm/loc_r0t4/idm_tseed0_comparison.pkl b/out/idm/loc_r0t4/idm_tseed0_comparison.pkl index 326c5f8..8548abc 100644 Binary files a/out/idm/loc_r0t4/idm_tseed0_comparison.pkl and b/out/idm/loc_r0t4/idm_tseed0_comparison.pkl differ diff --git a/out/idm/loc_r0t4/idm_tseed0_summary.pkl b/out/idm/loc_r0t4/idm_tseed0_summary.pkl index b168a09..5a0511f 100644 Binary files a/out/idm/loc_r0t4/idm_tseed0_summary.pkl and b/out/idm/loc_r0t4/idm_tseed0_summary.pkl differ diff --git a/out/shail/expA/loc_r0t0/policy_seed1_tseed0_comparison.pkl b/out/shail/expA/loc_r0t0/policy_seed1_tseed0_comparison.pkl index 7736e14..bcda5b9 100644 Binary files a/out/shail/expA/loc_r0t0/policy_seed1_tseed0_comparison.pkl and b/out/shail/expA/loc_r0t0/policy_seed1_tseed0_comparison.pkl differ diff --git a/out/shail/expA/loc_r0t0/policy_seed1_tseed0_summary.pkl b/out/shail/expA/loc_r0t0/policy_seed1_tseed0_summary.pkl index c04c9a5..855e8d2 100644 Binary files a/out/shail/expA/loc_r0t0/policy_seed1_tseed0_summary.pkl and b/out/shail/expA/loc_r0t0/policy_seed1_tseed0_summary.pkl differ diff --git a/out/shail/expA/loc_r0t0/policy_seed2_tseed0_comparison.pkl b/out/shail/expA/loc_r0t0/policy_seed2_tseed0_comparison.pkl index 0636b7d..4a1f097 100644 Binary files a/out/shail/expA/loc_r0t0/policy_seed2_tseed0_comparison.pkl and b/out/shail/expA/loc_r0t0/policy_seed2_tseed0_comparison.pkl differ diff --git a/out/shail/expA/loc_r0t0/policy_seed2_tseed0_summary.pkl b/out/shail/expA/loc_r0t0/policy_seed2_tseed0_summary.pkl index 3bb3150..7e6426d 100644 Binary files a/out/shail/expA/loc_r0t0/policy_seed2_tseed0_summary.pkl and b/out/shail/expA/loc_r0t0/policy_seed2_tseed0_summary.pkl differ diff --git a/out/shail/expA/loc_r0t0/policy_seed3_tseed0_comparison.pkl b/out/shail/expA/loc_r0t0/policy_seed3_tseed0_comparison.pkl index f6df78b..1875021 100644 Binary files a/out/shail/expA/loc_r0t0/policy_seed3_tseed0_comparison.pkl and b/out/shail/expA/loc_r0t0/policy_seed3_tseed0_comparison.pkl differ diff --git a/out/shail/expA/loc_r0t0/policy_seed3_tseed0_summary.pkl b/out/shail/expA/loc_r0t0/policy_seed3_tseed0_summary.pkl index 7cfb733..32e6928 100644 Binary files a/out/shail/expA/loc_r0t0/policy_seed3_tseed0_summary.pkl and b/out/shail/expA/loc_r0t0/policy_seed3_tseed0_summary.pkl differ diff --git a/out/shail/expA/loc_r0t0/policy_seed4_tseed0_comparison.pkl b/out/shail/expA/loc_r0t0/policy_seed4_tseed0_comparison.pkl index eff3628..c169389 100644 Binary files a/out/shail/expA/loc_r0t0/policy_seed4_tseed0_comparison.pkl and b/out/shail/expA/loc_r0t0/policy_seed4_tseed0_comparison.pkl differ diff --git a/out/shail/expA/loc_r0t0/policy_seed4_tseed0_summary.pkl b/out/shail/expA/loc_r0t0/policy_seed4_tseed0_summary.pkl index 226c774..ef10af4 100644 Binary files a/out/shail/expA/loc_r0t0/policy_seed4_tseed0_summary.pkl and b/out/shail/expA/loc_r0t0/policy_seed4_tseed0_summary.pkl differ diff --git a/out/shail/expA/loc_r0t0/policy_seed5_tseed0_comparison.pkl b/out/shail/expA/loc_r0t0/policy_seed5_tseed0_comparison.pkl index d1444dd..73cb398 100644 Binary files a/out/shail/expA/loc_r0t0/policy_seed5_tseed0_comparison.pkl and b/out/shail/expA/loc_r0t0/policy_seed5_tseed0_comparison.pkl differ diff --git a/out/shail/expA/loc_r0t0/policy_seed5_tseed0_summary.pkl b/out/shail/expA/loc_r0t0/policy_seed5_tseed0_summary.pkl index 07dbcde..623fcc8 100644 Binary files a/out/shail/expA/loc_r0t0/policy_seed5_tseed0_summary.pkl and b/out/shail/expA/loc_r0t0/policy_seed5_tseed0_summary.pkl differ diff --git