{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 2.8764760494232178, "min": 2.8764760494232178, "max": 2.8764760494232178, "count": 1 }, "SnowballTarget.Policy.Entropy.sum": { "value": 29457.9921875, "min": 29457.9921875, "max": 29457.9921875, "count": 1 }, "SnowballTarget.Step.mean": { "value": 9952.0, "min": 9952.0, "max": 9952.0, "count": 1 }, "SnowballTarget.Step.sum": { "value": 9952.0, "min": 9952.0, "max": 9952.0, "count": 1 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": { "value": 0.42714861035346985, "min": 0.42714861035346985, "max": 0.42714861035346985, "count": 1 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 82.86682891845703, "min": 82.86682891845703, "max": 82.86682891845703, "count": 1 }, "SnowballTarget.Environment.EpisodeLength.mean": { "value": 199.0, "min": 199.0, "max": 199.0, "count": 1 }, "SnowballTarget.Environment.EpisodeLength.sum": { "value": 8756.0, "min": 8756.0, "max": 8756.0, "count": 1 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.075464323256336, "min": 0.075464323256336, "max": 0.075464323256336, "count": 1 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.301857293025344, "min": 0.301857293025344, "max": 0.301857293025344, "count": 1 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.1226974766719721, "min": 0.1226974766719721, "max": 0.1226974766719721, "count": 1 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.4907899066878884, "min": 0.4907899066878884, "max": 0.4907899066878884, "count": 1 }, "SnowballTarget.Policy.LearningRate.mean": { "value": 0.00013764005412, "min": 0.00013764005412, "max": 0.00013764005412, "count": 1 }, "SnowballTarget.Policy.LearningRate.sum": { "value": 0.00055056021648, "min": 0.00055056021648, "max": 0.00055056021648, "count": 1 }, "SnowballTarget.Policy.Epsilon.mean": { "value": 0.14588, "min": 0.14588, "max": 0.14588, "count": 1 }, "SnowballTarget.Policy.Epsilon.sum": { "value": 0.58352, "min": 0.58352, "max": 0.58352, "count": 1 }, "SnowballTarget.Policy.Beta.mean": { "value": 0.002299412, "min": 0.002299412, "max": 0.002299412, "count": 1 }, "SnowballTarget.Policy.Beta.sum": { "value": 0.009197648, "min": 0.009197648, "max": 0.009197648, "count": 1 }, "SnowballTarget.Environment.CumulativeReward.mean": { "value": 3.3181818181818183, "min": 3.3181818181818183, "max": 3.3181818181818183, "count": 1 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 146.0, "min": 146.0, "max": 146.0, "count": 1 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 3.3181818181818183, "min": 3.3181818181818183, "max": 3.3181818181818183, "count": 1 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 146.0, "min": 146.0, "max": 146.0, "count": 1 }, "SnowballTarget.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 1 }, "SnowballTarget.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 1 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1693143187", "python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [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": "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": "1693143216" }, "total": 29.146032806999983, "count": 1, "self": 0.43072998899992854, "children": { "run_training.setup": { "total": 0.04406267900003513, "count": 1, "self": 0.04406267900003513 }, "TrainerController.start_learning": { "total": 28.67124013900002, "count": 1, "self": 0.05392419699876427, "children": { "TrainerController._reset_env": { "total": 4.1275869419999935, "count": 1, "self": 4.1275869419999935 }, "TrainerController.advance": { "total": 24.33563540300122, "count": 932, "self": 0.016133708001916602, "children": { "env_step": { "total": 24.319501694999303, "count": 932, "self": 18.018902834000528, "children": { "SubprocessEnvManager._take_step": { "total": 6.284462105999978, "count": 932, "self": 0.08621643700007553, "children": { "TorchPolicy.evaluate": { "total": 6.198245668999903, "count": 932, "self": 6.198245668999903 } } }, "workers": { "total": 0.016136754998797187, "count": 932, "self": 0.0, "children": { "worker_root": { "total": 28.44282814899975, "count": 932, "is_parallel": true, "self": 14.676246149996928, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005812446999925669, "count": 1, "is_parallel": true, "self": 0.004395728999838866, "children": { "_process_rank_one_or_two_observation": { "total": 0.001416718000086803, "count": 10, "is_parallel": true, "self": 0.001416718000086803 } } }, "UnityEnvironment.step": { "total": 0.034960924999950294, "count": 1, "is_parallel": true, "self": 0.0005615059999399818, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0003208200000699435, "count": 1, "is_parallel": true, "self": 0.0003208200000699435 }, "communicator.exchange": { "total": 0.03190008499996111, "count": 1, "is_parallel": true, "self": 0.03190008499996111 }, "steps_from_proto": { "total": 0.002178513999979259, "count": 1, "is_parallel": true, "self": 0.0004912699999977121, "children": { "_process_rank_one_or_two_observation": { "total": 0.001687243999981547, "count": 10, "is_parallel": true, "self": 0.001687243999981547 } } } } } } }, "UnityEnvironment.step": { "total": 13.766581999002824, "count": 931, "is_parallel": true, "self": 0.5573397650020979, "children": { "UnityEnvironment._generate_step_input": { "total": 0.2922190620015499, "count": 931, "is_parallel": true, "self": 0.2922190620015499 }, "communicator.exchange": { "total": 10.944364759997484, "count": 931, "is_parallel": true, "self": 10.944364759997484 }, "steps_from_proto": { "total": 1.9726584120016923, "count": 931, "is_parallel": true, "self": 0.38458958300157065, "children": { "_process_rank_one_or_two_observation": { "total": 1.5880688290001217, "count": 9310, "is_parallel": true, "self": 1.5880688290001217 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00023469300003853277, "count": 1, "self": 0.00023469300003853277, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 24.152284824003686, "count": 27026, "is_parallel": true, "self": 0.5616294250012288, "children": { "process_trajectory": { "total": 14.492275540002424, "count": 27026, "is_parallel": true, "self": 14.492275540002424 }, "_update_policy": { "total": 9.098379859000033, "count": 4, "is_parallel": true, "self": 3.8573799339993684, "children": { "TorchPPOOptimizer.update": { "total": 5.240999925000665, "count": 201, "is_parallel": true, "self": 5.240999925000665 } } } } } } } } }, "TrainerController._save_models": { "total": 0.15385890400000335, "count": 1, "self": 0.000917027000014059, "children": { "RLTrainer._checkpoint": { "total": 0.1529418769999893, "count": 1, "self": 0.1529418769999893 } } } } } } }