{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 1.6152853965759277, "min": 1.6152853965759277, "max": 2.88734769821167, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 15404.9765625, "min": 15404.9765625, "max": 29557.68359375, "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": 7.5939483642578125, "min": 0.08465117961168289, "max": 7.5939483642578125, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 1480.8199462890625, "min": 16.42232894897461, "max": 1517.674072265625, "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.Environment.CumulativeReward.mean": { "value": 15.295454545454545, "min": 2.6818181818181817, "max": 15.818181818181818, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 673.0, "min": 118.0, "max": 870.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 15.295454545454545, "min": 2.6818181818181817, "max": 15.818181818181818, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 673.0, "min": 118.0, "max": 870.0, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.05884845642026003, "min": 0.042890819961173166, "max": 0.05884845642026003, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.11769691284052006, "min": 0.08578163992234633, "max": 0.14945020310366158, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.3042387500697491, "min": 0.1109681136623098, "max": 0.3042387500697491, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.6084775001394982, "min": 0.2219362273246196, "max": 0.8250444426256067, "count": 20 }, "SnowballTarget.Policy.LearningRate.mean": { "value": 6.432097856000005e-06, "min": 6.432097856000005e-06, "max": 0.00029023200325600004, "count": 20 }, "SnowballTarget.Policy.LearningRate.sum": { "value": 1.286419571200001e-05, "min": 1.286419571200001e-05, "max": 0.0007419960526679999, "count": 20 }, "SnowballTarget.Policy.Epsilon.mean": { "value": 0.102144, "min": 0.102144, "max": 0.196744, "count": 20 }, "SnowballTarget.Policy.Epsilon.sum": { "value": 0.204288, "min": 0.204288, "max": 0.5473320000000002, "count": 20 }, "SnowballTarget.Policy.Beta.mean": { "value": 0.00011698560000000007, "min": 0.00011698560000000007, "max": 0.0048375256, "count": 20 }, "SnowballTarget.Policy.Beta.sum": { "value": 0.00023397120000000015, "min": 0.00023397120000000015, "max": 0.012371866800000002, "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": "1677710679", "python_version": "3.8.10 (default, Nov 14 2022, 12:59:47) \n[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 --force", "mlagents_version": "0.29.0.dev0", "mlagents_envs_version": "0.29.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.8.1+cu102", "numpy_version": "1.22.4", "end_time_seconds": "1677711146" }, "total": 466.70228948199997, "count": 1, "self": 0.42417477200012854, "children": { "run_training.setup": { "total": 0.10674178399995071, "count": 1, "self": 0.10674178399995071 }, "TrainerController.start_learning": { "total": 466.1713729259999, "count": 1, "self": 0.5451415709945877, "children": { "TrainerController._reset_env": { "total": 7.331290541000044, "count": 1, "self": 7.331290541000044 }, "TrainerController.advance": { "total": 458.17238222100536, "count": 18200, "self": 0.28932266699848697, "children": { "env_step": { "total": 457.8830595540069, "count": 18200, "self": 320.35797583299757, "children": { "SubprocessEnvManager._take_step": { "total": 137.2406449350051, "count": 18200, "self": 1.5290543090019355, "children": { "TorchPolicy.evaluate": { "total": 135.71159062600316, "count": 18200, "self": 30.2905803559928, "children": { "TorchPolicy.sample_actions": { "total": 105.42101027001036, "count": 18200, "self": 105.42101027001036 } } } } }, "workers": { "total": 0.2844387860042161, "count": 18200, "self": 0.0, "children": { "worker_root": { "total": 464.66502466899715, "count": 18200, "is_parallel": true, "self": 221.16348440200466, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.002174560000071324, "count": 1, "is_parallel": true, "self": 0.0007738339999150412, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014007260001562827, "count": 10, "is_parallel": true, "self": 0.0014007260001562827 } } }, "UnityEnvironment.step": { "total": 0.08619363399998292, "count": 1, "is_parallel": true, "self": 0.002991712000152802, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00025803599999107973, "count": 1, "is_parallel": true, "self": 0.00025803599999107973 }, "communicator.exchange": { "total": 0.08097321899992949, "count": 1, "is_parallel": true, "self": 0.08097321899992949 }, "steps_from_proto": { "total": 0.001970666999909554, "count": 1, "is_parallel": true, "self": 0.00048233899974547967, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014883280001640742, "count": 10, "is_parallel": true, "self": 0.0014883280001640742 } } } } } } }, "UnityEnvironment.step": { "total": 243.5015402669925, "count": 18199, "is_parallel": true, "self": 9.697661220998953, "children": { "UnityEnvironment._generate_step_input": { "total": 5.483377517013878, "count": 18199, "is_parallel": true, "self": 5.483377517013878 }, "communicator.exchange": { "total": 195.8069058279914, "count": 18199, "is_parallel": true, "self": 195.8069058279914 }, "steps_from_proto": { "total": 32.513595700988276, "count": 18199, "is_parallel": true, "self": 7.0953470900116145, "children": { "_process_rank_one_or_two_observation": { "total": 25.41824861097666, "count": 181990, "is_parallel": true, "self": 25.41824861097666 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00013384299995777837, "count": 1, "self": 0.00013384299995777837, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 453.43585246907253, "count": 528982, "is_parallel": true, "self": 13.739551421075703, "children": { "process_trajectory": { "total": 322.0069829139975, "count": 528982, "is_parallel": true, "self": 320.7396215989977, "children": { "RLTrainer._checkpoint": { "total": 1.267361314999789, "count": 4, "is_parallel": true, "self": 1.267361314999789 } } }, "_update_policy": { "total": 117.68931813399934, "count": 45, "is_parallel": true, "self": 60.278016426001386, "children": { "TorchPPOOptimizer.update": { "total": 57.41130170799795, "count": 2292, "is_parallel": true, "self": 57.41130170799795 } } } } } } } } }, "TrainerController._save_models": { "total": 0.12242474999993647, "count": 1, "self": 0.0006489879999662662, "children": { "RLTrainer._checkpoint": { "total": 0.1217757619999702, "count": 1, "self": 0.1217757619999702 } } } } } } }