{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 1.7562263011932373, "min": 1.7562263011932373, "max": 2.8640341758728027, "count": 10 }, "SnowballTarget.Policy.Entropy.sum": { "value": 18082.10546875, "min": 17038.705078125, "max": 29362.078125, "count": 10 }, "SnowballTarget.Step.mean": { "value": 99960.0, "min": 9952.0, "max": 99960.0, "count": 10 }, "SnowballTarget.Step.sum": { "value": 99960.0, "min": 9952.0, "max": 99960.0, "count": 10 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": { "value": 8.264595985412598, "min": 0.4249187707901001, "max": 8.264595985412598, "count": 10 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 1685.9776611328125, "min": 82.43424224853516, "max": 1685.9776611328125, "count": 10 }, "SnowballTarget.Environment.EpisodeLength.mean": { "value": 199.0, "min": 199.0, "max": 199.0, "count": 10 }, "SnowballTarget.Environment.EpisodeLength.sum": { "value": 10945.0, "min": 8756.0, "max": 10945.0, "count": 10 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.06772408748465572, "min": 0.06324473189660257, "max": 0.0722757178929825, "count": 10 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.33862043742327863, "min": 0.25456921600647653, "max": 0.36137858946491247, "count": 10 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.26413684066604165, "min": 0.1389135341730663, "max": 0.271015069063972, "count": 10 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 1.3206842033302082, "min": 0.5556541366922652, "max": 1.35507534531986, "count": 10 }, "SnowballTarget.Policy.LearningRate.mean": { "value": 1.6464094511999996e-05, "min": 1.6464094511999996e-05, "max": 0.000283764005412, "count": 10 }, "SnowballTarget.Policy.LearningRate.sum": { "value": 8.232047255999999e-05, "min": 8.232047255999999e-05, "max": 0.00127032007656, "count": 10 }, "SnowballTarget.Policy.Epsilon.mean": { "value": 0.105488, "min": 0.105488, "max": 0.194588, "count": 10 }, "SnowballTarget.Policy.Epsilon.sum": { "value": 0.52744, "min": 0.4615520000000001, "max": 0.92344, "count": 10 }, "SnowballTarget.Policy.Beta.mean": { "value": 0.0002838512, "min": 0.0002838512, "max": 0.0047299412, "count": 10 }, "SnowballTarget.Policy.Beta.sum": { "value": 0.001419256, "min": 0.001419256, "max": 0.021179656, "count": 10 }, "SnowballTarget.Environment.CumulativeReward.mean": { "value": 17.672727272727272, "min": 3.6818181818181817, "max": 17.672727272727272, "count": 10 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 972.0, "min": 162.0, "max": 972.0, "count": 10 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 17.672727272727272, "min": 3.6818181818181817, "max": 17.672727272727272, "count": 10 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 972.0, "min": 162.0, "max": 972.0, "count": 10 }, "SnowballTarget.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 10 }, "SnowballTarget.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 10 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1683117003", "python_version": "3.10.11 (main, Apr 5 2023, 14:15:10) [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", "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": "1683117249" }, "total": 246.8081528, "count": 1, "self": 0.7884301389999848, "children": { "run_training.setup": { "total": 0.03995504200000255, "count": 1, "self": 0.03995504200000255 }, "TrainerController.start_learning": { "total": 245.979767619, "count": 1, "self": 0.3581058350022772, "children": { "TrainerController._reset_env": { "total": 5.298969027000027, "count": 1, "self": 5.298969027000027 }, "TrainerController.advance": { "total": 240.0946731209977, "count": 9139, "self": 0.1501838449973718, "children": { "env_step": { "total": 239.94448927600033, "count": 9139, "self": 175.41678418400514, "children": { "SubprocessEnvManager._take_step": { "total": 64.37635004699823, "count": 9139, "self": 0.8765458759994829, "children": { "TorchPolicy.evaluate": { "total": 63.49980417099874, "count": 9139, "self": 63.49980417099874 } } }, "workers": { "total": 0.1513550449969614, "count": 9139, "self": 0.0, "children": { "worker_root": { "total": 245.02767225000224, "count": 9139, "is_parallel": true, "self": 114.9387168160033, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.007437401000004229, "count": 1, "is_parallel": true, "self": 0.00547502000000577, "children": { "_process_rank_one_or_two_observation": { "total": 0.0019623809999984587, "count": 10, "is_parallel": true, "self": 0.0019623809999984587 } } }, "UnityEnvironment.step": { "total": 0.0344401019999907, "count": 1, "is_parallel": true, "self": 0.0005832839999868611, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0003274489999967045, "count": 1, "is_parallel": true, "self": 0.0003274489999967045 }, "communicator.exchange": { "total": 0.031614434000005076, "count": 1, "is_parallel": true, "self": 0.031614434000005076 }, "steps_from_proto": { "total": 0.0019149350000020604, "count": 1, "is_parallel": true, "self": 0.00040229100011401897, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015126439998880414, "count": 10, "is_parallel": true, "self": 0.0015126439998880414 } } } } } } }, "UnityEnvironment.step": { "total": 130.08895543399893, "count": 9138, "is_parallel": true, "self": 5.163457792996184, "children": { "UnityEnvironment._generate_step_input": { "total": 2.731939688002228, "count": 9138, "is_parallel": true, "self": 2.731939688002228 }, "communicator.exchange": { "total": 104.90102576300058, "count": 9138, "is_parallel": true, "self": 104.90102576300058 }, "steps_from_proto": { "total": 17.292532189999946, "count": 9138, "is_parallel": true, "self": 3.356284920000519, "children": { "_process_rank_one_or_two_observation": { "total": 13.936247269999427, "count": 91380, "is_parallel": true, "self": 13.936247269999427 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00034299800000781033, "count": 1, "self": 0.00034299800000781033, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 238.38779213199737, "count": 216031, "is_parallel": true, "self": 4.960322920997271, "children": { "process_trajectory": { "total": 131.30731688700004, "count": 216031, "is_parallel": true, "self": 130.36027705900003, "children": { "RLTrainer._checkpoint": { "total": 0.9470398280000154, "count": 2, "is_parallel": true, "self": 0.9470398280000154 } } }, "_update_policy": { "total": 102.12015232400006, "count": 45, "is_parallel": true, "self": 37.010234576002745, "children": { "TorchPPOOptimizer.update": { "total": 65.10991774799732, "count": 2289, "is_parallel": true, "self": 65.10991774799732 } } } } } } } } }, "TrainerController._save_models": { "total": 0.22767663799999127, "count": 1, "self": 0.0012152099999980237, "children": { "RLTrainer._checkpoint": { "total": 0.22646142799999325, "count": 1, "self": 0.22646142799999325 } } } } } } }