{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.7534700036048889, "min": 0.7534700036048889, "max": 2.8699440956115723, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 7194.1318359375, "min": 7194.1318359375, "max": 29422.666015625, "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": 12.691561698913574, "min": 0.43297579884529114, "max": 12.691561698913574, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2474.8544921875, "min": 83.99730682373047, "max": 2558.1533203125, "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": 0.06477662945404768, "min": 0.06311868497460975, "max": 0.074396863625289, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2591065178161907, "min": 0.2591065178161907, "max": 0.37198431812644495, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.20713315590047368, "min": 0.1116226599197926, "max": 0.27924890693496257, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.8285326236018947, "min": 0.4464906396791704, "max": 1.396244534674813, "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": 24.954545454545453, "min": 3.659090909090909, "max": 25.254545454545454, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1098.0, "min": 161.0, "max": 1389.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 24.954545454545453, "min": 3.659090909090909, "max": 25.254545454545454, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1098.0, "min": 161.0, "max": 1389.0, "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": "1697206621", "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": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.0.1+cu118", "numpy_version": "1.23.5", "end_time_seconds": "1697207063" }, "total": 442.206734751, "count": 1, "self": 0.4314583709999624, "children": { "run_training.setup": { "total": 0.08559794400002829, "count": 1, "self": 0.08559794400002829 }, "TrainerController.start_learning": { "total": 441.689678436, "count": 1, "self": 0.5123677180029631, "children": { "TrainerController._reset_env": { "total": 8.031943664999972, "count": 1, "self": 8.031943664999972 }, "TrainerController.advance": { "total": 433.0620779499971, "count": 18199, "self": 0.23857868299512575, "children": { "env_step": { "total": 432.823499267002, "count": 18199, "self": 294.34832965301354, "children": { "SubprocessEnvManager._take_step": { "total": 138.22426689199648, "count": 18199, "self": 1.3497687449929572, "children": { "TorchPolicy.evaluate": { "total": 136.87449814700352, "count": 18199, "self": 136.87449814700352 } } }, "workers": { "total": 0.25090272199196306, "count": 18199, "self": 0.0, "children": { "worker_root": { "total": 440.5599570399983, "count": 18199, "is_parallel": true, "self": 214.81654641000353, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.00789940099997466, "count": 1, "is_parallel": true, "self": 0.005782267000085994, "children": { "_process_rank_one_or_two_observation": { "total": 0.002117133999888665, "count": 10, "is_parallel": true, "self": 0.002117133999888665 } } }, "UnityEnvironment.step": { "total": 0.032601045000035356, "count": 1, "is_parallel": true, "self": 0.00040285200003609134, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004104760000132046, "count": 1, "is_parallel": true, "self": 0.0004104760000132046 }, "communicator.exchange": { "total": 0.030622972999992726, "count": 1, "is_parallel": true, "self": 0.030622972999992726 }, "steps_from_proto": { "total": 0.001164743999993334, "count": 1, "is_parallel": true, "self": 0.00027354599995987883, "children": { "_process_rank_one_or_two_observation": { "total": 0.0008911980000334552, "count": 10, "is_parallel": true, "self": 0.0008911980000334552 } } } } } } }, "UnityEnvironment.step": { "total": 225.7434106299948, "count": 18198, "is_parallel": true, "self": 10.110358904983116, "children": { "UnityEnvironment._generate_step_input": { "total": 5.111241722003399, "count": 18198, "is_parallel": true, "self": 5.111241722003399 }, "communicator.exchange": { "total": 178.46551988499874, "count": 18198, "is_parallel": true, "self": 178.46551988499874 }, "steps_from_proto": { "total": 32.05629011800954, "count": 18198, "is_parallel": true, "self": 5.825964421993717, "children": { "_process_rank_one_or_two_observation": { "total": 26.230325696015825, "count": 181980, "is_parallel": true, "self": 26.230325696015825 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00011291499993149046, "count": 1, "self": 0.00011291499993149046, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 429.57185089402054, "count": 453771, "is_parallel": true, "self": 9.497245402023054, "children": { "process_trajectory": { "total": 244.4802662369973, "count": 453771, "is_parallel": true, "self": 243.71116015999723, "children": { "RLTrainer._checkpoint": { "total": 0.7691060770000604, "count": 4, "is_parallel": true, "self": 0.7691060770000604 } } }, "_update_policy": { "total": 175.5943392550002, "count": 90, "is_parallel": true, "self": 53.35668271100246, "children": { "TorchPPOOptimizer.update": { "total": 122.23765654399773, "count": 4584, "is_parallel": true, "self": 122.23765654399773 } } } } } } } } }, "TrainerController._save_models": { "total": 0.08317618800003856, "count": 1, "self": 0.000812296000049173, "children": { "RLTrainer._checkpoint": { "total": 0.08236389199998939, "count": 1, "self": 0.08236389199998939 } } } } } } }