{ "name": "root", "gauges": { "Worm.Policy.Entropy.mean": { "value": 0.8075920343399048, "min": 0.8075920343399048, "max": 1.418938398361206, "count": 233 }, "Worm.Policy.Entropy.sum": { "value": 24227.76171875, "min": 24227.76171875, "max": 42568.15234375, "count": 233 }, "Worm.Environment.EpisodeLength.mean": { "value": 999.0, "min": 999.0, "max": 999.0, "count": 233 }, "Worm.Environment.EpisodeLength.sum": { "value": 29970.0, "min": 29970.0, "max": 29970.0, "count": 233 }, "Worm.Step.mean": { "value": 6989000.0, "min": 29000.0, "max": 6989000.0, "count": 233 }, "Worm.Step.sum": { "value": 6989000.0, "min": 29000.0, "max": 6989000.0, "count": 233 }, "Worm.Policy.ExtrinsicValueEstimate.mean": { "value": 185.81259155273438, "min": -0.0501045286655426, "max": 187.16067504882812, "count": 233 }, "Worm.Policy.ExtrinsicValueEstimate.sum": { "value": 5574.3779296875, "min": -1.453031301498413, "max": 5614.8203125, "count": 233 }, "Worm.Environment.CumulativeReward.mean": { "value": 905.6671040852865, "min": 0.24104817385474842, "max": 941.0137613932292, "count": 233 }, "Worm.Environment.CumulativeReward.sum": { "value": 27170.013122558594, "min": 7.231445215642452, "max": 28230.412841796875, "count": 233 }, "Worm.Policy.ExtrinsicReward.mean": { "value": 905.6671040852865, "min": 0.24104817385474842, "max": 941.0137613932292, "count": 233 }, "Worm.Policy.ExtrinsicReward.sum": { "value": 27170.013122558594, "min": 7.231445215642452, "max": 28230.412841796875, "count": 233 }, "Worm.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 233 }, "Worm.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 233 }, "Worm.Losses.PolicyLoss.mean": { "value": 0.01853727632676185, "min": 0.011913047112535597, "max": 0.02329795364113081, "count": 232 }, "Worm.Losses.PolicyLoss.sum": { "value": 0.01853727632676185, "min": 0.011913047112535597, "max": 0.02329795364113081, "count": 232 }, "Worm.Losses.ValueLoss.mean": { "value": 7.894609258288429, "min": 0.0013617553382313677, "max": 10.170667988913399, "count": 232 }, "Worm.Losses.ValueLoss.sum": { "value": 7.894609258288429, "min": 0.0013617553382313677, "max": 10.170667988913399, "count": 232 }, "Worm.Policy.LearningRate.mean": { "value": 1.7143851428571302e-06, "min": 1.7143851428571302e-06, "max": 0.00029871428614285713, "count": 232 }, "Worm.Policy.LearningRate.sum": { "value": 1.7143851428571302e-06, "min": 1.7143851428571302e-06, "max": 0.00029871428614285713, "count": 232 }, "Worm.Policy.Epsilon.mean": { "value": 0.10057142857142858, "min": 0.10057142857142858, "max": 0.1995714285714285, "count": 232 }, "Worm.Policy.Epsilon.sum": { "value": 0.10057142857142858, "min": 0.10057142857142858, "max": 0.1995714285714285, "count": 232 }, "Worm.Policy.Beta.mean": { "value": 3.851428571428551e-05, "min": 3.851428571428551e-05, "max": 0.004978614285714285, "count": 232 }, "Worm.Policy.Beta.sum": { "value": 3.851428571428551e-05, "min": 3.851428571428551e-05, "max": 0.004978614285714285, "count": 232 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1660127524", "python_version": "3.7.13 (default, Apr 24 2022, 01:04:09) \n[GCC 7.5.