{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.9762190580368042, "min": 0.9755625128746033, "max": 2.8792080879211426, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 9320.939453125, "min": 9320.939453125, "max": 29485.970703125, "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": 12.823467254638672, "min": 0.28154247999191284, "max": 12.823467254638672, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2500.576171875, "min": 54.619239807128906, "max": 2591.286865234375, "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": 0.0720371722924813, "min": 0.06407953511887028, "max": 0.07371681388073793, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2881486891699252, "min": 0.2697323913778425, "max": 0.36671964720410277, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.21963737905025482, "min": 0.1026726399454763, "max": 0.3016506288127572, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.8785495162010193, "min": 0.4106905597819052, "max": 1.3419327104792875, "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": 25.204545454545453, "min": 3.0454545454545454, "max": 25.345454545454544, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1109.0, "min": 134.0, "max": 1394.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.204545454545453, "min": 3.0454545454545454, "max": 25.345454545454544, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1109.0, "min": 134.0, "max": 1394.0, "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": "1713144784", "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 --resume", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.2.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1713145214" }, "total": 430.1065551070001, "count": 1, "self": 0.4352247830001943, "children": { "run_training.setup": { "total": 0.051813315999879705, "count": 1, "self": 0.051813315999879705 }, "TrainerController.start_learning": { "total": 429.619517008, "count": 1, "self": 0.5234175960317771, "children": { "TrainerController._reset_env": { "total": 1.9357260090000636, "count": 1, "self": 1.9357260090000636 }, "TrainerController.advance": { "total": 427.0710663899681, "count": 18199, "self": 0.250295360977816, "children": { "env_step": { "total": 426.8207710289903, "count": 18199, "self": 272.7054329159773, "children": { "SubprocessEnvManager._take_step": { "total": 153.8506171009908, "count": 18199, "self": 1.4067258389686685, "children": { "TorchPolicy.evaluate": { "total": 152.44389126202213, "count": 18199, "self": 152.44389126202213 } } }, "workers": { "total": 0.26472101202216436, "count": 18199, "self": 0.0, "children": { "worker_root": { "total": 428.52180088099794, "count": 18199, "is_parallel": true, "self": 215.78107422199082, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0021773650000795897, "count": 1, "is_parallel": true, "self": 0.0006145360002847156, "children": { "_process_rank_one_or_two_observation": { "total": 0.001562828999794874, "count": 10, "is_parallel": true, "self": 0.001562828999794874 } } }, "UnityEnvironment.step": { "total": 0.037762431999908586, "count": 1, "is_parallel": true, "self": 0.0006618439997509995, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004125340001337463, "count": 1, "is_parallel": true, "self": 0.0004125340001337463 }, "communicator.exchange": { "total": 0.03474637299996175, "count": 1, "is_parallel": true, "self": 0.03474637299996175 }, "steps_from_proto": { "total": 0.0019416810000620899, "count": 1, "is_parallel": true, "self": 0.00036929600082658, "children": { "_process_rank_one_or_two_observation": { "total": 0.00157238499923551, "count": 10, "is_parallel": true, "self": 0.00157238499923551 } } } } } } }, "UnityEnvironment.step": { "total": 212.74072665900712, "count": 18198, "is_parallel": true, "self": 9.94486589698181, "children": { "UnityEnvironment._generate_step_input": { "total": 5.1811700920452495, "count": 18198, "is_parallel": true, "self": 5.1811700920452495 }, "communicator.exchange": { "total": 165.21308734798095, "count": 18198, "is_parallel": true, "self": 165.21308734798095 }, "steps_from_proto": { "total": 32.40160332199912, "count": 18198, "is_parallel": true, "self": 6.003392198945221, "children": { "_process_rank_one_or_two_observation": { "total": 26.398211123053898, "count": 181980, "is_parallel": true, "self": 26.398211123053898 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00018660700015971088, "count": 1, "self": 0.00018660700015971088, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 421.5347157050387, "count": 661566, "is_parallel": true, "self": 13.932437474222752, "children": { "process_trajectory": { "total": 232.94877017981617, "count": 661566, "is_parallel": true, "self": 232.1817329988162, "children": { "RLTrainer._checkpoint": { "total": 0.7670371809999779, "count": 4, "is_parallel": true, "self": 0.7670371809999779 } } }, "_update_policy": { "total": 174.6535080509998, "count": 90, "is_parallel": true, "self": 49.58315617201333, "children": { "TorchPPOOptimizer.update": { "total": 125.07035187898646, "count": 4587, "is_parallel": true, "self": 125.07035187898646 } } } } } } } } }, "TrainerController._save_models": { "total": 0.08912040599989268, "count": 1, "self": 0.0011585830002331932, "children": { "RLTrainer._checkpoint": { "total": 0.08796182299965949, "count": 1, "self": 0.08796182299965949 } } } } } } }