{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 1.0066593885421753, "min": 1.0066593885421753, "max": 2.8634772300720215, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 9611.583984375, "min": 9611.583984375, "max": 29387.8671875, "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": 12.748875617980957, "min": 0.47284165024757385, "max": 12.748875617980957, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2486.03076171875, "min": 91.73127746582031, "max": 2587.74365234375, "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": 0.06818116002968473, "min": 0.06265999621353009, "max": 0.07374588498679062, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2727246401187389, "min": 0.25063998485412037, "max": 0.3580512018719067, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.2152100779554423, "min": 0.13095808991541466, "max": 0.2863897971078461, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.8608403118217692, "min": 0.5238323596616586, "max": 1.4319489855392307, "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": 24.931818181818183, "min": 3.727272727272727, "max": 25.418181818181818, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1097.0, "min": 164.0, "max": 1398.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 24.931818181818183, "min": 3.727272727272727, "max": 25.418181818181818, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1097.0, "min": 164.0, "max": 1398.0, "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": "1718079327", "python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [GCC 11.4.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn /content/ml-agents/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": "2.3.0+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1718079794" }, "total": 467.3438878029999, "count": 1, "self": 0.44113904199991794, "children": { "run_training.setup": { "total": 0.0571027910000339, "count": 1, "self": 0.0571027910000339 }, "TrainerController.start_learning": { "total": 466.84564596999996, "count": 1, "self": 0.6505716100015206, "children": { "TrainerController._reset_env": { "total": 3.7223732899999504, "count": 1, "self": 3.7223732899999504 }, "TrainerController.advance": { "total": 462.37848966699846, "count": 18200, "self": 0.3097301170010951, "children": { "env_step": { "total": 462.06875954999737, "count": 18200, "self": 302.93464075800034, "children": { "SubprocessEnvManager._take_step": { "total": 158.81862589298646, "count": 18200, "self": 1.5717196939908717, "children": { "TorchPolicy.evaluate": { "total": 157.2469061989956, "count": 18200, "self": 157.2469061989956 } } }, "workers": { "total": 0.31549289901056454, "count": 18200, "self": 0.0, "children": { "worker_root": { "total": 465.5133196040017, "count": 18200, "is_parallel": true, "self": 234.91911559700134, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005572398000026624, "count": 1, "is_parallel": true, "self": 0.003897696999956679, "children": { "_process_rank_one_or_two_observation": { "total": 0.0016747010000699447, "count": 10, "is_parallel": true, "self": 0.0016747010000699447 } } }, "UnityEnvironment.step": { "total": 0.03589550200001668, "count": 1, "is_parallel": true, "self": 0.000681331000123464, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004310199999508768, "count": 1, "is_parallel": true, "self": 0.0004310199999508768 }, "communicator.exchange": { "total": 0.03278807499998493, "count": 1, "is_parallel": true, "self": 0.03278807499998493 }, "steps_from_proto": { "total": 0.0019950759999574075, "count": 1, "is_parallel": true, "self": 0.00037145999965559895, "children": { "_process_rank_one_or_two_observation": { "total": 0.0016236160003018085, "count": 10, "is_parallel": true, "self": 0.0016236160003018085 } } } } } } }, "UnityEnvironment.step": { "total": 230.59420400700037, "count": 18199, "is_parallel": true, "self": 10.381635480988734, "children": { "UnityEnvironment._generate_step_input": { "total": 5.411519367007145, "count": 18199, "is_parallel": true, "self": 5.411519367007145 }, "communicator.exchange": { "total": 181.3349070850005, "count": 18199, "is_parallel": true, "self": 181.3349070850005 }, "steps_from_proto": { "total": 33.46614207400398, "count": 18199, "is_parallel": true, "self": 6.516861519002532, "children": { "_process_rank_one_or_two_observation": { "total": 26.94928055500145, "count": 181990, "is_parallel": true, "self": 26.94928055500145 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00011409499995806982, "count": 1, "self": 0.00011409499995806982, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 457.16079414099045, "count": 684051, "is_parallel": true, "self": 13.726160267970954, "children": { "process_trajectory": { "total": 254.26241474501944, "count": 684051, "is_parallel": true, "self": 253.45785331101945, "children": { "RLTrainer._checkpoint": { "total": 0.8045614339999929, "count": 4, "is_parallel": true, "self": 0.8045614339999929 } } }, "_update_policy": { "total": 189.17221912800005, "count": 90, "is_parallel": true, "self": 59.668733992995726, "children": { "TorchPPOOptimizer.update": { "total": 129.50348513500433, "count": 4587, "is_parallel": true, "self": 129.50348513500433 } } } } } } } } }, "TrainerController._save_models": { "total": 0.0940973080000731, "count": 1, "self": 0.00098652800011223, "children": { "RLTrainer._checkpoint": { "total": 0.09311077999996087, "count": 1, "self": 0.09311077999996087 } } } } } } }