{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.8985287547111511, "min": 0.8797258138656616, "max": 2.854275703430176, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 8579.15234375, "min": 8579.15234375, "max": 29262.03515625, "count": 20 }, "SnowballTarget.Step.mean": { "value": 199984.0, "min": 9952.0, "max": 199984.0, "count": 20 }, "SnowballTarget.Step.sum": { "value": 199984.0, "min": 9952.0, "max": 199984.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": { "value": 12.868033409118652, "min": 0.3897717595100403, "max": 12.868033409118652, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2509.2666015625, "min": 75.61572265625, "max": 2611.51904296875, "count": 20 }, "SnowballTarget.Environment.EpisodeLength.mean": { "value": 199.0, "min": 199.0, "max": 199.0, "count": 20 }, "SnowballTarget.Environment.EpisodeLength.sum": { "value": 8756.0, "min": 8756.0, "max": 10945.0, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.06541426751062086, "min": 0.06292996812730516, "max": 0.07807722912705276, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.26165707004248345, "min": 0.2599613550375901, "max": 0.3734648721162789, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.21233359439408078, "min": 0.1389858523525261, "max": 0.2898073337826074, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.8493343775763231, "min": 0.5559434094101044, "max": 1.4490366689130372, "count": 20 }, "SnowballTarget.Policy.LearningRate.mean": { "value": 8.082097306000005e-06, "min": 8.082097306000005e-06, "max": 0.000291882002706, "count": 20 }, "SnowballTarget.Policy.LearningRate.sum": { "value": 3.232838922400002e-05, "min": 3.232838922400002e-05, "max": 0.00138516003828, "count": 20 }, "SnowballTarget.Policy.Epsilon.mean": { "value": 0.10269400000000001, "min": 0.10269400000000001, "max": 0.19729400000000002, "count": 20 }, "SnowballTarget.Policy.Epsilon.sum": { "value": 0.41077600000000003, "min": 0.41077600000000003, "max": 0.96172, "count": 20 }, "SnowballTarget.Policy.Beta.mean": { "value": 0.0001444306000000001, "min": 0.0001444306000000001, "max": 0.0048649706, "count": 20 }, "SnowballTarget.Policy.Beta.sum": { "value": 0.0005777224000000004, "min": 0.0005777224000000004, "max": 0.023089828, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.mean": { "value": 25.454545454545453, "min": 3.8636363636363638, "max": 25.5, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1120.0, "min": 170.0, "max": 1393.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.454545454545453, "min": 3.8636363636363638, "max": 25.5, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1120.0, "min": 170.0, "max": 1393.0, "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": "1706708935", "python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [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=SnowballTarget11 --no-graphics", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.2.0+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1706709414" }, "total": 479.590365735, "count": 1, "self": 0.4439867510000113, "children": { "run_training.setup": { "total": 0.05832370500002071, "count": 1, "self": 0.05832370500002071 }, "TrainerController.start_learning": { "total": 479.08805527899995, "count": 1, "self": 0.5992673630171339, "children": { "TrainerController._reset_env": { "total": 3.4608356030000778, "count": 1, "self": 3.4608356030000778 }, "TrainerController.advance": { "total": 474.9304949529828, "count": 18199, "self": 0.29689831897417207, "children": { "env_step": { "total": 474.63359663400865, "count": 18199, "self": 308.46675962504946, "children": { "SubprocessEnvManager._take_step": { "total": 165.86239487998, "count": 18199, "self": 1.5786597369833544, "children": { "TorchPolicy.evaluate": { "total": 164.28373514299665, "count": 18199, "self": 164.28373514299665 } } }, "workers": { "total": 0.3044421289791899, "count": 18199, "self": 0.0, "children": { "worker_root": { "total": 477.80183805397974, "count": 18199, "is_parallel": true, "self": 239.2384881789692, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.00524941700018644, "count": 1, "is_parallel": true, "self": 0.0035291610004151153, "children": { "_process_rank_one_or_two_observation": { "total": 0.0017202559997713252, "count": 10, "is_parallel": true, "self": 0.0017202559997713252 } } }, "UnityEnvironment.step": { "total": 0.041573670999923706, "count": 1, "is_parallel": true, "self": 0.0007353349999448255, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0003919480000149633, "count": 1, "is_parallel": true, "self": 0.0003919480000149633 }, "communicator.exchange": { "total": 0.03820433200007756, "count": 1, "is_parallel": true, "self": 0.03820433200007756 }, "steps_from_proto": { "total": 0.002242055999886361, "count": 1, "is_parallel": true, "self": 0.00043376999974498176, "children": { "_process_rank_one_or_two_observation": { "total": 0.0018082860001413792, "count": 10, "is_parallel": true, "self": 0.0018082860001413792 } } } } } } }, "UnityEnvironment.step": { "total": 238.56334987501054, "count": 18198, "is_parallel": true, "self": 11.06278494002413, "children": { "UnityEnvironment._generate_step_input": { "total": 5.589199743013523, "count": 18198, "is_parallel": true, "self": 5.589199743013523 }, "communicator.exchange": { "total": 185.5602110319985, "count": 18198, "is_parallel": true, "self": 185.5602110319985 }, "steps_from_proto": { "total": 36.351154159974385, "count": 18198, "is_parallel": true, "self": 6.733862152003212, "children": { "_process_rank_one_or_two_observation": { "total": 29.617292007971173, "count": 181980, "is_parallel": true, "self": 29.617292007971173 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00017663499988884723, "count": 1, "self": 0.00017663499988884723, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 468.8638211619898, "count": 706041, "is_parallel": true, "self": 16.400347642005954, "children": { "process_trajectory": { "total": 260.0813492669831, "count": 706041, "is_parallel": true, "self": 259.32911807198275, "children": { "RLTrainer._checkpoint": { "total": 0.7522311950003768, "count": 4, "is_parallel": true, "self": 0.7522311950003768 } } }, "_update_policy": { "total": 192.3821242530007, "count": 90, "is_parallel": true, "self": 57.86339078400101, "children": { "TorchPPOOptimizer.update": { "total": 134.5187334689997, "count": 4584, "is_parallel": true, "self": 134.5187334689997 } } } } } } } } }, "TrainerController._save_models": { "total": 0.09728072500001872, "count": 1, "self": 0.001361193000093408, "children": { "RLTrainer._checkpoint": { "total": 0.09591953199992531, "count": 1, "self": 0.09591953199992531 } } } } } } }