{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.8810881972312927, "min": 0.8810881972312927, "max": 2.8669867515563965, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 8461.08984375, "min": 8461.08984375, "max": 29392.34765625, "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": 12.680058479309082, "min": 0.3252701461315155, "max": 12.680058479309082, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2472.611328125, "min": 63.10240936279297, "max": 2562.2216796875, "count": 20 }, "SnowballTarget.Environment.EpisodeLength.mean": { "value": 199.0, "min": 199.0, "max": 199.0, "count": 20 }, "SnowballTarget.Environment.EpisodeLength.sum": { "value": 10945.0, "min": 8756.0, "max": 10945.0, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.06581442098139828, "min": 0.06162149602143259, "max": 0.07700291397871778, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2632576839255931, "min": 0.2479495871682279, "max": 0.35525800241785144, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.2101420859495799, "min": 0.11770065980917757, "max": 0.2884563007191116, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.8405683437983196, "min": 0.4708026392367103, "max": 1.442281503595558, "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": 25.09090909090909, "min": 3.7954545454545454, "max": 25.09090909090909, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1104.0, "min": 167.0, "max": 1375.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.09090909090909, "min": 3.7954545454545454, "max": 25.09090909090909, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1104.0, "min": 167.0, "max": 1375.0, "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": "1742237574", "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics --force", "mlagents_version": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.6.0+cu124", "numpy_version": "1.23.5", "end_time_seconds": "1742238167" }, "total": 592.978670495, "count": 1, "self": 0.8913174000000481, "children": { "run_training.setup": { "total": 0.03523441400000138, "count": 1, "self": 0.03523441400000138 }, "TrainerController.start_learning": { "total": 592.0521186809999, "count": 1, "self": 0.9451072699997667, "children": { "TrainerController._reset_env": { "total": 3.6813201200000094, "count": 1, "self": 3.6813201200000094 }, "TrainerController.advance": { "total": 587.2775506320003, "count": 18211, "self": 0.42289937300529346, "children": { "env_step": { "total": 586.854651258995, "count": 18211, "self": 455.25796333098805, "children": { "SubprocessEnvManager._take_step": { "total": 131.1858955340046, "count": 18211, "self": 2.2511695720015723, "children": { "TorchPolicy.evaluate": { "total": 128.93472596200303, "count": 18211, "self": 128.93472596200303 } } }, "workers": { "total": 0.41079239400232836, "count": 18211, "self": 0.0, "children": { "worker_root": { "total": 590.1094837979929, "count": 18211, "is_parallel": true, "self": 274.4720231189959, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.008646337999948628, "count": 1, "is_parallel": true, "self": 0.005087539999976798, "children": { "_process_rank_one_or_two_observation": { "total": 0.00355879799997183, "count": 10, "is_parallel": true, "self": 0.00355879799997183 } } }, "UnityEnvironment.step": { "total": 0.04952709599996297, "count": 1, "is_parallel": true, "self": 0.0007951359999651686, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005109330000436785, "count": 1, "is_parallel": true, "self": 0.0005109330000436785 }, "communicator.exchange": { "total": 0.04587914199998977, "count": 1, "is_parallel": true, "self": 0.04587914199998977 }, "steps_from_proto": { "total": 0.00234188499996435, "count": 1, "is_parallel": true, "self": 0.0004708170000071732, "children": { "_process_rank_one_or_two_observation": { "total": 0.0018710679999571767, "count": 10, "is_parallel": true, "self": 0.0018710679999571767 } } } } } } }, "UnityEnvironment.step": { "total": 315.637460678997, "count": 18210, "is_parallel": true, "self": 14.419870947010281, "children": { "UnityEnvironment._generate_step_input": { "total": 7.564104602985992, "count": 18210, "is_parallel": true, "self": 7.564104602985992 }, "communicator.exchange": { "total": 249.67994862000347, "count": 18210, "is_parallel": true, "self": 249.67994862000347 }, "steps_from_proto": { "total": 43.973536508997256, "count": 18210, "is_parallel": true, "self": 8.873659214033296, "children": { "_process_rank_one_or_two_observation": { "total": 35.09987729496396, "count": 182100, "is_parallel": true, "self": 35.09987729496396 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00023752599986437417, "count": 1, "self": 0.00023752599986437417, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 580.5204539630404, "count": 774043, "is_parallel": true, "self": 16.81976365401374, "children": { "process_trajectory": { "total": 305.07259707702667, "count": 774043, "is_parallel": true, "self": 303.7211782590267, "children": { "RLTrainer._checkpoint": { "total": 1.3514188179999564, "count": 4, "is_parallel": true, "self": 1.3514188179999564 } } }, "_update_policy": { "total": 258.628093232, "count": 90, "is_parallel": true, "self": 76.58258026699349, "children": { "TorchPPOOptimizer.update": { "total": 182.04551296500654, "count": 4587, "is_parallel": true, "self": 182.04551296500654 } } } } } } } } }, "TrainerController._save_models": { "total": 0.1479031329999998, "count": 1, "self": 0.0018557490000148391, "children": { "RLTrainer._checkpoint": { "total": 0.14604738399998496, "count": 1, "self": 0.14604738399998496 } } } } } } }