{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 1.0184093713760376, "min": 1.0184093713760376, "max": 2.864177942276001, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 9779.78515625, "min": 9779.78515625, "max": 29332.046875, "count": 20 }, "SnowballTarget.Step.mean": { "value": 199984.0, "min": 9952.0, "max": 199984.0, "count": 20 }, "SnowballTarget.Step.sum": { "value": 199984.0, "min": 9952.0, "max": 199984.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": { "value": 12.69029426574707, "min": 0.4401818811893463, "max": 12.69029426574707, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2474.607421875, "min": 85.3952865600586, "max": 2562.44287109375, "count": 20 }, "SnowballTarget.Environment.EpisodeLength.mean": { "value": 199.0, "min": 199.0, "max": 199.0, "count": 20 }, "SnowballTarget.Environment.EpisodeLength.sum": { "value": 10945.0, "min": 8756.0, "max": 10945.0, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.06714481875093826, "min": 0.06391084169245362, "max": 0.07324904690692932, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.26857927500375306, "min": 0.25601766722712793, "max": 0.3662452345346466, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.1870088366170724, "min": 0.10832047196305997, "max": 0.28163755851633404, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.7480353464682896, "min": 0.43328188785223987, "max": 1.4081877925816702, "count": 20 }, "SnowballTarget.Policy.LearningRate.mean": { "value": 8.082097306000005e-06, "min": 8.082097306000005e-06, "max": 0.000291882002706, "count": 20 }, "SnowballTarget.Policy.LearningRate.sum": { "value": 3.232838922400002e-05, "min": 3.232838922400002e-05, "max": 0.00138516003828, "count": 20 }, "SnowballTarget.Policy.Epsilon.mean": { "value": 0.10269400000000001, "min": 0.10269400000000001, "max": 0.19729400000000002, "count": 20 }, "SnowballTarget.Policy.Epsilon.sum": { "value": 0.41077600000000003, "min": 0.41077600000000003, "max": 0.96172, "count": 20 }, "SnowballTarget.Policy.Beta.mean": { "value": 0.0001444306000000001, "min": 0.0001444306000000001, "max": 0.0048649706, "count": 20 }, "SnowballTarget.Policy.Beta.sum": { "value": 0.0005777224000000004, "min": 0.0005777224000000004, "max": 0.023089828, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.mean": { "value": 25.454545454545453, "min": 3.2045454545454546, "max": 25.454545454545453, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1120.0, "min": 141.0, "max": 1387.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.454545454545453, "min": 3.2045454545454546, "max": 25.454545454545453, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1120.0, "min": 141.0, "max": 1387.0, "count": 20 }, "SnowballTarget.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 20 }, "SnowballTarget.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 20 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1719118065", "python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [GCC 11.4.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.3.0+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1719118539" }, "total": 473.370432501, "count": 1, "self": 0.4360264949999646, "children": { "run_training.setup": { "total": 0.06218403399998351, "count": 1, "self": 0.06218403399998351 }, "TrainerController.start_learning": { "total": 472.87222197200003, "count": 1, "self": 0.6343780040152751, "children": { "TrainerController._reset_env": { "total": 2.9674806030000127, "count": 1, "self": 2.9674806030000127 }, "TrainerController.advance": { "total": 469.16877457098474, "count": 18223, "self": 0.30580697997447714, "children": { "env_step": { "total": 468.86296759101026, "count": 18223, "self": 304.2011739509966, "children": { "SubprocessEnvManager._take_step": { "total": 164.36670737400812, "count": 18223, "self": 1.5368024410257703, "children": { "TorchPolicy.evaluate": { "total": 162.82990493298234, "count": 18223, "self": 162.82990493298234 } } }, "workers": { "total": 0.2950862660055691, "count": 18223, "self": 0.0, "children": { "worker_root": { "total": 471.6213539149918, "count": 18223, "is_parallel": true, "self": 237.98914278098914, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0052971420000176295, "count": 1, "is_parallel": true, "self": 0.003711594000264995, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015855479997526345, "count": 10, "is_parallel": true, "self": 0.0015855479997526345 } } }, "UnityEnvironment.step": { "total": 0.04422669599989604, "count": 1, "is_parallel": true, "self": 0.0006925529999080027, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004135350000069593, "count": 1, "is_parallel": true, "self": 0.0004135350000069593 }, "communicator.exchange": { "total": 0.04104521800002203, "count": 1, "is_parallel": true, "self": 0.04104521800002203 }, "steps_from_proto": { "total": 0.002075389999959043, "count": 1, "is_parallel": true, "self": 0.0004011489997992612, "children": { "_process_rank_one_or_two_observation": { "total": 0.0016742410001597818, "count": 10, "is_parallel": true, "self": 0.0016742410001597818 } } } } } } }, "UnityEnvironment.step": { "total": 233.63221113400266, "count": 18222, "is_parallel": true, "self": 10.615754644000049, "children": { "UnityEnvironment._generate_step_input": { "total": 5.732393482993871, "count": 18222, "is_parallel": true, "self": 5.732393482993871 }, "communicator.exchange": { "total": 181.90929106699184, "count": 18222, "is_parallel": true, "self": 181.90929106699184 }, "steps_from_proto": { "total": 35.3747719400169, "count": 18222, "is_parallel": true, "self": 6.738404349988741, "children": { "_process_rank_one_or_two_observation": { "total": 28.636367590028158, "count": 182220, "is_parallel": true, "self": 28.636367590028158 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00015549899990219274, "count": 1, "self": 0.00015549899990219274, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 463.2478174840336, "count": 701994, "is_parallel": true, "self": 15.212879152033452, "children": { "process_trajectory": { "total": 255.55602838199843, "count": 701994, "is_parallel": true, "self": 254.15787026399835, "children": { "RLTrainer._checkpoint": { "total": 1.398158118000083, "count": 4, "is_parallel": true, "self": 1.398158118000083 } } }, "_update_policy": { "total": 192.4789099500017, "count": 90, "is_parallel": true, "self": 60.562149855010034, "children": { "TorchPPOOptimizer.update": { "total": 131.91676009499167, "count": 4587, "is_parallel": true, "self": 131.91676009499167 } } } } } } } } }, "TrainerController._save_models": { "total": 0.10143329500010623, "count": 1, "self": 0.0009372840002015437, "children": { "RLTrainer._checkpoint": { "total": 0.10049601099990468, "count": 1, "self": 0.10049601099990468 } } } } } } }