a/out/shail/expB/loc_r0t4/policy_seed1_tseed0_comparison.pkl b/out/shail/expB/loc_r0t4/policy_seed1_tseed0_comparison.pkl index b59930a..91d0614 100644 Binary files a/out/shail/expB/loc_r0t4/policy_seed1_tseed0_comparison.pkl and b/out/shail/expB/loc_r0t4/policy_seed1_tseed0_comparison.pkl differ diff --git a/out/shail/expB/loc_r0t4/policy_seed1_tseed0_summary.pkl b/out/shail/expB/loc_r0t4/policy_seed1_tseed0_summary.pkl index f0af2f3..632d7f7 100644 Binary files a/out/shail/expB/loc_r0t4/policy_seed1_tseed0_summary.pkl and b/out/shail/expB/loc_r0t4/policy_seed1_tseed0_summary.pkl differ diff --git a/out/shail/expB/loc_r0t4/policy_seed2_tseed0_comparison.pkl b/out/shail/expB/loc_r0t4/policy_seed2_tseed0_comparison.pkl index 814cde4..4a7f99d 100644 Binary files a/out/shail/expB/loc_r0t4/policy_seed2_tseed0_comparison.pkl and b/out/shail/expB/loc_r0t4/policy_seed2_tseed0_comparison.pkl differ diff --git a/out/shail/expB/loc_r0t4/policy_seed2_tseed0_summary.pkl b/out/shail/expB/loc_r0t4/policy_seed2_tseed0_summary.pkl index 71c675f..494aec0 100644 Binary files a/out/shail/expB/loc_r0t4/policy_seed2_tseed0_summary.pkl and b/out/shail/expB/loc_r0t4/policy_seed2_tseed0_summary.pkl differ diff --git a/out/shail/expB/loc_r0t4/policy_seed3_tseed0_comparison.pkl b/out/shail/expB/loc_r0t4/policy_seed3_tseed0_comparison.pkl index c14eed7..ac29c3b 100644 Binary files a/out/shail/expB/loc_r0t4/policy_seed3_tseed0_comparison.pkl and b/out/shail/expB/loc_r0t4/policy_seed3_tseed0_comparison.pkl differ diff --git a/out/shail/expB/loc_r0t4/policy_seed3_tseed0_summary.pkl b/out/shail/expB/loc_r0t4/policy_seed3_tseed0_summary.pkl index f72e631..a7f9226 100644 Binary files a/out/shail/expB/loc_r0t4/policy_seed3_tseed0_summary.pkl and b/out/shail/expB/loc_r0t4/policy_seed3_tseed0_summary.pkl differ diff --git a/out/shail/expB/loc_r0t4/policy_seed4_tseed0_comparison.pkl b/out/shail/expB/loc_r0t4/policy_seed4_tseed0_comparison.pkl index c4aa52f..0fc17b6 100644 Binary files a/out/shail/expB/loc_r0t4/policy_seed4_tseed0_comparison.pkl and b/out/shail/expB/loc_r0t4/policy_seed4_tseed0_comparison.pkl differ diff --git a/out/shail/expB/loc_r0t4/policy_seed4_tseed0_summary.pkl b/out/shail/expB/loc_r0t4/policy_seed4_tseed0_summary.pkl index 54a14a4..5ba57e1 100644 Binary files a/out/shail/expB/loc_r0t4/policy_seed4_tseed0_summary.pkl and b/out/shail/expB/loc_r0t4/policy_seed4_tseed0_summary.pkl differ diff --git a/out/shail/expB/loc_r0t4/policy_seed5_tseed0_comparison.pkl b/out/shail/expB/loc_r0t4/policy_seed5_tseed0_comparison.pkl index cb94ee6..3763165 100644 Binary files a/out/shail/expB/loc_r0t4/policy_seed5_tseed0_comparison.pkl and b/out/shail/expB/loc_r0t4/policy_seed5_tseed0_comparison.pkl differ diff --git a/out/shail/expB/loc_r0t4/policy_seed5_tseed0_summary.pkl b/out/shail/expB/loc_r0t4/policy_seed5_tseed0_summary.pkl index 16a6a87..addec93 100644 Binary files a/out/shail/expB/loc_r0t4/policy_seed5_tseed0_summary.pkl and b/out/shail/expB/loc_r0t4/policy_seed5_tseed0_summary.pkl differ diff --git a/test_policies/gail/expA/config.json b/test_policies/gail/expA/config.json index 7ee8f8d..e254f61 100644 --- a/test_policies/gail/expA/config.json +++ b/test_policies/gail/expA/config.json @@ -1,32 +1,31 @@ { - "discriminator": { - "activation": 0, - "hidden_layer_size": 10, - "iterations_per_epoch": 100, - "learning_rate": 0.001, - "n_hidden_layers_element": 4, - "n_hidden_layers_global": 1, - "weight_decay": 0.0001 - }, - "experiment": "A", - "policy": { - "activation": 0, - "clip_ratio": 