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 97a3947..29bedc8 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 5ed53a8..ecec438 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 54ef594..c753646 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 9587401..5ebcb8b 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 f0bbd04..18d1dbb 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 727ab01..899041d 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 71956a8..77f1b42 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 9807193..fc71fc9 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 023a738..8ac190a 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 da38427..e21d0ae 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 01c1e67..038fa25 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 908dbd6..333c65b 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 6871842..e5a394a 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 164b855..a7f1fad 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 33ce257..8fe2118 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 c97c831..b0aa8bb 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 af5badf..68d863b 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 b309989..95c2cf3 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 fce6b7f..ec42132 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 17efe68..bf3855f 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 972d918..0effd17 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 d8496af..bc1a4ca 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 8548abc..326c5f8 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 5a0511f..b168a09 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 bcda5b9..7736e14 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 855e8d2..c04c9a5 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 4a1f097..0636b7d 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 7e6426d..3bb3150 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 1875021..f6df78b 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 32e6928..7cfb733 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 c169389..eff3628 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 ef10af4..226c774 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 73cb398..d1444dd 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 623fcc8..07dbcde 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 91d0614..b59930a 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 632d7f7..f0af2f3 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 4a7f99d..814cde4 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 494aec0..71c675f 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 ac29c3b..c14eed7 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 a7f9226..f72e631 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 0fc17b6..c4aa52f 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 5ba57e1..54a14a4 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 3763165..cb94ee6 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 addec93..16a6a87 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 e254f61..7ee8f8d 100644 --- a/test_policies/gail/expA/config.json +++ b/test_policies/gail/expA/config.json @@ -1,31 +1,32 @@ { - "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 + "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 + } } \ 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 0530c10..af72d7e 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 9d85579..ade886d 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 6d48834..06332e1 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 709f468..c02da5d 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 a524ac9..ba1a512 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 b05e446..05b0f4a 100644 --- a/test_policies/gail/expB/config.json +++ b/test_policies/gail/expB/config.json @@ -1,31 +1,32 @@ { - "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 + "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 + } } \ 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 a97af9c..369fd74 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 62b1490..f0e3ad6 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 4291a26..97606cb 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 a8b9423..e016c5b 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 c9fe325..38dd9c8 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 76472e0..b6814f2 100644 --- a/test_policies/shail/expA/config.json +++ b/test_policies/shail/expA/config.json @@ -1,33 +1,34 @@ { - "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 + "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 + } } \ 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 3819718..0adc3bf 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 52753fd..9c5e335 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 15a6c1d..781fa4d 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 98cc3e7..0168852 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 f3e3bff..d43c6a0 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 3a35200..6c3b641 100644 --- a/test_policies/shail/expB/config.json +++ b/test_policies/shail/expB/config.json @@ -1,33 +1,34 @@ { - "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 + "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 + } } \ 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 e5a93dc..1e35f3c 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 c1ce024..d6c7217 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 ad03c95..36cd43b 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 3c309da..c13b265 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 7600e77..8dcaf98 100644 Binary files a/test_policies/shail/expB/policy_seed5.pt and b/test_policies/shail/expB/policy_seed5.pt differ