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/Worm.yaml --env=./trained-envs-executables/linux/Worm/Worm --run-id=PushBlock Training --no-graphics", "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": "1.21.6", "end_time_seconds": "1660136405" }, "total": 8881.830426859, "count": 1, "self": 0.3892054290008673, "children": { "run_training.setup": { "total": 0.04222111799981576, "count": 1, "self": 0.04222111799981576 }, "TrainerController.start_learning": { "total": 8881.399000312, "count": 1, "self": 12.810893498015503, "children": { "TrainerController._reset_env": { "total": 9.321045778000098, "count": 1, "self": 9.321045778000098 }, "TrainerController.advance": { "total": 8859.149600393985, "count": 701000, "self": 14.13721502599401, "children": { "env_step": { "total": 7251.756922832681, "count": 701000, "self": 6386.022913035704, "children": { "SubprocessEnvManager._take_step": { "total": 858.3625304840384, "count": 701000, "self": 58.990014658093514, "children": { "TorchPolicy.evaluate": { "total": 799.3725158259449, "count": 701000, "self": 203.9437816147638, "children": { "TorchPolicy.sample_actions": { "total": 595.4287342111811, "count": 701000, "self": 595.4287342111811 } } } } }, "workers": { "total": 7.371479312938391, "count": 701000, "self": 0.0, "children": { "worker_root": { "total": 8857.138676524453, "count": 701000, "is_parallel": true, "self": 3277.337091225454, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0010683850000532402, "count": 1, "is_parallel": true, "self": 0.00034967200008395594, "children": { "_process_rank_one_or_two_observation": { "total": 0.0007187129999692843, "count": 2, "is_parallel": true, "self": 0.0007187129999692843 } } }, "UnityEnvironment.step": { "total": 0.030562207000002672, "count": 1, "is_parallel": true, "self": 0.00023362000001725391, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00039819099993110285, "count": 1, "is_parallel": true, "self": 0.00039819099993110285 }, "communicator.exchange": { "total": 0.02934107999999469, "count": 1, "is_parallel": true, "self": 0.02934107999999469 }, "steps_from_proto": { "total": 0.0005893160000596254, "count": 1, "is_parallel": true, "self": 0.0002181469999413821, "children": { "_process_rank_one_or_two_observation": { "total": 0.0003711690001182433, "count": 2, "is_parallel": true, "self": 0.0003711690001182433 } } } } } } }, "UnityEnvironment.step": { "total": 5579.801585298999, "count": 700999, "is_parallel": true, "self": 116.98237653461729, "children": { "UnityEnvironment._generate_step_input": { "total": 214.1962914984215, "count": 700999, "is_parallel": true, "self": 214.1962914984215 }, "communicator.exchange": { "total": 4946.531019579072, "count": 700999, "is_parallel": true, "self": 4946.531019579072 }, "steps_from_proto": { "total": 302.09189768688884, "count": 700999, "is_parallel": true, "self": 120.60829531996205, "children": { "_process_rank_one_or_two_observation": { "total": 181.4836023669268, "count": 1401998, "is_parallel": true, "self": 181.4836023669268 } } } } } } } } } } }, "trainer_advance": { "total": 1593.2554625353087, "count": 701000, "self": 16.456634260653118, "children": { "process_trajectory": { "total": 454.4748560246562, "count": 701000, "self": 452.8033211146562, "children": { "RLTrainer._checkpoint": { "total": 1.6715349099999912, "count": 14, "self": 1.6715349099999912 } } }, "_update_policy": { "total": 1122.3239722499993, "count": 233, "self": 978.796790962986, "children": { "TorchPPOOptimizer.update": { "total": 143.52718128701326, "count": 9786, "self": 143.52718128701326 } } } } } } }, "trainer_threads": { "total": 1.2869986676378176e-06, "count": 1, "self": 1.2869986676378176e-06 }, "TrainerController._save_models": { "total": 0.11745935500039195, "count": 1, "self": 0.0023483910008508246, "children": { "RLTrainer._checkpoint": { "total": 0.11511096399954113, "count": 1, "self": 0.11511096399954113 } } } } } } }