0.2, - "hidden_layer_size": 40, - "iterations_per_epoch": 100, - "learning_rate": 0.0003, - "learning_rate_decay": 1.0, - "n_hidden_layers": 2 - }, - "seed": 5, - "train_epochs": 100, - "trainenv": { - "stop_on_collision": false, - "use_idm": true - }, - "value": { - "iterations_per_epoch": 1000, - "learning_rate": 0.0001, - "weight_decay": 0.001 - } + "experiment": "A", + "trainenv": { + "stop_on_collision": false + }, + "policy": { + "learning_rate": 0.0003, + "learning_rate_decay": 1.0, + "clip_ratio": 0.2, + "iterations_per_epoch": 100, + "hidden_layer_size": 40, + "n_hidden_layers": 2, + "activation": 0 + }, + "value": { + "learning_rate": 0.0001, + "weight_decay": 0.001, + "iterations_per_epoch": 1000 + }, + "discriminator": { + "learning_rate": 0.001, + "weight_decay": 0.0001, + "iterations_per_epoch": 100, + "n_hidden_layers_element": 4, + "n_hidden_layers_global": 1, + "hidden_layer_size": 10, + "activation": 0 + }, + "train_epochs": 100, + "seed": 0 } \ No newline at end of file diff --git a/test_policies/gail/expA/policy_seed1.pt b/test_policies/gail/expA/policy_seed1.pt index af72d7e..0530c10 100644 Binary files a/test_policies/gail/expA/policy_seed1.pt and b/test_policies/gail/expA/policy_seed1.pt differ diff --git a/test_policies/gail/expA/policy_seed2.pt b/test_policies/gail/expA/policy_seed2.pt index ade886d..9d85579 100644 Binary files a/test_policies/gail/expA/policy_seed2.pt and b/test_policies/gail/expA/policy_seed2.pt differ diff --git a/test_policies/gail/expA/policy_seed3.pt b/test_policies/gail/expA/policy_seed3.pt index 06332e1..6d48834 100644 Binary files a/test_policies/gail/expA/policy_seed3.pt and b/test_policies/gail/expA/policy_seed3.pt differ diff --git a/test_policies/gail/expA/policy_seed4.pt b/test_policies/gail/expA/policy_seed4.pt index c02da5d..709f468 100644 Binary files a/test_policies/gail/expA/policy_seed4.pt and b/test_policies/gail/expA/policy_seed4.pt differ diff --git a/test_policies/gail/expA/policy_seed5.pt b/test_policies/gail/expA/policy_seed5.pt index ba1a512..a524ac9 100644 Binary files a/test_policies/gail/expA/policy_seed5.pt and b/test_policies/gail/expA/policy_seed5.pt differ diff --git a/test_policies/gail/expB/config.json b/test_policies/gail/expB/config.json index 05b0f4a..b05e446 100644 --- a/test_policies/gail/expB/config.json +++ b/test_policies/gail/expB/config.json @@ -1,32 +1,31 @@ { - "discriminator": { - "activation": 0, - "hidden_layer_size": 10, - "iterations_per_epoch": 100, - "learning_rate": 0.001, - "n_hidden_layers_element": 4, - "n_hidden_layers_global": 1, - "weight_decay": 0.0001 - }, - "experiment": "B", - "policy": { - "activation": 0, - "clip_ratio": 0.2, - "hidden_layer_size": 40, - "iterations_per_epoch": 100, - "learning_rate": 0.0003, - "learning_rate_decay": 1.0, - "n_hidden_layers": 2 - }, - "seed": 4, - "train_epochs": 100, - "trainenv": { - "stop_on_collision": false, - "use_idm": true - }, - "value": { - "iterations_per_epoch": 1000, - "learning_rate": 0.0001, - "weight_decay": 0.001 - } + "experiment": "B", + "trainenv": { + "stop_on_collision": false + }, + "policy": { + "learning_rate": 0.0003, + "learning_rate_decay": 1.0, + "clip_ratio": 0.2, + "iterations_per_epoch": 100, + "hidden_layer_size": 40, + "n_hidden_layers": 2, + "activation": 0 + }, + "value": { + "learning_rate": 0.0001, + "weight_decay": 0.001, + "iterations_per_epoch": 1000 + }, + "discriminator": { + "learning_rate": 0.001, + "weight_decay": 0.0001, + "iterations_per_epoch": 100, + "n_hidden_layers_element": 