{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 2.86368465423584, "min": 2.86368465423584, "max": 2.8896350860595703, "count": 70 }, "SnowballTarget.Policy.Entropy.sum": { "value": 29452.99609375, "min": 27148.046875, "max": 29764.734375, "count": 70 }, "SnowballTarget.Step.mean": { "value": 899968.0, "min": 209936.0, "max": 899968.0, "count": 70 }, "SnowballTarget.Step.sum": { "value": 899968.0, "min": 209936.0, "max": 899968.0, "count": 70 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": { "value": 0.20816949009895325, "min": 0.13810323178768158, "max": 0.22446715831756592, "count": 70 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 42.466575622558594, "min": 26.930130004882812, "max": 44.093170166015625, "count": 70 }, "SnowballTarget.Environment.EpisodeLength.mean": { "value": 199.0, "min": 199.0, "max": 199.0, "count": 70 }, "SnowballTarget.Environment.EpisodeLength.sum": { "value": 10945.0, "min": 8756.0, "max": 10945.0, "count": 70 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.07152454630243786, "min": 0.06032311512236072, "max": 0.07438520623832859, "count": 70 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.3576227315121893, "min": 0.2412924604894429, "max": 0.37192603119164297, "count": 70 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.05462366772048614, "min": 0.035928833608826, "max": 0.06355765520357617, "count": 70 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.2731183386024307, "min": 0.143715334435304, "max": 0.3177882760178809, "count": 70 }, "SnowballTarget.Policy.LearningRate.mean": { "value": 1.6019469333333316e-08, "min": 1.6019469333333316e-08, "max": 2.3149428360000004e-06, "count": 70 }, "SnowballTarget.Policy.LearningRate.sum": { "value": 8.009734666666658e-08, "min": 8.009734666666658e-08, "max": 1.1409719679999999e-05, "count": 70 }, "SnowballTarget.Policy.Epsilon.mean": { "value": 0.10053066666666668, "min": 0.10053066666666668, "max": 0.17716400000000002, "count": 70 }, "SnowballTarget.Policy.Epsilon.sum": { "value": 0.5026533333333334, "min": 0.40652266666666664, "max": 0.8803200000000001, "count": 70 }, "SnowballTarget.Policy.Beta.mean": { "value": 3.648026666666663e-05, "min": 3.648026666666663e-05, "max": 0.0038604836000000003, "count": 70 }, "SnowballTarget.Policy.Beta.sum": { "value": 0.00018240133333333316, "min": 0.00018240133333333316, "max": 0.019027968, "count": 70 }, "SnowballTarget.Environment.CumulativeReward.mean": { "value": 4.181818181818182, "min": 2.6818181818181817, "max": 5.054545454545455, "count": 70 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 230.0, "min": 118.0, "max": 278.0, "count": 70 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 4.181818181818182, "min": 2.6818181818181817, "max": 5.054545454545455, "count": 70 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 230.0, "min": 118.0, "max": 278.0, "count": 70 }, "SnowballTarget.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 70 }, "SnowballTarget.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 70 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1691789716", "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 --resume", "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": "1691791543" }, "total": 1827.0801377919997, "count": 1, "self": 0.4342306569988068, "children": { "run_training.setup": { "total": 0.06550851800056989, "count": 1, "self": 0.06550851800056989 }, "TrainerController.start_learning": { "total": 1826.5803986170004, "count": 1, "self": 2.248516801940241, "children": { "TrainerController._reset_env": { "total": 5.191542315999868, "count": 1, "self": 5.191542315999868 }, "TrainerController.advance": { "total": 1818.99052772506, "count": 63674, "self": 1.1208480139430321, "children": { "env_step": { "total": 1817.869679711117, "count": 63674, "self": 1327.5544179470871, "children": { "SubprocessEnvManager._take_step": { "total": 489.137316015901, "count": 63674, "self": 6.948076970018519, "children": { "TorchPolicy.evaluate": { "total": 482.18923904588246, "count": 63674, "self": 482.18923904588246 } } }, "workers": { "total": 1.1779457481288773, "count": 63674, "self": 0.0, "children": { "worker_root": { "total": 1820.362834624936, "count": 63674, "is_parallel": true, "self": 848.1124487679917, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0029990170005476102, "count": 1, "is_parallel": true, "self": 0.0006937140014997567, "children": { "_process_rank_one_or_two_observation": { "total": 0.0023053029990478535, "count": 10, "is_parallel": true, "self": 0.0023053029990478535 } } }, "UnityEnvironment.step": { "total": 0.04061070199986716, "count": 1, "is_parallel": true, "self": 0.0007622849998369929, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004748560004372848, "count": 1, "is_parallel": true, "self": 0.0004748560004372848 }, "communicator.exchange": { "total": 0.03663902199969016, "count": 1, "is_parallel": true, "self": 0.03663902199969016 }, "steps_from_proto": { "total": 0.0027345389999027248, "count": 1, "is_parallel": true, "self": 0.0007086479990903172, "children": { "_process_rank_one_or_two_observation": { "total": 0.0020258910008124076, "count": 10, "is_parallel": true, "self": 0.0020258910008124076 } } } } } } }, "UnityEnvironment.step": { "total": 972.2503858569444, "count": 63673, "is_parallel": true, "self": 40.23167197309613, "children": { "UnityEnvironment._generate_step_input": { "total": 20.783129467002254, "count": 63673, "is_parallel": true, "self": 20.783129467002254 }, "communicator.exchange": { "total": 766.8359551070089, "count": 63673, "is_parallel": true, "self": 766.8359551070089 }, "steps_from_proto": { "total": 144.3996293098371, "count": 63673, "is_parallel": true, "self": 27.111744930974965, "children": { "_process_rank_one_or_two_observation": { "total": 117.28788437886215, "count": 636730, "is_parallel": true, "self": 117.28788437886215 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.0002277430003232439, "count": 1, "self": 0.0002277430003232439, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 1803.0946918022964, "count": 1680449, "is_parallel": true, "self": 39.56978513161266, "children": { "process_trajectory": { "total": 987.1128867326761, "count": 1680449, "is_parallel": true, "self": 981.707200308676, "children": { "RLTrainer._checkpoint": { "total": 5.405686424000123, "count": 14, "is_parallel": true, "self": 5.405686424000123 } } }, "_update_policy": { "total": 776.4120199380077, "count": 318, "is_parallel": true, "self": 311.6997565030133, "children": { "TorchPPOOptimizer.update": { "total": 464.7122634349944, "count": 16212, "is_parallel": true, "self": 464.7122634349944 } } } } } } } } }, "TrainerController._save_models": { "total": 0.14958403099990392, "count": 1, "self": 0.0010529000001042732, "children": { "RLTrainer._checkpoint": { "total": 0.14853113099979964, "count": 1, "self": 0.14853113099979964 } } } } } } }