{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 1.2991029024124146, "min": 1.2991029024124146, "max": 2.884037494659424, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 12160.90234375, "min": 12160.90234375, "max": 31014.328125, "count": 20 }, "SnowballTarget.Step.mean": { "value": 199992.0, "min": 9984.0, "max": 199992.0, "count": 20 }, "SnowballTarget.Step.sum": { "value": 199992.0, "min": 9984.0, "max": 199992.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": { "value": 6.463836669921875, "min": 0.2772822678089142, "max": 6.463836669921875, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 976.0393676757812, "min": 41.037776947021484, "max": 976.0393676757812, "count": 20 }, "SnowballTarget.Environment.EpisodeLength.mean": { "value": 199.0, "min": 199.0, "max": 199.0, "count": 20 }, "SnowballTarget.Environment.EpisodeLength.sum": { "value": 10945.0, "min": 8756.0, "max": 10945.0, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.mean": { "value": 25.80392156862745, "min": 3.090909090909091, "max": 25.80392156862745, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1316.0, "min": 136.0, "max": 1359.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.80392156862745, "min": 3.090909090909091, "max": 25.80392156862745, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1316.0, "min": 136.0, "max": 1359.0, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.05945388550963539, "min": 0.05945388550963539, "max": 0.06657232236554722, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.23781554203854155, "min": 0.23781554203854155, "max": 0.3284966726993195, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.183262244425714, "min": 0.09850787479829576, "max": 0.2549174259283713, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.733048977702856, "min": 0.39403149919318303, "max": 1.2277166165411473, "count": 20 }, "SnowballTarget.Policy.LearningRate.mean": { "value": 7.950097350000008e-06, "min": 7.950097350000008e-06, "max": 0.00029175000275, "count": 20 }, "SnowballTarget.Policy.LearningRate.sum": { "value": 3.180038940000003e-05, "min": 3.180038940000003e-05, "max": 0.0013845000385, "count": 20 }, "SnowballTarget.Policy.Epsilon.mean": { "value": 0.09999999999999998, "min": 0.09999999999999998, "max": 0.09999999999999998, "count": 20 }, "SnowballTarget.Policy.Epsilon.sum": { "value": 0.3999999999999999, "min": 0.3999999999999999, "max": 0.4999999999999999, "count": 20 }, "SnowballTarget.Policy.Beta.mean": { "value": 3.623500000000002e-05, "min": 3.623500000000002e-05, "max": 0.0009727749999999999, "count": 20 }, "SnowballTarget.Policy.Beta.sum": { "value": 0.00014494000000000009, "min": 0.00014494000000000009, "max": 0.004618850000000001, "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": "1696276818", "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": "1696277972" }, "total": 1154.428818762, "count": 1, "self": 1.0753539990000718, "children": { "run_training.setup": { "total": 0.08416951399999562, "count": 1, "self": 0.08416951399999562 }, "TrainerController.start_learning": { "total": 1153.269295249, "count": 1, "self": 1.1662224659935418, "children": { "TrainerController._reset_env": { "total": 4.575206643999991, "count": 1, "self": 4.575206643999991 }, "TrainerController.advance": { "total": 1147.1329956800066, "count": 18236, "self": 0.510800703026689, "children": { "env_step": { "total": 1146.62219497698, "count": 18236, "self": 999.805822083998, "children": { "SubprocessEnvManager._take_step": { "total": 146.34128918899745, "count": 18236, "self": 2.886309995996129, "children": { "TorchPolicy.evaluate": { "total": 143.45497919300132, "count": 18236, "self": 143.45497919300132 } } }, "workers": { "total": 0.47508370398441, "count": 18236, "self": 0.0, "children": { "worker_root": { "total": 1150.283555413998, "count": 18236, "is_parallel": true, "self": 780.1486684300111, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.00773595199999022, "count": 1, "is_parallel": true, "self": 0.004757176999987678, "children": { "_process_rank_one_or_two_observation": { "total": 0.0029787750000025426, "count": 10, "is_parallel": true, "self": 0.0029787750000025426 } } }, "UnityEnvironment.step": { "total": 0.060158758000000034, "count": 1, "is_parallel": true, "self": 0.0008301029999699949, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005832270000212247, "count": 1, "is_parallel": true, "self": 0.0005832270000212247 }, "communicator.exchange": { "total": 0.054616455999990876, "count": 1, "is_parallel": true, "self": 0.054616455999990876 }, "steps_from_proto": { "total": 0.004128972000017939, "count": 1, "is_parallel": true, "self": 0.0005346530000167604, "children": { "_process_rank_one_or_two_observation": { "total": 0.003594319000001178, "count": 10, "is_parallel": true, "self": 0.003594319000001178 } } } } } } }, "UnityEnvironment.step": { "total": 370.13488698398703, "count": 18235, "is_parallel": true, "self": 15.883491138994145, "children": { "UnityEnvironment._generate_step_input": { "total": 7.7538960629972, "count": 18235, "is_parallel": true, "self": 7.7538960629972 }, "communicator.exchange": { "total": 294.34221507598284, "count": 18235, "is_parallel": true, "self": 294.34221507598284 }, "steps_from_proto": { "total": 52.15528470601279, "count": 18235, "is_parallel": true, "self": 10.470978443024336, "children": { "_process_rank_one_or_two_observation": { "total": 41.68430626298846, "count": 182350, "is_parallel": true, "self": 41.68430626298846 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00040532899993195315, "count": 1, "self": 0.00040532899993195315, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 1146.375508204033, "count": 200925, "is_parallel": true, "self": 4.437364087048536, "children": { "process_trajectory": { "total": 187.06477452898466, "count": 200925, "is_parallel": true, "self": 163.72388005998377, "children": { "RLTrainer._checkpoint": { "total": 23.340894469000887, "count": 40, "is_parallel": true, "self": 23.340894469000887 } } }, "_update_policy": { "total": 954.8733695879998, "count": 90, "is_parallel": true, "self": 262.44180190999714, "children": { "TorchPPOOptimizer.update": { "total": 692.4315676780027, "count": 12600, "is_parallel": true, "self": 692.4315676780027 } } } } } } } } }, "TrainerController._save_models": { "total": 0.39446512999984407, "count": 1, "self": 0.003891258999829006, "children": { "RLTrainer._checkpoint": { "total": 0.39057387100001506, "count": 1, "self": 0.39057387100001506 } } } } } } }