{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.9916243553161621, "min": 0.9916243553161621, "max": 2.8611271381378174, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 9468.029296875, "min": 9468.029296875, "max": 29584.0546875, "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": 13.086578369140625, "min": 0.35481277108192444, "max": 13.086578369140625, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2551.8828125, "min": 68.83367919921875, "max": 2616.5205078125, "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": 0.06700570289389113, "min": 0.06134848138350993, "max": 0.07262712494530563, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2680228115755645, "min": 0.24539392553403971, "max": 0.35755560667066855, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.19048134891279772, "min": 0.11672893525146896, "max": 0.2749690232323665, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.7619253956511909, "min": 0.46691574100587585, "max": 1.3670401809846653, "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": 26.068181818181817, "min": 3.409090909090909, "max": 26.068181818181817, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1147.0, "min": 150.0, "max": 1402.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 26.068181818181817, "min": 3.409090909090909, "max": 26.068181818181817, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1147.0, "min": 150.0, "max": 1402.0, "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": "1678192713", "python_version": "3.8.10 (default, Nov 14 2022, 12:59:47) \n[GCC 9.4.0]", "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": "0.29.0.dev0", "mlagents_envs_version": "0.29.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.8.1+cu102", "numpy_version": "1.22.4", "end_time_seconds": "1678193155" }, "total": 442.09493863500006, "count": 1, "self": 0.39054416600038167, "children": { "run_training.setup": { "total": 0.11151254499986862, "count": 1, "self": 0.11151254499986862 }, "TrainerController.start_learning": { "total": 441.5928819239998, "count": 1, "self": 0.5249085259836193, "children": { "TrainerController._reset_env": { "total": 9.343022850000125, "count": 1, "self": 9.343022850000125 }, "TrainerController.advance": { "total": 431.60727551001605, "count": 18202, "self": 0.25697436304017174, "children": { "env_step": { "total": 431.3503011469759, "count": 18202, "self": 296.1415565539926, "children": { "SubprocessEnvManager._take_step": { "total": 134.95326432099841, "count": 18202, "self": 1.4285403019960086, "children": { "TorchPolicy.evaluate": { "total": 133.5247240190024, "count": 18202, "self": 30.098336554995967, "children": { "TorchPolicy.sample_actions": { "total": 103.42638746400644, "count": 18202, "self": 103.42638746400644 } } } } }, "workers": { "total": 0.25548027198487944, "count": 18202, "self": 0.0, "children": { "worker_root": { "total": 440.1694369540105, "count": 18202, "is_parallel": true, "self": 214.6345030760233, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005157194000048548, "count": 1, "is_parallel": true, "self": 0.003901863999772104, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012553300002764445, "count": 10, "is_parallel": true, "self": 0.0012553300002764445 } } }, "UnityEnvironment.step": { "total": 0.03476408100004846, "count": 1, "is_parallel": true, "self": 0.0005292600001212122, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00036726999996972154, "count": 1, "is_parallel": true, "self": 0.00036726999996972154 }, "communicator.exchange": { "total": 0.03208363199996711, "count": 1, "is_parallel": true, "self": 0.03208363199996711 }, "steps_from_proto": { "total": 0.0017839189999904193, "count": 1, "is_parallel": true, "self": 0.0004259800002728298, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013579389997175895, "count": 10, "is_parallel": true, "self": 0.0013579389997175895 } } } } } } }, "UnityEnvironment.step": { "total": 225.5349338779872, "count": 18201, "is_parallel": true, "self": 9.065974545948393, "children": { "UnityEnvironment._generate_step_input": { "total": 5.048941426001875, "count": 18201, "is_parallel": true, "self": 5.048941426001875 }, "communicator.exchange": { "total": 182.0123310030267, "count": 18201, "is_parallel": true, "self": 182.0123310030267 }, "steps_from_proto": { "total": 29.407686903010244, "count": 18201, "is_parallel": true, "self": 6.288258906034571, "children": { "_process_rank_one_or_two_observation": { "total": 23.119427996975674, "count": 182010, "is_parallel": true, "self": 23.119427996975674 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.0001503729999967618, "count": 1, "self": 0.0001503729999967618, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 428.52472799804787, "count": 386275, "is_parallel": true, "self": 9.400413322207214, "children": { "process_trajectory": { "total": 245.80493783184352, "count": 386275, "is_parallel": true, "self": 244.96299476084346, "children": { "RLTrainer._checkpoint": { "total": 0.8419430710000597, "count": 4, "is_parallel": true, "self": 0.8419430710000597 } } }, "_update_policy": { "total": 173.31937684399713, "count": 90, "is_parallel": true, "self": 59.01655073599386, "children": { "TorchPPOOptimizer.update": { "total": 114.30282610800327, "count": 4587, "is_parallel": true, "self": 114.30282610800327 } } } } } } } } }, "TrainerController._save_models": { "total": 0.11752466500001901, "count": 1, "self": 0.0008922649999476562, "children": { "RLTrainer._checkpoint": { "total": 0.11663240000007136, "count": 1, "self": 0.11663240000007136 } } } } } } }