{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 1.006279468536377, "min": 1.006279468536377, "max": 2.8712151050567627, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 9641.1640625, "min": 9641.1640625, "max": 29467.28125, "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": 13.048412322998047, "min": 0.346085786819458, "max": 13.048412322998047, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2544.4404296875, "min": 67.14064025878906, "max": 2641.282958984375, "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": 0.0637497174568981, "min": 0.0628459351899116, "max": 0.07480647636851903, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2549988698275924, "min": 0.2549988698275924, "max": 0.3597638165731184, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.18983629499288168, "min": 0.10006606624137573, "max": 0.29342734942249227, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.7593451799715267, "min": 0.40026426496550294, "max": 1.4671367471124612, "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": 25.84090909090909, "min": 3.0454545454545454, "max": 25.84090909090909, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1137.0, "min": 134.0, "max": 1401.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.84090909090909, "min": 3.0454545454545454, "max": 25.84090909090909, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1137.0, "min": 134.0, "max": 1401.0, "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": "1711660647", "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": "2.2.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1711661225" }, "total": 578.0435552160001, "count": 1, "self": 0.5473047580001094, "children": { "run_training.setup": { "total": 0.12221278200001962, "count": 1, "self": 0.12221278200001962 }, "TrainerController.start_learning": { "total": 577.374037676, "count": 1, "self": 0.8389270099954729, "children": { "TrainerController._reset_env": { "total": 4.351390480999953, "count": 1, "self": 4.351390480999953 }, "TrainerController.advance": { "total": 572.0734477650045, "count": 18203, "self": 0.44033896300152264, "children": { "env_step": { "total": 571.633108802003, "count": 18203, "self": 438.2503542320086, "children": { "SubprocessEnvManager._take_step": { "total": 132.9781009659979, "count": 18203, "self": 2.133280130003527, "children": { "TorchPolicy.evaluate": { "total": 130.84482083599437, "count": 18203, "self": 130.84482083599437 } } }, "workers": { "total": 0.4046536039965076, "count": 18203, "self": 0.0, "children": { "worker_root": { "total": 575.4624964329862, "count": 18203, "is_parallel": true, "self": 271.5756528790025, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.01258693400006905, "count": 1, "is_parallel": true, "self": 0.010418331999971997, "children": { "_process_rank_one_or_two_observation": { "total": 0.002168602000097053, "count": 10, "is_parallel": true, "self": 0.002168602000097053 } } }, "UnityEnvironment.step": { "total": 0.04567319399995995, "count": 1, "is_parallel": true, "self": 0.0009468819999938205, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005313460000024861, "count": 1, "is_parallel": true, "self": 0.0005313460000024861 }, "communicator.exchange": { "total": 0.04175710699996671, "count": 1, "is_parallel": true, "self": 0.04175710699996671 }, "steps_from_proto": { "total": 0.0024378589999969336, "count": 1, "is_parallel": true, "self": 0.0006110539999326647, "children": { "_process_rank_one_or_two_observation": { "total": 0.0018268050000642688, "count": 10, "is_parallel": true, "self": 0.0018268050000642688 } } } } } } }, "UnityEnvironment.step": { "total": 303.8868435539837, "count": 18202, "is_parallel": true, "self": 14.401921396968987, "children": { "UnityEnvironment._generate_step_input": { "total": 7.44700186799696, "count": 18202, "is_parallel": true, "self": 7.44700186799696 }, "communicator.exchange": { "total": 237.39793622099364, "count": 18202, "is_parallel": true, "self": 237.39793622099364 }, "steps_from_proto": { "total": 44.63998406802409, "count": 18202, "is_parallel": true, "self": 8.881529488012916, "children": { "_process_rank_one_or_two_observation": { "total": 35.758454580011175, "count": 182020, "is_parallel": true, "self": 35.758454580011175 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00029556799995589245, "count": 1, "self": 0.00029556799995589245, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 565.2910543030424, "count": 767716, "is_parallel": true, "self": 18.231015574034018, "children": { "process_trajectory": { "total": 297.87004974700847, "count": 767716, "is_parallel": true, "self": 296.9949957550084, "children": { "RLTrainer._checkpoint": { "total": 0.875053992000062, "count": 4, "is_parallel": true, "self": 0.875053992000062 } } }, "_update_policy": { "total": 249.18998898199993, "count": 90, "is_parallel": true, "self": 71.24316688600129, "children": { "TorchPPOOptimizer.update": { "total": 177.94682209599864, "count": 4587, "is_parallel": true, "self": 177.94682209599864 } } } } } } } } }, "TrainerController._save_models": { "total": 0.10997685200004526, "count": 1, "self": 0.0013107209999816405, "children": { "RLTrainer._checkpoint": { "total": 0.10866613100006361, "count": 1, "self": 0.10866613100006361 } } } } } } }