{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.9601648449897766, "min": 0.9601648449897766, "max": 2.862175941467285, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 9188.77734375, "min": 9188.77734375, "max": 29374.51171875, "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": 12.695140838623047, "min": 0.39527571201324463, "max": 12.695140838623047, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2475.552490234375, "min": 76.68348693847656, "max": 2565.52099609375, "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": 0.06207279962323168, "min": 0.06207279962323168, "max": 0.07862484243284429, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.24829119849292672, "min": 0.24829119849292672, "max": 0.36034094464711797, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.209342308999861, "min": 0.12120918023820018, "max": 0.30513307493106995, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.837369235999444, "min": 0.4848367209528007, "max": 1.5256653746553497, "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": 24.795454545454547, "min": 3.3636363636363638, "max": 25.295454545454547, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1091.0, "min": 148.0, "max": 1373.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 24.795454545454547, "min": 3.3636363636363638, "max": 25.295454545454547, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1091.0, "min": 148.0, "max": 1373.0, "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": "1689720793", "python_version": "3.10.12 (main, Jun 7 2023, 12:45:35) [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": "0.31.0.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": "1689721300" }, "total": 507.28347753300005, "count": 1, "self": 0.7396019040000965, "children": { "run_training.setup": { "total": 0.19666246100001672, "count": 1, "self": 0.19666246100001672 }, "TrainerController.start_learning": { "total": 506.34721316799994, "count": 1, "self": 0.5721232540014398, "children": { "TrainerController._reset_env": { "total": 7.514627692999966, "count": 1, "self": 7.514627692999966 }, "TrainerController.advance": { "total": 498.00749385099846, "count": 18223, "self": 0.28549797399551835, "children": { "env_step": { "total": 497.72199587700294, "count": 18223, "self": 360.89926101699774, "children": { "SubprocessEnvManager._take_step": { "total": 136.54389012900077, "count": 18223, "self": 1.9921528270114663, "children": { "TorchPolicy.evaluate": { "total": 134.5517373019893, "count": 18223, "self": 134.5517373019893 } } }, "workers": { "total": 0.2788447310044262, "count": 18223, "self": 0.0, "children": { "worker_root": { "total": 504.7925301100079, "count": 18223, "is_parallel": true, "self": 241.2670867980146, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.008132121000016923, "count": 1, "is_parallel": true, "self": 0.005594064999968396, "children": { "_process_rank_one_or_two_observation": { "total": 0.0025380560000485275, "count": 10, "is_parallel": true, "self": 0.0025380560000485275 } } }, "UnityEnvironment.step": { "total": 0.08256927899998345, "count": 1, "is_parallel": true, "self": 0.0006631929999798558, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005344420000028549, "count": 1, "is_parallel": true, "self": 0.0005344420000028549 }, "communicator.exchange": { "total": 0.07866807599998538, "count": 1, "is_parallel": true, "self": 0.07866807599998538 }, "steps_from_proto": { "total": 0.002703568000015366, "count": 1, "is_parallel": true, "self": 0.0005398310000828133, "children": { "_process_rank_one_or_two_observation": { "total": 0.002163736999932553, "count": 10, "is_parallel": true, "self": 0.002163736999932553 } } } } } } }, "UnityEnvironment.step": { "total": 263.5254433119933, "count": 18222, "is_parallel": true, "self": 11.253450737991159, "children": { "UnityEnvironment._generate_step_input": { "total": 5.836810312010584, "count": 18222, "is_parallel": true, "self": 5.836810312010584 }, "communicator.exchange": { "total": 206.53743121799425, "count": 18222, "is_parallel": true, "self": 206.53743121799425 }, "steps_from_proto": { "total": 39.89775104399729, "count": 18222, "is_parallel": true, "self": 7.185671469004035, "children": { "_process_rank_one_or_two_observation": { "total": 32.712079574993254, "count": 182220, "is_parallel": true, "self": 32.712079574993254 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00015483499998936168, "count": 1, "self": 0.00015483499998936168, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 493.8336025100251, "count": 478666, "is_parallel": true, "self": 11.005357187999948, "children": { "process_trajectory": { "total": 272.85432073402603, "count": 478666, "is_parallel": true, "self": 271.01784687702605, "children": { "RLTrainer._checkpoint": { "total": 1.8364738569999872, "count": 4, "is_parallel": true, "self": 1.8364738569999872 } } }, "_update_policy": { "total": 209.97392458799914, "count": 90, "is_parallel": true, "self": 81.96400736599975, "children": { "TorchPPOOptimizer.update": { "total": 128.0099172219994, "count": 4587, "is_parallel": true, "self": 128.0099172219994 } } } } } } } } }, "TrainerController._save_models": { "total": 0.25281353500008663, "count": 1, "self": 0.0012256530000058774, "children": { "RLTrainer._checkpoint": { "total": 0.25158788200008075, "count": 1, "self": 0.25158788200008075 } } } } } } }