{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.9599045515060425, "min": 0.9599045515060425, "max": 2.8872427940368652, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 9122.9326171875, "min": 9122.9326171875, "max": 29472.974609375, "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": 9.611108779907227, "min": 0.2997777462005615, "max": 9.611108779907227, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 1874.166259765625, "min": 58.156883239746094, "max": 1939.076416015625, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.06868914460995025, "min": 0.060118325604952255, "max": 0.07675132557564854, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.274756578439801, "min": 0.24047330241980902, "max": 0.35523072656018057, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.24134502107021855, "min": 0.09416864959491125, "max": 0.2992779325036442, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.9653800842808742, "min": 0.376674598379645, "max": 1.496389662518221, "count": 20 }, "SnowballTarget.Policy.LearningRate.mean": { "value": 2.6940973060000025e-06, "min": 2.6940973060000025e-06, "max": 9.729400270599998e-05, "count": 20 }, "SnowballTarget.Policy.LearningRate.sum": { "value": 1.077638922400001e-05, "min": 1.077638922400001e-05, "max": 0.0004617200382800001, "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.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.Environment.CumulativeReward.mean": { "value": 18.863636363636363, "min": 2.772727272727273, "max": 19.01818181818182, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 830.0, "min": 122.0, "max": 1046.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 18.863636363636363, "min": 2.772727272727273, "max": 19.01818181818182, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 830.0, "min": 122.0, "max": 1046.0, "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": "1729766024", "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 --force --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": "2.5.0+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1729766489" }, "total": 465.04024809099997, "count": 1, "self": 0.4277564040000925, "children": { "run_training.setup": { "total": 0.053001660999939304, "count": 1, "self": 0.053001660999939304 }, "TrainerController.start_learning": { "total": 464.55949002599993, "count": 1, "self": 0.4193181639807335, "children": { "TrainerController._reset_env": { "total": 2.0030833690000236, "count": 1, "self": 2.0030833690000236 }, "TrainerController.advance": { "total": 462.03315522901937, "count": 18192, "self": 0.4215804150222766, "children": { "env_step": { "total": 321.4241384349863, "count": 18192, "self": 241.42859034793605, "children": { "SubprocessEnvManager._take_step": { "total": 79.73931556102661, "count": 18192, "self": 1.376657903002524, "children": { "TorchPolicy.evaluate": { "total": 78.36265765802409, "count": 18192, "self": 78.36265765802409 } } }, "workers": { "total": 0.25623252602360935, "count": 18192, "self": 0.0, "children": { "worker_root": { "total": 462.8466639429862, "count": 18192, "is_parallel": true, "self": 252.52501165199124, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0027474600000232385, "count": 1, "is_parallel": true, "self": 0.0008456520000663659, "children": { "_process_rank_one_or_two_observation": { "total": 0.0019018079999568727, "count": 10, "is_parallel": true, "self": 0.0019018079999568727 } } }, "UnityEnvironment.step": { "total": 0.04785243800006356, "count": 1, "is_parallel": true, "self": 0.0006358840000757482, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004326920000039536, "count": 1, "is_parallel": true, "self": 0.0004326920000039536 }, "communicator.exchange": { "total": 0.04144227699998737, "count": 1, "is_parallel": true, "self": 0.04144227699998737 }, "steps_from_proto": { "total": 0.005341584999996485, "count": 1, "is_parallel": true, "self": 0.0005590739999661309, "children": { "_process_rank_one_or_two_observation": { "total": 0.004782511000030354, "count": 10, "is_parallel": true, "self": 0.004782511000030354 } } } } } } }, "UnityEnvironment.step": { "total": 210.32165229099496, "count": 18191, "is_parallel": true, "self": 10.390054017976354, "children": { "UnityEnvironment._generate_step_input": { "total": 5.697726550013499, "count": 18191, "is_parallel": true, "self": 5.697726550013499 }, "communicator.exchange": { "total": 160.66426348101209, "count": 18191, "is_parallel": true, "self": 160.66426348101209 }, "steps_from_proto": { "total": 33.56960824199302, "count": 18191, "is_parallel": true, "self": 6.301000773012447, "children": { "_process_rank_one_or_two_observation": { "total": 27.268607468980576, "count": 181910, "is_parallel": true, "self": 27.268607468980576 } } } } } } } } } } }, "trainer_advance": { "total": 140.18743637901082, "count": 18192, "self": 0.5166296449901893, "children": { "process_trajectory": { "total": 30.601529997021316, "count": 18192, "self": 30.012546636021398, "children": { "RLTrainer._checkpoint": { "total": 0.5889833609999187, "count": 4, "self": 0.5889833609999187 } } }, "_update_policy": { "total": 109.06927673699931, "count": 90, "self": 41.40219522999291, "children": { "TorchPPOOptimizer.update": { "total": 67.6670815070064, "count": 4587, "self": 67.6670815070064 } } } } } } }, "trainer_threads": { "total": 1.1539998467924306e-06, "count": 1, "self": 1.1539998467924306e-06 }, "TrainerController._save_models": { "total": 0.10393210999995972, "count": 1, "self": 0.0008169230000021344, "children": { "RLTrainer._checkpoint": { "total": 0.10311518699995759, "count": 1, "self": 0.10311518699995759 } } } } } } }