{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.8507401943206787, "min": 0.8291850090026855, "max": 2.866727828979492, "count": 30 }, "SnowballTarget.Policy.Entropy.sum": { "value": 8740.5048828125, "min": 8026.5107421875, "max": 29515.830078125, "count": 30 }, "SnowballTarget.Step.mean": { "value": 299968.0, "min": 9952.0, "max": 299968.0, "count": 30 }, "SnowballTarget.Step.sum": { "value": 299968.0, "min": 9952.0, "max": 299968.0, "count": 30 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": { "value": 13.296443939208984, "min": 0.26397505402565, "max": 13.543513298034668, "count": 30 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2712.474609375, "min": 51.21116256713867, "max": 2770.18115234375, "count": 30 }, "SnowballTarget.Environment.EpisodeLength.mean": { "value": 199.0, "min": 199.0, "max": 199.0, "count": 30 }, "SnowballTarget.Environment.EpisodeLength.sum": { "value": 10945.0, "min": 8756.0, "max": 10945.0, "count": 30 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.0708061565295793, "min": 0.060227686083546325, "max": 0.07714225342230444, "count": 30 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.35403078264789656, "min": 0.2409107443341853, "max": 0.38200219925013645, "count": 30 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.17968245756392384, "min": 0.11114339690481988, "max": 0.2831786065124998, "count": 30 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.8984122878196192, "min": 0.4445735876192795, "max": 1.415893032562499, "count": 30 }, "SnowballTarget.Policy.LearningRate.mean": { "value": 5.288098237333331e-06, "min": 5.288098237333331e-06, "max": 0.00029458800180399996, "count": 30 }, "SnowballTarget.Policy.LearningRate.sum": { "value": 2.6440491186666655e-05, "min": 2.6440491186666655e-05, "max": 0.0014234400255199997, "count": 30 }, "SnowballTarget.Policy.Epsilon.mean": { "value": 0.10176266666666667, "min": 0.10176266666666667, "max": 0.198196, "count": 30 }, "SnowballTarget.Policy.Epsilon.sum": { "value": 0.5088133333333333, "min": 0.42025066666666666, "max": 0.97448, "count": 30 }, "SnowballTarget.Policy.Beta.mean": { "value": 9.795706666666662e-05, "min": 9.795706666666662e-05, "max": 0.0049099804000000006, "count": 30 }, "SnowballTarget.Policy.Beta.sum": { "value": 0.0004897853333333331, "min": 0.0004897853333333331, "max": 0.023726551999999998, "count": 30 }, "SnowballTarget.Environment.CumulativeReward.mean": { "value": 26.327272727272728, "min": 3.0681818181818183, "max": 26.490909090909092, "count": 30 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1448.0, "min": 135.0, "max": 1457.0, "count": 30 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 26.327272727272728, "min": 3.0681818181818183, "max": 26.490909090909092, "count": 30 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1448.0, "min": 135.0, "max": 1457.0, "count": 30 }, "SnowballTarget.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 30 }, "SnowballTarget.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 30 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1688715987", "python_version": "3.10.12 (main, Jun 7 2023, 12:45:35) [GCC 9.4.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn /content/ml-agents/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": "1688716684" }, "total": 696.7644324510002, "count": 1, "self": 0.8390476290001061, "children": { "run_training.setup": { "total": 0.03734973800010266, "count": 1, "self": 0.03734973800010266 }, "TrainerController.start_learning": { "total": 695.888035084, "count": 1, "self": 0.9058814670070205, "children": { "TrainerController._reset_env": { "total": 3.87089740600004, "count": 1, "self": 3.87089740600004 }, "TrainerController.advance": { "total": 690.8863383759926, "count": 27347, "self": 0.43264958397867304, "children": { "env_step": { "total": 690.453688792014, "count": 27347, "self": 499.93059462204974, "children": { "SubprocessEnvManager._take_step": { "total": 190.09455864195797, "count": 27347, "self": 2.6695299849275216, "children": { "TorchPolicy.evaluate": { "total": 187.42502865703045, "count": 27347, "self": 187.42502865703045 } } }, "workers": { "total": 0.4285355280062504, "count": 27347, "self": 0.0, "children": { "worker_root": { "total": 693.3791361980893, "count": 27347, "is_parallel": true, "self": 320.8251622021039, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0018797029997585923, "count": 1, "is_parallel": true, "self": 0.0005528279998543439, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013268749999042484, "count": 10, "is_parallel": true, "self": 0.0013268749999042484 } } }, "UnityEnvironment.step": { "total": 0.035829946999911044, "count": 1, "is_parallel": true, "self": 0.0005721009997614601, "children": { "UnityEnvironment._generate_step_input": { "total": 0.000423312000293663, "count": 1, "is_parallel": true, "self": 0.000423312000293663 }, "communicator.exchange": { "total": 0.03289218700001584, "count": 1, "is_parallel": true, "self": 0.03289218700001584 }, "steps_from_proto": { "total": 0.0019423469998400833, "count": 1, "is_parallel": true, "self": 0.00046012799930394976, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014822190005361335, "count": 10, "is_parallel": true, "self": 0.0014822190005361335 } } } } } } }, "UnityEnvironment.step": { "total": 372.5539739959854, "count": 27346, "is_parallel": true, "self": 15.195663510088707, "children": { "UnityEnvironment._generate_step_input": { "total": 7.814785227968969, "count": 27346, "is_parallel": true, "self": 7.814785227968969 }, "communicator.exchange": { "total": 298.43525926600387, "count": 27346, "is_parallel": true, "self": 298.43525926600387 }, "steps_from_proto": { "total": 51.10826599192387, "count": 27346, "is_parallel": true, "self": 9.469808990055299, "children": { "_process_rank_one_or_two_observation": { "total": 41.638457001868574, "count": 273460, "is_parallel": true, "self": 41.638457001868574 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00015593399984936696, "count": 1, "self": 0.00015593399984936696, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 685.7832788439732, "count": 692323, "is_parallel": true, "self": 14.158524109112932, "children": { "process_trajectory": { "total": 379.73044558385754, "count": 692323, "is_parallel": true, "self": 377.75901040285817, "children": { "RLTrainer._checkpoint": { "total": 1.9714351809993786, "count": 6, "is_parallel": true, "self": 1.9714351809993786 } } }, "_update_policy": { "total": 291.89430915100274, "count": 136, "is_parallel": true, "self": 106.11507624400383, "children": { "TorchPPOOptimizer.update": { "total": 185.7792329069989, "count": 6933, "is_parallel": true, "self": 185.7792329069989 } } } } } } } } }, "TrainerController._save_models": { "total": 0.22476190100042004, "count": 1, "self": 0.0011713479998434195, "children": { "RLTrainer._checkpoint": { "total": 0.22359055300057662, "count": 1, "self": 0.22359055300057662 } } } } } } }