{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.5212552547454834, "min": 0.5212552547454834, "max": 2.823472499847412, "count": 30 }, "SnowballTarget.Policy.Entropy.sum": { "value": 5366.84423828125, "min": 5211.24267578125, "max": 28822.0078125, "count": 30 }, "SnowballTarget.Step.mean": { "value": 299968.0, "min": 9952.0, "max": 299968.0, "count": 30 }, "SnowballTarget.Step.sum": { "value": 299968.0, "min": 9952.0, "max": 299968.0, "count": 30 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": { "value": 26.778047561645508, "min": 0.4260154664516449, "max": 26.778047561645508, "count": 30 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 5462.7216796875, "min": 82.64700317382812, "max": 5477.35302734375, "count": 30 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.07018861216772004, "min": 0.06425004584764846, "max": 0.07332311038478699, "count": 30 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.3509430608386002, "min": 0.25845869857927456, "max": 0.35843144043567865, "count": 30 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.17590927585082894, "min": 0.16702564289409885, "max": 0.3398141638671651, "count": 30 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.8795463792541447, "min": 0.6681025715763954, "max": 1.6990708193358255, "count": 30 }, "SnowballTarget.Policy.LearningRate.mean": { "value": 5.288098237333332e-06, "min": 5.288098237333332e-06, "max": 0.0002945880018039999, "count": 30 }, "SnowballTarget.Policy.LearningRate.sum": { "value": 2.644049118666666e-05, "min": 2.644049118666666e-05, "max": 0.00142344002552, "count": 30 }, "SnowballTarget.Policy.Epsilon.mean": { "value": 0.10176266666666664, "min": 0.10176266666666664, "max": 0.198196, "count": 30 }, "SnowballTarget.Policy.Epsilon.sum": { "value": 0.5088133333333332, "min": 0.42025066666666666, "max": 0.9744800000000001, "count": 30 }, "SnowballTarget.Policy.Beta.mean": { "value": 4.507706666666664e-05, "min": 4.507706666666664e-05, "max": 0.0019641003999999996, "count": 30 }, "SnowballTarget.Policy.Beta.sum": { "value": 0.00022538533333333322, "min": 0.00022538533333333322, "max": 0.009492152, "count": 30 }, "SnowballTarget.Environment.EpisodeLength.mean": { "value": 199.0, "min": 199.0, "max": 199.0, "count": 30 }, "SnowballTarget.Environment.EpisodeLength.sum": { "value": 10945.0, "min": 8756.0, "max": 10945.0, "count": 30 }, "SnowballTarget.Environment.CumulativeReward.mean": { "value": 26.30909090909091, "min": 4.431818181818182, "max": 26.745454545454546, "count": 30 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1447.0, "min": 195.0, "max": 1471.0, "count": 30 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 26.30909090909091, "min": 4.431818181818182, "max": 26.745454545454546, "count": 30 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1447.0, "min": 195.0, "max": 1471.0, "count": 30 }, "SnowballTarget.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 30 }, "SnowballTarget.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 30 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1764586598", "python_version": "3.10.6 | packaged by conda-forge | (main, Aug 22 2022, 20:35:26) [GCC 10.4.0]", "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": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.8.0+cu128", "numpy_version": "1.23.5", "end_time_seconds": "1764587373" }, "total": 775.564756849, "count": 1, "self": 0.43530339799997364, "children": { "run_training.setup": { "total": 0.029861223000011705, "count": 1, "self": 0.029861223000011705 }, "TrainerController.start_learning": { "total": 775.099592228, "count": 1, "self": 0.6251697349671304, "children": { "TrainerController._reset_env": { "total": 3.1322960189999094, "count": 1, "self": 3.1322960189999094 }, "TrainerController.advance": { "total": 771.2244012730332, "count": 27328, "self": 0.6310758190234083, "children": { "env_step": { "total": 488.79915576399105, "count": 27328, "self": 383.303813302002, "children": { "SubprocessEnvManager._take_step": { "total": 105.12632256299366, "count": 27328, "self": 1.9497518859868705, "children": { "TorchPolicy.evaluate": { "total": 103.1765706770068, "count": 27328, "self": 103.1765706770068 } } }, "workers": { "total": 0.3690198989953615, "count": 27328, "self": 0.0, "children": { "worker_root": { "total": 772.4082089249906, "count": 27328, "is_parallel": true, "self": 436.9386260549818, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005678278999994291, "count": 1, "is_parallel": true, "self": 0.004171400999894104, "children": { "_process_rank_one_or_two_observation": { "total": 0.001506878000100187, "count": 10, "is_parallel": true, "self": 0.001506878000100187 } } }, "UnityEnvironment.step": { "total": 0.0349108629999364, "count": 1, "is_parallel": true, "self": 0.0006066439999585782, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004011209999816856, "count": 1, "is_parallel": true, "self": 0.0004011209999816856 }, "communicator.exchange": { "total": 0.03206100399995648, "count": 1, "is_parallel": true, "self": 0.03206100399995648 }, "steps_from_proto": { "total": 0.0018420940000396513, "count": 1, "is_parallel": true, "self": 0.0003755929999442742, "children": { "_process_rank_one_or_two_observation": { "total": 0.001466501000095377, "count": 10, "is_parallel": true, "self": 0.001466501000095377 } } } } } } }, "UnityEnvironment.step": { "total": 335.4695828700088, "count": 27327, "is_parallel": true, "self": 15.483895376006103, "children": { "UnityEnvironment._generate_step_input": { "total": 8.163920658994584, "count": 27327, "is_parallel": true, "self": 8.163920658994584 }, "communicator.exchange": { "total": 257.42597281699784, "count": 27327, "is_parallel": true, "self": 257.42597281699784 }, "steps_from_proto": { "total": 54.39579401801029, "count": 27327, "is_parallel": true, "self": 10.227048283090198, "children": { "_process_rank_one_or_two_observation": { "total": 44.168745734920094, "count": 273270, "is_parallel": true, "self": 44.168745734920094 } } } } } } } } } } }, "trainer_advance": { "total": 281.79416969001875, "count": 27328, "self": 0.7822801750253348, "children": { "process_trajectory": { "total": 40.24612741099281, "count": 27328, "self": 39.47031623099258, "children": { "RLTrainer._checkpoint": { "total": 0.7758111800002325, "count": 6, "self": 0.7758111800002325 } } }, "_update_policy": { "total": 240.7657621040006, "count": 136, "self": 98.20917119098988, "children": { "TorchPPOOptimizer.update": { "total": 142.55659091301072, "count": 11555, "self": 142.55659091301072 } } } } } } }, "trainer_threads": { "total": 9.629998203308787e-07, "count": 1, "self": 9.629998203308787e-07 }, "TrainerController._save_models": { "total": 0.11772423799993703, "count": 1, "self": 0.0012363579999146168, "children": { "RLTrainer._checkpoint": { "total": 0.11648788000002241, "count": 1, "self": 0.11648788000002241 } } } } } } }