{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 1.0930838584899902, "min": 1.0794390439987183, "max": 2.8600387573242188, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 10436.7646484375, "min": 10436.7646484375, "max": 29321.1171875, "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": 11.253480911254883, "min": 0.4318237602710724, "max": 11.253480911254883, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2194.4287109375, "min": 83.77381134033203, "max": 2245.712890625, "count": 20 }, "SnowballTarget.Environment.EpisodeLength.mean": { "value": 199.0, "min": 199.0, "max": 199.0, "count": 20 }, "SnowballTarget.Environment.EpisodeLength.sum": { "value": 8756.0, "min": 8756.0, "max": 10945.0, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.07199650896134199, "min": 0.06265978160235511, "max": 0.07979974280221058, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.28798603584536797, "min": 0.2510336281642701, "max": 0.3989987140110529, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.20088188835949292, "min": 0.13821507838335545, "max": 0.2686585400034399, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.8035275534379717, "min": 0.5528603135334218, "max": 1.3432927000171997, "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": 22.045454545454547, "min": 3.772727272727273, "max": 22.272727272727273, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 970.0, "min": 166.0, "max": 1225.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 22.045454545454547, "min": 3.772727272727273, "max": 22.272727272727273, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 970.0, "min": 166.0, "max": 1225.0, "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": "1687835143", "python_version": "3.10.12 (main, Jun 7 2023, 12:45:35) [GCC 9.4.0]", "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": "0.31.0.dev0", "mlagents_envs_version": "0.31.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.11.0+cu102", "numpy_version": "1.21.2", "end_time_seconds": "1687835594" }, "total": 451.41695249200006, "count": 1, "self": 0.8047378260000642, "children": { "run_training.setup": { "total": 0.041685296999958155, "count": 1, "self": 0.041685296999958155 }, "TrainerController.start_learning": { "total": 450.57052936900004, "count": 1, "self": 0.5195777809896072, "children": { "TrainerController._reset_env": { "total": 4.122380730000032, "count": 1, "self": 4.122380730000032 }, "TrainerController.advance": { "total": 445.72684177501026, "count": 18217, "self": 0.2602205130178845, "children": { "env_step": { "total": 445.4666212619924, "count": 18217, "self": 323.61068736599714, "children": { "SubprocessEnvManager._take_step": { "total": 121.6119492849989, "count": 18217, "self": 1.6459419490016671, "children": { "TorchPolicy.evaluate": { "total": 119.96600733599723, "count": 18217, "self": 119.96600733599723 } } }, "workers": { "total": 0.2439846109963355, "count": 18217, "self": 0.0, "children": { "worker_root": { "total": 449.11133096600724, "count": 18217, "is_parallel": true, "self": 211.78620228801037, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005382672999985516, "count": 1, "is_parallel": true, "self": 0.00390066999989358, "children": { "_process_rank_one_or_two_observation": { "total": 0.001482003000091936, "count": 10, "is_parallel": true, "self": 0.001482003000091936 } } }, "UnityEnvironment.step": { "total": 0.04685991299993475, "count": 1, "is_parallel": true, "self": 0.0005801380000320933, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00042017399994165316, "count": 1, "is_parallel": true, "self": 0.00042017399994165316 }, "communicator.exchange": { "total": 0.043829381000023204, "count": 1, "is_parallel": true, "self": 0.043829381000023204 }, "steps_from_proto": { "total": 0.002030219999937799, "count": 1, "is_parallel": true, "self": 0.0003606670001090606, "children": { "_process_rank_one_or_two_observation": { "total": 0.0016695529998287384, "count": 10, "is_parallel": true, "self": 0.0016695529998287384 } } } } } } }, "UnityEnvironment.step": { "total": 237.32512867799687, "count": 18216, "is_parallel": true, "self": 9.929257630981624, "children": { "UnityEnvironment._generate_step_input": { "total": 5.07307375799769, "count": 18216, "is_parallel": true, "self": 5.07307375799769 }, "communicator.exchange": { "total": 189.15610813401076, "count": 18216, "is_parallel": true, "self": 189.15610813401076 }, "steps_from_proto": { "total": 33.16668915500679, "count": 18216, "is_parallel": true, "self": 5.952032423013748, "children": { "_process_rank_one_or_two_observation": { "total": 27.214656731993045, "count": 182160, "is_parallel": true, "self": 27.214656731993045 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.0001230380000833975, "count": 1, "self": 0.0001230380000833975, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 442.36113467503174, "count": 423772, "is_parallel": true, "self": 9.328584668017697, "children": { "process_trajectory": { "total": 242.23922988701327, "count": 423772, "is_parallel": true, "self": 240.71238035101317, "children": { "RLTrainer._checkpoint": { "total": 1.5268495360000998, "count": 4, "is_parallel": true, "self": 1.5268495360000998 } } }, "_update_policy": { "total": 190.79332012000077, "count": 90, "is_parallel": true, "self": 74.03909111200915, "children": { "TorchPPOOptimizer.update": { "total": 116.75422900799163, "count": 4584, "is_parallel": true, "self": 116.75422900799163 } } } } } } } } }, "TrainerController._save_models": { "total": 0.2016060450000623, "count": 1, "self": 0.0015166079999744397, "children": { "RLTrainer._checkpoint": { "total": 0.20008943700008786, "count": 1, "self": 0.20008943700008786 } } } } } } }