{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.7236392498016357, "min": 0.6671388149261475, "max": 2.8741025924682617, "count": 100 }, "SnowballTarget.Policy.Entropy.sum": { "value": 6901.34765625, "min": 6621.30419921875, "max": 29450.615234375, "count": 100 }, "SnowballTarget.Step.mean": { "value": 999952.0, "min": 9952.0, "max": 999952.0, "count": 100 }, "SnowballTarget.Step.sum": { "value": 999952.0, "min": 9952.0, "max": 999952.0, "count": 100 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": { "value": 13.914094924926758, "min": 0.20598557591438293, "max": 13.997663497924805, "count": 100 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2713.24853515625, "min": 39.96120071411133, "max": 2864.0966796875, "count": 100 }, "SnowballTarget.Environment.EpisodeLength.mean": { "value": 199.0, "min": 199.0, "max": 199.0, "count": 100 }, "SnowballTarget.Environment.EpisodeLength.sum": { "value": 8756.0, "min": 8756.0, "max": 10945.0, "count": 100 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.035934752648245194, "min": 0.024169132694927008, "max": 0.04102505868650041, "count": 100 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.14373901059298078, "min": 0.09667653077970803, "max": 0.19341183612899235, "count": 100 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.19834377275158965, "min": 0.10267827349404494, "max": 0.3755148438115915, "count": 100 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.7933750910063586, "min": 0.4107130939761798, "max": 1.6518405750393867, "count": 100 }, "SnowballTarget.Policy.LearningRate.mean": { "value": 1.3764995412000023e-06, "min": 1.3764995412000023e-06, "max": 0.00029837640054119997, "count": 100 }, "SnowballTarget.Policy.LearningRate.sum": { "value": 5.505998164800009e-06, "min": 5.505998164800009e-06, "max": 0.001477032007656, "count": 100 }, "SnowballTarget.Policy.Epsilon.mean": { "value": 0.10045880000000001, "min": 0.10045880000000001, "max": 0.19945880000000002, "count": 100 }, "SnowballTarget.Policy.Epsilon.sum": { "value": 0.40183520000000006, "min": 0.40183520000000006, "max": 0.992344, "count": 100 }, "SnowballTarget.Policy.Beta.mean": { "value": 3.289412000000005e-05, "min": 3.289412000000005e-05, "max": 0.00497299412, "count": 100 }, "SnowballTarget.Policy.Beta.sum": { "value": 0.0001315764800000002, "min": 0.0001315764800000002, "max": 0.0246179656, "count": 100 }, "SnowballTarget.Environment.CumulativeReward.mean": { "value": 26.68888888888889, "min": 2.6363636363636362, "max": 27.654545454545456, "count": 100 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1201.0, "min": 116.0, "max": 1521.0, "count": 100 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 26.68888888888889, "min": 2.6363636363636362, "max": 27.654545454545456, "count": 100 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1201.0, "min": 116.0, "max": 1521.0, "count": 100 }, "SnowballTarget.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 100 }, "SnowballTarget.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 100 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1747901075", "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": "1747903666" }, "total": 2591.0808448959997, "count": 1, "self": 1.3373183019998578, "children": { "run_training.setup": { "total": 0.04386732899990875, "count": 1, "self": 0.04386732899990875 }, "TrainerController.start_learning": { "total": 2589.699659265, "count": 1, "self": 4.3409059360847095, "children": { "TrainerController._reset_env": { "total": 3.844263060000003, "count": 1, "self": 3.844263060000003 }, "TrainerController.advance": { "total": 2581.381505847915, "count": 90942, "self": 2.137206398916078, "children": { "env_step": { "total": 2579.244299448999, "count": 90942, "self": 1885.8009423379685, "children": { "SubprocessEnvManager._take_step": { "total": 691.4001852959808, "count": 90942, "self": 10.811671299006093, "children": { "TorchPolicy.evaluate": { "total": 680.5885139969747, "count": 90942, "self": 680.5885139969747 } } }, "workers": { "total": 2.0431718150495044, "count": 90942, "self": 0.0, "children": { "worker_root": { "total": 2580.490567093998, "count": 90942, "is_parallel": true, "self": 1069.2596755530203, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.006843603999982406, "count": 1, "is_parallel": true, "self": 0.004562033999945925, "children": { "_process_rank_one_or_two_observation": { "total": 0.0022815700000364814, "count": 10, "is_parallel": true, "self": 0.0022815700000364814 } } }, "UnityEnvironment.step": { "total": 0.04793558399990161, "count": 1, "is_parallel": true, "self": 0.0007180509999216156, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00045635100002527906, "count": 1, "is_parallel": true, "self": 0.00045635100002527906 }, "communicator.exchange": { "total": 0.044513626999901135, "count": 1, "is_parallel": true, "self": 0.044513626999901135 }, "steps_from_proto": { "total": 0.0022475550000535804, "count": 1, "is_parallel": true, "self": 0.00042605400017237116, "children": { "_process_rank_one_or_two_observation": { "total": 0.0018215009998812093, "count": 10, "is_parallel": true, "self": 0.0018215009998812093 } } } } } } }, "UnityEnvironment.step": { "total": 1511.2308915409776, "count": 90941, "is_parallel": true, "self": 69.50451772897077, "children": { "UnityEnvironment._generate_step_input": { "total": 36.050689971040356, "count": 90941, "is_parallel": true, "self": 36.050689971040356 }, "communicator.exchange": { "total": 1191.6192000440083, "count": 90941, "is_parallel": true, "self": 1191.6192000440083 }, "steps_from_proto": { "total": 214.0564837969581, "count": 90941, "is_parallel": true, "self": 42.65219936110793, "children": { "_process_rank_one_or_two_observation": { "total": 171.40428443585017, "count": 909410, "is_parallel": true, "self": 171.40428443585017 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00025783000000956235, "count": 1, "self": 0.00025783000000956235, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 2547.227404425341, "count": 3877453, "is_parallel": true, "self": 84.31743167719196, "children": { "process_trajectory": { "total": 1485.7807651361468, "count": 3877453, "is_parallel": true, "self": 1483.1218496941465, "children": { "RLTrainer._checkpoint": { "total": 2.6589154420004206, "count": 10, "is_parallel": true, "self": 2.6589154420004206 } } }, "_update_policy": { "total": 977.129207612002, "count": 454, "is_parallel": true, "self": 341.6394724670047, "children": { "TorchPPOOptimizer.update": { "total": 635.4897351449973, "count": 5448, "is_parallel": true, "self": 635.4897351449973 } } } } } } } } }, "TrainerController._save_models": { "total": 0.1327265909999369, "count": 1, "self": 0.0016084320000118169, "children": { "RLTrainer._checkpoint": { "total": 0.13111815899992507, "count": 1, "self": 0.13111815899992507 } } } } } } }