{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.9730653166770935, "min": 0.9730653166770935, "max": 2.8372488021850586, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 9248.0126953125, "min": 9248.0126953125, "max": 28962.63671875, "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": 12.147684097290039, "min": 0.5183202028274536, "max": 12.147684097290039, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2368.79833984375, "min": 100.55412292480469, "max": 2468.6396484375, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.07598898437059046, "min": 0.06306512795109645, "max": 0.0798003033684069, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.3039559374823618, "min": 0.2522605118043858, "max": 0.3990015168420345, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.18809393362379542, "min": 0.1294777403886923, "max": 0.2813445357131023, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.7523757344951817, "min": 0.5179109615547692, "max": 1.4067226785655116, "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.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.Environment.CumulativeReward.mean": { "value": 24.0, "min": 3.590909090909091, "max": 24.0, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1056.0, "min": 158.0, "max": 1314.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 24.0, "min": 3.590909090909091, "max": 24.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1056.0, "min": 158.0, "max": 1314.0, "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": "1748851445", "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", "mlagents_version": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.7.0+cu126", "numpy_version": "1.23.5", "end_time_seconds": "1748851870" }, "total": 424.547065288, "count": 1, "self": 0.6526978379999946, "children": { "run_training.setup": { "total": 0.02307603899998867, "count": 1, "self": 0.02307603899998867 }, "TrainerController.start_learning": { "total": 423.871291411, "count": 1, "self": 0.33245968499409173, "children": { "TrainerController._reset_env": { "total": 3.6562808879999693, "count": 1, "self": 3.6562808879999693 }, "TrainerController.advance": { "total": 419.7454503220059, "count": 18192, "self": 0.3636107680057421, "children": { "env_step": { "total": 299.2737166230115, "count": 18192, "self": 229.04904405201364, "children": { "SubprocessEnvManager._take_step": { "total": 70.02868512300199, "count": 18192, "self": 1.2236360059977187, "children": { "TorchPolicy.evaluate": { "total": 68.80504911700427, "count": 18192, "self": 68.80504911700427 } } }, "workers": { "total": 0.19598744799588985, "count": 18192, "self": 0.0, "children": { "worker_root": { "total": 422.2821207400126, "count": 18192, "is_parallel": true, "self": 221.2993273040106, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005363579000004393, "count": 1, "is_parallel": true, "self": 0.0038107520003904938, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015528269996138988, "count": 10, "is_parallel": true, "self": 0.0015528269996138988 } } }, "UnityEnvironment.step": { "total": 0.06583315600005335, "count": 1, "is_parallel": true, "self": 0.0006103150000171809, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00041200800001206517, "count": 1, "is_parallel": true, "self": 0.00041200800001206517 }, "communicator.exchange": { "total": 0.059522095000033914, "count": 1, "is_parallel": true, "self": 0.059522095000033914 }, "steps_from_proto": { "total": 0.0052887379999901896, "count": 1, "is_parallel": true, "self": 0.00042532600002687104, "children": { "_process_rank_one_or_two_observation": { "total": 0.0048634119999633185, "count": 10, "is_parallel": true, "self": 0.0048634119999633185 } } } } } } }, "UnityEnvironment.step": { "total": 200.982793436002, "count": 18191, "is_parallel": true, "self": 9.819533180006601, "children": { "UnityEnvironment._generate_step_input": { "total": 5.462072520989409, "count": 18191, "is_parallel": true, "self": 5.462072520989409 }, "communicator.exchange": { "total": 153.94034799100393, "count": 18191, "is_parallel": true, "self": 153.94034799100393 }, "steps_from_proto": { "total": 31.760839744002055, "count": 18191, "is_parallel": true, "self": 5.704065858982631, "children": { "_process_rank_one_or_two_observation": { "total": 26.056773885019425, "count": 181910, "is_parallel": true, "self": 26.056773885019425 } } } } } } } } } } }, "trainer_advance": { "total": 120.10812293098866, "count": 18192, "self": 0.4143354909933805, "children": { "process_trajectory": { "total": 27.500290366995614, "count": 18192, "self": 27.04062750399555, "children": { "RLTrainer._checkpoint": { "total": 0.4596628630000623, "count": 4, "self": 0.4596628630000623 } } }, "_update_policy": { "total": 92.19349707299966, "count": 90, "self": 37.3568479789991, "children": { "TorchPPOOptimizer.update": { "total": 54.83664909400056, "count": 4587, "self": 54.83664909400056 } } } } } } }, "trainer_threads": { "total": 1.13999999484804e-06, "count": 1, "self": 1.13999999484804e-06 }, "TrainerController._save_models": { "total": 0.1370993760000374, "count": 1, "self": 0.001098900999977559, "children": { "RLTrainer._checkpoint": { "total": 0.13600047500005985, "count": 1, "self": 0.13600047500005985 } } } } } } }