{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.9108371138572693, "min": 0.9108371138572693, "max": 2.878413438796997, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 8716.7109375, "min": 8716.7109375, "max": 29541.15625, "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": 13.015144348144531, "min": 0.14040417969226837, "max": 13.015144348144531, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2537.953125, "min": 27.23841094970703, "max": 2646.31787109375, "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": 0.0641491334861391, "min": 0.06143837441763311, "max": 0.07340202864981941, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2565965339445564, "min": 0.24575349767053245, "max": 0.36074423822648505, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.20640891005157255, "min": 0.11867487373962707, "max": 0.3025228931185077, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.8256356402062902, "min": 0.4746994949585083, "max": 1.432960453278878, "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": 25.5, "min": 3.0681818181818183, "max": 25.795454545454547, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1122.0, "min": 135.0, "max": 1396.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.5, "min": 3.0681818181818183, "max": 25.795454545454547, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1122.0, "min": 135.0, "max": 1396.0, "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": "1691752250", "python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [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": "0.31.0.dev0", "mlagents_envs_version": "0.31.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.11.0+cu102", "numpy_version": "1.21.2", "end_time_seconds": "1691752868" }, "total": 617.7437533359999, "count": 1, "self": 0.538676531999954, "children": { "run_training.setup": { "total": 0.05699502599998141, "count": 1, "self": 0.05699502599998141 }, "TrainerController.start_learning": { "total": 617.148081778, "count": 1, "self": 0.849781381018829, "children": { "TrainerController._reset_env": { "total": 1.5485823679998703, "count": 1, "self": 1.5485823679998703 }, "TrainerController.advance": { "total": 614.5897424229815, "count": 18203, "self": 0.45222604796276755, "children": { "env_step": { "total": 614.1375163750188, "count": 18203, "self": 498.40031808601293, "children": { "SubprocessEnvManager._take_step": { "total": 115.30415713699608, "count": 18203, "self": 2.7712979960062967, "children": { "TorchPolicy.evaluate": { "total": 112.53285914098979, "count": 18203, "self": 112.53285914098979 } } }, "workers": { "total": 0.4330411520097641, "count": 18203, "self": 0.0, "children": { "worker_root": { "total": 614.6872063030158, "count": 18203, "is_parallel": true, "self": 270.1819094930157, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0071942130000479665, "count": 1, "is_parallel": true, "self": 0.004989089000446256, "children": { "_process_rank_one_or_two_observation": { "total": 0.0022051239996017102, "count": 10, "is_parallel": true, "self": 0.0022051239996017102 } } }, "UnityEnvironment.step": { "total": 0.04769815000008748, "count": 1, "is_parallel": true, "self": 0.0009000320001177897, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00035770999988926633, "count": 1, "is_parallel": true, "self": 0.00035770999988926633 }, "communicator.exchange": { "total": 0.04355422399999043, "count": 1, "is_parallel": true, "self": 0.04355422399999043 }, "steps_from_proto": { "total": 0.0028861840000899974, "count": 1, "is_parallel": true, "self": 0.000790100999893184, "children": { "_process_rank_one_or_two_observation": { "total": 0.0020960830001968134, "count": 10, "is_parallel": true, "self": 0.0020960830001968134 } } } } } } }, "UnityEnvironment.step": { "total": 344.5052968100001, "count": 18202, "is_parallel": true, "self": 15.046259061988394, "children": { "UnityEnvironment._generate_step_input": { "total": 7.830843568012142, "count": 18202, "is_parallel": true, "self": 7.830843568012142 }, "communicator.exchange": { "total": 271.65803912199294, "count": 18202, "is_parallel": true, "self": 271.65803912199294 }, "steps_from_proto": { "total": 49.97015505800664, "count": 18202, "is_parallel": true, "self": 9.546942870983912, "children": { "_process_rank_one_or_two_observation": { "total": 40.42321218702273, "count": 182020, "is_parallel": true, "self": 40.42321218702273 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00016704399990885577, "count": 1, "self": 0.00016704399990885577, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 609.1534694799527, "count": 605416, "is_parallel": true, "self": 14.517985931959629, "children": { "process_trajectory": { "total": 328.83458938799345, "count": 605416, "is_parallel": true, "self": 327.31650768899317, "children": { "RLTrainer._checkpoint": { "total": 1.5180816990002768, "count": 4, "is_parallel": true, "self": 1.5180816990002768 } } }, "_update_policy": { "total": 265.80089415999964, "count": 90, "is_parallel": true, "self": 94.41906200299991, "children": { "TorchPPOOptimizer.update": { "total": 171.38183215699974, "count": 4587, "is_parallel": true, "self": 171.38183215699974 } } } } } } } } }, "TrainerController._save_models": { "total": 0.15980856199985283, "count": 1, "self": 0.0010996799999247742, "children": { "RLTrainer._checkpoint": { "total": 0.15870888199992805, "count": 1, "self": 0.15870888199992805 } } } } } } }