{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 1.1423933506011963, "min": 1.1423933506011963, "max": 2.849839687347412, "count": 15 }, "SnowballTarget.Policy.Entropy.sum": { "value": 11674.1171875, "min": 11135.353515625, "max": 29185.20703125, "count": 15 }, "SnowballTarget.Step.mean": { "value": 149984.0, "min": 9952.0, "max": 149984.0, "count": 15 }, "SnowballTarget.Step.sum": { "value": 149984.0, "min": 9952.0, "max": 149984.0, "count": 15 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": { "value": 12.03204345703125, "min": 0.41945621371269226, "max": 12.03204345703125, "count": 15 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2466.56884765625, "min": 81.37450408935547, "max": 2466.56884765625, "count": 15 }, "SnowballTarget.Environment.EpisodeLength.mean": { "value": 199.0, "min": 199.0, "max": 199.0, "count": 15 }, "SnowballTarget.Environment.EpisodeLength.sum": { "value": 10945.0, "min": 8756.0, "max": 10945.0, "count": 15 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.02850102154770866, "min": 0.02715948994082282, "max": 0.03786330181756056, "count": 15 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.1425051077385433, "min": 0.10863795976329128, "max": 0.16722320581466193, "count": 15 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.23758389726281165, "min": 0.12270995005965232, "max": 0.3125932976603508, "count": 15 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 1.1879194863140583, "min": 0.4908398002386093, "max": 1.562966488301754, "count": 15 }, "SnowballTarget.Policy.LearningRate.mean": { "value": 9.776096741333336e-06, "min": 9.776096741333336e-06, "max": 0.000289176003608, "count": 15 }, "SnowballTarget.Policy.LearningRate.sum": { "value": 4.888048370666668e-05, "min": 4.888048370666668e-05, "max": 0.0013468800510399999, "count": 15 }, "SnowballTarget.Policy.Epsilon.mean": { "value": 0.10325866666666668, "min": 0.10325866666666668, "max": 0.196392, "count": 15 }, "SnowballTarget.Policy.Epsilon.sum": { "value": 0.5162933333333334, "min": 0.43943466666666664, "max": 0.94896, "count": 15 }, "SnowballTarget.Policy.Beta.mean": { "value": 0.00017260746666666676, "min": 0.00017260746666666676, "max": 0.004819960799999999, "count": 15 }, "SnowballTarget.Policy.Beta.sum": { "value": 0.0008630373333333338, "min": 0.0008630373333333338, "max": 0.022453104, "count": 15 }, "SnowballTarget.Environment.CumulativeReward.mean": { "value": 23.727272727272727, "min": 3.5454545454545454, "max": 24.25, "count": 15 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1305.0, "min": 156.0, "max": 1311.0, "count": 15 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 23.727272727272727, "min": 3.5454545454545454, "max": 24.25, "count": 15 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1305.0, "min": 156.0, "max": 1311.0, "count": 15 }, "SnowballTarget.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 15 }, "SnowballTarget.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 15 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1675843178", "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": "1.21.6", "end_time_seconds": "1675843653" }, "total": 474.893120133, "count": 1, "self": 0.5436823820000427, "children": { "run_training.setup": { "total": 0.24930607499993584, "count": 1, "self": 0.24930607499993584 }, "TrainerController.start_learning": { "total": 474.10013167600005, "count": 1, "self": 0.7322830389929322, "children": { "TrainerController._reset_env": { "total": 4.439574778000065, "count": 1, "self": 4.439574778000065 }, "TrainerController.advance": { "total": 468.7857527310073, "count": 13672, "self": 0.35482043100194005, "children": { "env_step": { "total": 468.43093230000534, "count": 13672, "self": 356.53096391199733, "children": { "SubprocessEnvManager._take_step": { "total": 111.56999483399989, "count": 13672, "self": 1.879139852983485, "children": { "TorchPolicy.evaluate": { "total": 109.6908549810164, "count": 13672, "self": 18.200927154006536, "children": { "TorchPolicy.sample_actions": { "total": 91.48992782700986, "count": 13672, "self": 91.48992782700986 } } } } }, "workers": { "total": 0.3299735540081201, "count": 13672, "self": 0.0, "children": { "worker_root": { "total": 472.4533822030088, "count": 13672, "is_parallel": true, "self": 215.79291343701732, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.008182450999925095, "count": 1, "is_parallel": true, "self": 0.004812439999909657, "children": { "_process_rank_one_or_two_observation": { "total": 0.003370011000015438, "count": 10, "is_parallel": true, "self": 0.003370011000015438 } } }, "UnityEnvironment.step": { "total": 0.04523271899995507, "count": 1, "is_parallel": true, "self": 0.0006993479998982366, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00046684900007676333, "count": 1, "is_parallel": true, "self": 0.00046684900007676333 }, "communicator.exchange": { "total": 0.04130628500001876, "count": 1, "is_parallel": true, "self": 0.04130628500001876 }, "steps_from_proto": { "total": 0.0027602369999613074, "count": 1, "is_parallel": true, "self": 0.0007601599997997255, "children": { "_process_rank_one_or_two_observation": { "total": 0.002000077000161582, "count": 10, "is_parallel": true, "self": 0.002000077000161582 } } } } } } }, "UnityEnvironment.step": { "total": 256.6604687659915, "count": 13671, "is_parallel": true, "self": 10.583427900016318, "children": { "UnityEnvironment._generate_step_input": { "total": 5.7460929979858975, "count": 13671, "is_parallel": true, "self": 5.7460929979858975 }, "communicator.exchange": { "total": 202.31195415299408, "count": 13671, "is_parallel": true, "self": 202.31195415299408 }, "steps_from_proto": { "total": 38.01899371499519, "count": 13671, "is_parallel": true, "self": 8.216695931959066, "children": { "_process_rank_one_or_two_observation": { "total": 29.802297783036124, "count": 136710, "is_parallel": true, "self": 29.802297783036124 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.0002493009999398055, "count": 1, "self": 0.0002493009999398055, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 464.0099603490286, "count": 524291, "is_parallel": true, "self": 13.614415453931542, "children": { "process_trajectory": { "total": 244.28630206209675, "count": 524291, "is_parallel": true, "self": 243.03004654209678, "children": { "RLTrainer._checkpoint": { "total": 1.2562555199999679, "count": 3, "is_parallel": true, "self": 1.2562555199999679 } } }, "_update_policy": { "total": 206.10924283300028, "count": 68, "is_parallel": true, "self": 99.61722932000487, "children": { "TorchPPOOptimizer.update": { "total": 106.49201351299541, "count": 1360, "is_parallel": true, "self": 106.49201351299541 } } } } } } } } }, "TrainerController._save_models": { "total": 0.14227182699983132, "count": 1, "self": 0.002192171999695347, "children": { "RLTrainer._checkpoint": { "total": 0.14007965500013597, "count": 1, "self": 0.14007965500013597 } } } } } } }