{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 1.0749859809875488, "min": 1.0749859809875488, "max": 2.8845808506011963, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 10323.08984375, "min": 10323.08984375, "max": 29699.64453125, "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": 12.502165794372559, "min": 0.23804718255996704, "max": 12.502165794372559, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2437.92236328125, "min": 46.18115234375, "max": 2546.56494140625, "count": 20 }, "SnowballTarget.Policy.CuriosityValueEstimate.mean": { "value": 3.6209359169006348, "min": 1.0830051898956299, "max": 5.617513656616211, "count": 20 }, "SnowballTarget.Policy.CuriosityValueEstimate.sum": { "value": 706.08251953125, "min": 210.10299682617188, "max": 1151.59033203125, "count": 20 }, "SnowballTarget.Environment.EpisodeLength.mean": { "value": 199.0, "min": 199.0, "max": 199.0, "count": 20 }, "SnowballTarget.Environment.EpisodeLength.sum": { "value": 10945.0, "min": 8756.0, "max": 10945.0, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.07086987895651392, "min": 0.06283836557989822, "max": 0.07555267589404871, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2834795158260557, "min": 0.25860794359708533, "max": 0.37012536303932303, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.11374905727365438, "min": 0.1063170893081263, "max": 0.1838985693951448, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.4549962290946175, "min": 0.4549962290946175, "max": 0.8538182090018311, "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.Losses.CuriosityForwardLoss.mean": { "value": 0.03560235113928131, "min": 0.03529992929714567, "max": 0.12645662729354468, "count": 20 }, "SnowballTarget.Losses.CuriosityForwardLoss.sum": { "value": 0.14240940455712525, "min": 0.14240940455712525, "max": 0.5058265091741787, "count": 20 }, "SnowballTarget.Losses.CuriosityInverseLoss.mean": { "value": 0.9248626173711291, "min": 0.9248626173711291, "max": 2.7975179116953823, "count": 20 }, "SnowballTarget.Losses.CuriosityInverseLoss.sum": { "value": 3.6994504694845163, "min": 3.6994504694845163, "max": 13.126384894053139, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.mean": { "value": 24.204545454545453, "min": 3.159090909090909, "max": 24.672727272727272, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1065.0, "min": 139.0, "max": 1357.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 24.204545454545453, "min": 3.159090909090909, "max": 24.672727272727272, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1065.0, "min": 139.0, "max": 1357.0, "count": 20 }, "SnowballTarget.Policy.CuriosityReward.mean": { "value": 7.2575455182655295, "min": 7.1541644076054745, "max": 13.579688123952259, "count": 20 }, "SnowballTarget.Policy.CuriosityReward.sum": { "value": 319.3320028036833, "min": 318.79507821053267, "max": 746.8828468173742, "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": "1729396585", "python_version": "3.10.12 (main, Sep 11 2024, 15:47:36) [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": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.4.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1729397274" }, "total": 689.2803061250006, "count": 1, "self": 0.6957692510004563, "children": { "run_training.setup": { "total": 0.07508449099987047, "count": 1, "self": 0.07508449099987047 }, "TrainerController.start_learning": { "total": 688.5094523830003, "count": 1, "self": 0.8463738540467602, "children": { "TrainerController._reset_env": { "total": 5.219617856999321, "count": 1, "self": 5.219617856999321 }, "TrainerController.advance": { "total": 682.350698227955, "count": 18208, "self": 0.42673828398073965, "children": { "env_step": { "total": 681.9239599439743, "count": 18208, "self": 552.8366894150158, "children": { "SubprocessEnvManager._take_step": { "total": 128.67166493795685, "count": 18208, "self": 2.2173823590501343, "children": { "TorchPolicy.evaluate": { "total": 126.45428257890671, "count": 18208, "self": 126.45428257890671 } } }, "workers": { "total": 0.4156055910016221, "count": 18208, "self": 0.0, "children": { "worker_root": { "total": 686.5758296169961, "count": 18208, "is_parallel": true, "self": 382.14631724896935, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0034162190004281, "count": 1, "is_parallel": true, "self": 0.0010745510007836856, "children": { "_process_rank_one_or_two_observation": { "total": 0.0023416679996444145, "count": 10, "is_parallel": true, "self": 0.0023416679996444145 } } }, "UnityEnvironment.step": { "total": 0.04492873700019118, "count": 1, "is_parallel": true, "self": 0.0008644779991300311, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004064129998369026, "count": 1, "is_parallel": true, "self": 0.0004064129998369026 }, "communicator.exchange": { "total": 0.04116251200048282, "count": 1, "is_parallel": true, "self": 0.04116251200048282 }, "steps_from_proto": { "total": 0.0024953340007414226, "count": 1, "is_parallel": true, "self": 0.00042668100195442094, "children": { "_process_rank_one_or_two_observation": { "total": 0.0020686529987870017, "count": 10, "is_parallel": true, "self": 0.0020686529987870017 } } } } } } }, "UnityEnvironment.step": { "total": 304.42951236802674, "count": 18207, "is_parallel": true, "self": 14.718953087142836, "children": { "UnityEnvironment._generate_step_input": { "total": 7.389445729977524, "count": 18207, "is_parallel": true, "self": 7.389445729977524 }, "communicator.exchange": { "total": 239.32590429795255, "count": 18207, "is_parallel": true, "self": 239.32590429795255 }, "steps_from_proto": { "total": 42.99520925295383, "count": 18207, "is_parallel": true, "self": 8.616244793079204, "children": { "_process_rank_one_or_two_observation": { "total": 34.378964459874624, "count": 182070, "is_parallel": true, "self": 34.378964459874624 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.0002183799997510505, "count": 1, "self": 0.0002183799997510505, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 676.3816852376822, "count": 694815, "is_parallel": true, "self": 15.743785705432856, "children": { "process_trajectory": { "total": 326.2889463312422, "count": 694815, "is_parallel": true, "self": 325.49776529224073, "children": { "RLTrainer._checkpoint": { "total": 0.791181039001458, "count": 4, "is_parallel": true, "self": 0.791181039001458 } } }, "_update_policy": { "total": 334.34895320100713, "count": 90, "is_parallel": true, "self": 197.986553354006, "children": { "TorchPPOOptimizer.update": { "total": 136.36239984700114, "count": 4587, "is_parallel": true, "self": 136.36239984700114 } } } } } } } } }, "TrainerController._save_models": { "total": 0.09254406399941217, "count": 1, "self": 0.0011805979993368965, "children": { "RLTrainer._checkpoint": { "total": 0.09136346600007528, "count": 1, "self": 0.09136346600007528 } } } } } } }