4, + "n_hidden_layers_global": 1, + "hidden_layer_size": 10, + "activation": 0 + }, + "train_epochs": 100, + "seed": 0 } \ No newline at end of file diff --git a/test_policies/gail/expB/policy_seed1.pt b/test_policies/gail/expB/policy_seed1.pt index 369fd74..a97af9c 100644 Binary files a/test_policies/gail/expB/policy_seed1.pt and b/test_policies/gail/expB/policy_seed1.pt differ diff --git a/test_policies/gail/expB/policy_seed2.pt b/test_policies/gail/expB/policy_seed2.pt index f0e3ad6..62b1490 100644 Binary files a/test_policies/gail/expB/policy_seed2.pt and b/test_policies/gail/expB/policy_seed2.pt differ diff --git a/test_policies/gail/expB/policy_seed3.pt b/test_policies/gail/expB/policy_seed3.pt index 97606cb..4291a26 100644 Binary files a/test_policies/gail/expB/policy_seed3.pt and b/test_policies/gail/expB/policy_seed3.pt differ diff --git a/test_policies/gail/expB/policy_seed4.pt b/test_policies/gail/expB/policy_seed4.pt index e016c5b..a8b9423 100644 Binary files a/test_policies/gail/expB/policy_seed4.pt and b/test_policies/gail/expB/policy_seed4.pt differ diff --git a/test_policies/gail/expB/policy_seed5.pt b/test_policies/gail/expB/policy_seed5.pt index 38dd9c8..c9fe325 100644 Binary files a/test_policies/gail/expB/policy_seed5.pt and b/test_policies/gail/expB/policy_seed5.pt differ diff --git a/test_policies/shail/expA/config.json b/test_policies/shail/expA/config.json index b6814f2..76472e0 100644 --- a/test_policies/shail/expA/config.json +++ b/test_policies/shail/expA/config.json @@ -1,34 +1,33 @@ { - "discriminator": { - "activation": 0, - "hidden_layer_size": 10, - "iterations_per_epoch": 100, - "learning_rate": 0.001, - "n_hidden_layers_element": 4, - "n_hidden_layers_global": 1, - "weight_decay": 0.0001 - }, - "experiment": "A", - "policy": { - "activation": 0, - "clip_ratio": 0.2, - "hidden_layer_size": 40, - "iterations_per_epoch": 100, - "learning_rate": 0.0003, - "learning_rate_decay": 1.0, - "n_hidden_layers": 2, - "option": 0 - }, - "seed": 3, - "train_epochs": 90, - "trainenv": { - "abort_unsafe_collision_method": "circle", - "safe_actions_collision_method": "circle", - "stop_on_collision": false, - "use_idm": true - }, - "value": { - "iterations_per_epoch": 1000, - "learning_rate": 0.001 - } + "experiment": "A", + "trainenv": { + "stop_on_collision": false, + "safe_actions_collision_method": "circle", + "abort_unsafe_collision_method": "circle" + }, + "policy": { + "learning_rate": 0.0003, + "learning_rate_decay": 1.0, + "clip_ratio": 0.2, + "iterations_per_epoch": 100, + "hidden_layer_size": 40, + "n_hidden_layers": 2, + "activation": 0, + "option": 0 + }, + "value": { + "learning_rate": 0.001, + "iterations_per_epoch": 1000 + }, + "discriminator": { + "learning_rate": 0.001, + "weight_decay": 0.0001, + "iterations_per_epoch": 100, + "n_hidden_layers_element": 4, + "n_hidden_layers_global": 1, + "hidden_layer_size": 10, + "activation": 0 + }, + "train_epochs": 90, + "seed": 0 } \ No newline at end of file diff --git a/test_policies/shail/expA/policy_seed1.pt b/test_policies/shail/expA/policy_seed1.pt index 0adc3bf..3819718 100644 Binary files a/test_policies/shail/expA/policy_seed1.pt and b/test_policies/shail/expA/policy_seed1.pt differ diff --git a/test_policies/shail/expA/policy_seed2.pt b/test_policies/shail/expA/policy_seed2.pt index 9c5e335..52753fd 100644 Binary files a/test_policies/shail/expA/policy_seed2.pt and b/test_policies/shail/expA/policy_seed2.pt differ diff --git a/test_policies/shail/expA/policy_seed3.pt