{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.9345560073852539, "min": 0.9320113062858582, "max": 2.8662009239196777, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 8923.140625, "min": 8923.140625, "max": 29352.763671875, "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": 12.829136848449707, "min": 0.46453410387039185, "max": 12.829136848449707, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2501.681640625, "min": 90.11961364746094, "max": 2613.8994140625, "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": 0.07228338971464265, "min": 0.06481362974131935, "max": 0.07639430910043588, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2891335588585706, "min": 0.2596489386330587, "max": 0.370819503661301, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.18370835442899489, "min": 0.1305065834757817, "max": 0.29838238941395984, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.7348334177159795, "min": 0.5220263339031268, "max": 1.3704651153701195, "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": 25.0, "min": 3.75, "max": 25.454545454545453, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1100.0, "min": 165.0, "max": 1400.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.0, "min": 3.75, "max": 25.454545454545453, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1100.0, "min": 165.0, "max": 1400.0, "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": "1719226607", "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=SnowballTarget1 --no-graphics", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.3.0+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1719227059" }, "total": 452.27630015700004, "count": 1, "self": 0.4967265689999749, "children": { "run_training.setup": { "total": 0.05602550399999018, "count": 1, "self": 0.05602550399999018 }, "TrainerController.start_learning": { "total": 451.7235480840001, "count": 1, "self": 0.5898095190126469, "children": { "TrainerController._reset_env": { "total": 3.5386379250001028, "count": 1, "self": 3.5386379250001028 }, "TrainerController.advance": { "total": 447.4984455739873, "count": 18201, "self": 0.2906601549776724, "children": { "env_step": { "total": 447.2077854190096, "count": 18201, "self": 290.66108184903, "children": { "SubprocessEnvManager._take_step": { "total": 156.25982882399273, "count": 18201, "self": 1.4689840540041814, "children": { "TorchPolicy.evaluate": { "total": 154.79084476998855, "count": 18201, "self": 154.79084476998855 } } }, "workers": { "total": 0.2868747459868928, "count": 18201, "self": 0.0, "children": { "worker_root": { "total": 450.41503036299355, "count": 18201, "is_parallel": true, "self": 227.4785978299966, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.007283013000005667, "count": 1, "is_parallel": true, "self": 0.0057436840002083045, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015393289997973625, "count": 10, "is_parallel": true, "self": 0.0015393289997973625 } } }, "UnityEnvironment.step": { "total": 0.03743933600003402, "count": 1, "is_parallel": true, "self": 0.0006848920000948056, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004159349999781625, "count": 1, "is_parallel": true, "self": 0.0004159349999781625 }, "communicator.exchange": { "total": 0.03434735600001204, "count": 1, "is_parallel": true, "self": 0.03434735600001204 }, "steps_from_proto": { "total": 0.0019911529999490085, "count": 1, "is_parallel": true, "self": 0.00038361899976280256, "children": { "_process_rank_one_or_two_observation": { "total": 0.001607534000186206, "count": 10, "is_parallel": true, "self": 0.001607534000186206 } } } } } } }, "UnityEnvironment.step": { "total": 222.93643253299695, "count": 18200, "is_parallel": true, "self": 10.07367633301692, "children": { "UnityEnvironment._generate_step_input": { "total": 5.249282015997437, "count": 18200, "is_parallel": true, "self": 5.249282015997437 }, "communicator.exchange": { "total": 174.5612100449904, "count": 18200, "is_parallel": true, "self": 174.5612100449904 }, "steps_from_proto": { "total": 33.0522641389922, "count": 18200, "is_parallel": true, "self": 6.264541963968782, "children": { "_process_rank_one_or_two_observation": { "total": 26.78772217502342, "count": 182000, "is_parallel": true, "self": 26.78772217502342 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00016441100001429731, "count": 1, "self": 0.00016441100001429731, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 441.93327114394117, "count": 680852, "is_parallel": true, "self": 13.944358725947836, "children": { "process_trajectory": { "total": 243.84902410499365, "count": 680852, "is_parallel": true, "self": 242.76655448799363, "children": { "RLTrainer._checkpoint": { "total": 1.0824696170000152, "count": 4, "is_parallel": true, "self": 1.0824696170000152 } } }, "_update_policy": { "total": 184.1398883129997, "count": 90, "is_parallel": true, "self": 56.48678743899825, "children": { "TorchPPOOptimizer.update": { "total": 127.65310087400144, "count": 4584, "is_parallel": true, "self": 127.65310087400144 } } } } } } } } }, "TrainerController._save_models": { "total": 0.09649065500002507, "count": 1, "self": 0.0009906479999699513, "children": { "RLTrainer._checkpoint": { "total": 0.09550000700005512, "count": 1, "self": 0.09550000700005512 } } } } } } }