b/test_policies/shail/expA/policy_seed3.pt index 781fa4d..15a6c1d 100644 Binary files a/test_policies/shail/expA/policy_seed3.pt and b/test_policies/shail/expA/policy_seed3.pt differ diff --git a/test_policies/shail/expA/policy_seed4.pt b/test_policies/shail/expA/policy_seed4.pt index 0168852..98cc3e7 100644 Binary files a/test_policies/shail/expA/policy_seed4.pt and b/test_policies/shail/expA/policy_seed4.pt differ diff --git a/test_policies/shail/expA/policy_seed5.pt b/test_policies/shail/expA/policy_seed5.pt index d43c6a0..f3e3bff 100644 Binary files a/test_policies/shail/expA/policy_seed5.pt and b/test_policies/shail/expA/policy_seed5.pt differ diff --git a/test_policies/shail/expB/config.json b/test_policies/shail/expB/config.json index 6c3b641..3a35200 100644 --- a/test_policies/shail/expB/config.json +++ b/test_policies/shail/expB/config.json @@ -1,34 +1,33 @@ { - "discriminator": { - "activation": 0, - "hidden_layer_size": 10, - "iterations_per_epoch": 100, - "learning_rate": 0.001, - "n_hidden_layers_element": 4, - "n_hidden_layers_global": 2, - "weight_decay": 0.0001 - }, - "experiment": "B", - "policy": { - "activation": 0, - "clip_ratio": 0.2, - "hidden_layer_size": 20, - "iterations_per_epoch": 100, - "learning_rate": 0.0003, - "learning_rate_decay": 1.0, - "n_hidden_layers": 2, - "option": 0 - }, - "seed": 3, - "train_epochs": 85, - "trainenv": { - "abort_unsafe_collision_method": "circle", - "safe_actions_collision_method": "circle", - "stop_on_collision": false, - "use_idm": true - }, - "value": { - "iterations_per_epoch": 1000, - "learning_rate": 0.001 - } + "experiment": "B", + "trainenv": { + "stop_on_collision": false, + "safe_actions_collision_method": "circle", + "abort_unsafe_collision_method": "circle" + }, + "policy": { + "learning_rate": 0.0003, + "learning_rate_decay": 1.0, + "clip_ratio": 0.2, + "iterations_per_epoch": 100, + "hidden_layer_size": 20, + "n_hidden_layers": 2, + "activation": 0, + "option": 0 + }, + "value": { + "learning_rate": 0.001, + "iterations_per_epoch": 1000 + }, + "discriminator": { + "learning_rate": 0.001, + "weight_decay": 0.0001, + "iterations_per_epoch": 100, + "n_hidden_layers_element": 4, + "n_hidden_layers_global": 2, + "hidden_layer_size": 10, + "activation": 0 + }, + "train_epochs": 85, + "seed": 0 } \ No newline at end of file diff --git a/test_policies/shail/expB/policy_seed1.pt b/test_policies/shail/expB/policy_seed1.pt index 1e35f3c..e5a93dc 100644 Binary files a/test_policies/shail/expB/policy_seed1.pt and b/test_policies/shail/expB/policy_seed1.pt differ diff --git a/test_policies/shail/expB/policy_seed2.pt b/test_policies/shail/expB/policy_seed2.pt index d6c7217..c1ce024 100644 Binary files a/test_policies/shail/expB/policy_seed2.pt and b/test_policies/shail/expB/policy_seed2.pt differ diff --git a/test_policies/shail/expB/policy_seed3.pt b/test_policies/shail/expB/policy_seed3.pt index 36cd43b..ad03c95 100644 Binary files a/test_policies/shail/expB/policy_seed3.pt and b/test_policies/shail/expB/policy_seed3.pt differ diff --git a/test_policies/shail/expB/policy_seed4.pt b/test_policies/shail/expB/policy_seed4.pt index c13b265..3c309da 100644 Binary files a/test_policies/shail/expB/policy_seed4.pt and b/test_policies/shail/expB/policy_seed4.pt differ diff --git a/test_policies/shail/expB/policy_seed5.pt b/test_policies/shail/expB/policy_seed5.pt index 8dcaf98..7600e77 100644 Binary files a/test_policies/shail/expB/policy_seed5.pt and b/test_policies/shail/expB/policy_seed5.pt differ