{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.9158356189727783, "min": 0.9158356189727783, "max": 2.8722453117370605, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 8774.62109375, "min": 8774.62109375, "max": 29509.44921875, "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": 12.926004409790039, "min": 0.3318011462688446, "max": 12.926004409790039, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2520.57080078125, "min": 64.36942291259766, "max": 2623.70361328125, "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": 0.0666139591314063, "min": 0.06304143815244363, "max": 0.07493882821827177, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2664558365256252, "min": 0.25216575260977453, "max": 0.3746941410913589, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.20493138289334725, "min": 0.134104045573622, "max": 0.2954873890415126, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.819725531573389, "min": 0.536416182294488, "max": 1.3300590956327962, "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": 25.522727272727273, "min": 3.7954545454545454, "max": 25.522727272727273, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1123.0, "min": 167.0, "max": 1387.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.522727272727273, "min": 3.7954545454545454, "max": 25.522727272727273, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1123.0, "min": 167.0, "max": 1387.0, "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": "1720172637", "python_version": "3.10.5 | packaged by conda-forge | (main, Jun 14 2022, 07:06:46) [GCC 10.3.0]", "command_line_arguments": "/home/evgenii/anaconda3/envs/hf_unit_5/bin/mlagents-learn ./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": "2.3.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1720172857" }, "total": 219.64906156899997, "count": 1, "self": 0.21867410899994866, "children": { "run_training.setup": { "total": 0.013962648999950034, "count": 1, "self": 0.013962648999950034 }, "TrainerController.start_learning": { "total": 219.41642481100007, "count": 1, "self": 0.3159237389745613, "children": { "TrainerController._reset_env": { "total": 1.2437744629996814, "count": 1, "self": 1.2437744629996814 }, "TrainerController.advance": { "total": 217.78327850102687, "count": 18205, "self": 0.16095041401786148, "children": { "env_step": { "total": 217.622328087009, "count": 18205, "self": 143.00400726799853, "children": { "SubprocessEnvManager._take_step": { "total": 74.45935391804142, "count": 18205, "self": 0.8274331680877367, "children": { "TorchPolicy.evaluate": { "total": 73.63192074995368, "count": 18205, "self": 73.63192074995368 } } }, "workers": { "total": 0.1589669009690624, "count": 18205, "self": 0.0, "children": { "worker_root": { "total": 219.05230195408058, "count": 18205, "is_parallel": true, "self": 121.5084438831218, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0010520019995965413, "count": 1, "is_parallel": true, "self": 0.0002799359999698936, "children": { "_process_rank_one_or_two_observation": { "total": 0.0007720659996266477, "count": 10, "is_parallel": true, "self": 0.0007720659996266477 } } }, "UnityEnvironment.step": { "total": 0.016687395999724686, "count": 1, "is_parallel": true, "self": 0.00021699500030081253, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0001554809996378026, "count": 1, "is_parallel": true, "self": 0.0001554809996378026 }, "communicator.exchange": { "total": 0.01553979199979949, "count": 1, "is_parallel": true, "self": 0.01553979199979949 }, "steps_from_proto": { "total": 0.0007751279999865801, "count": 1, "is_parallel": true, "self": 0.00019358499775989912, "children": { "_process_rank_one_or_two_observation": { "total": 0.000581543002226681, "count": 10, "is_parallel": true, "self": 0.000581543002226681 } } } } } } }, "UnityEnvironment.step": { "total": 97.54385807095878, "count": 18204, "is_parallel": true, "self": 3.967036522049966, "children": { "UnityEnvironment._generate_step_input": { "total": 2.279983206885845, "count": 18204, "is_parallel": true, "self": 2.279983206885845 }, "communicator.exchange": { "total": 78.33445492296323, "count": 18204, "is_parallel": true, "self": 78.33445492296323 }, "steps_from_proto": { "total": 12.962383419059734, "count": 18204, "is_parallel": true, "self": 2.7552431331550906, "children": { "_process_rank_one_or_two_observation": { "total": 10.207140285904643, "count": 182040, "is_parallel": true, "self": 10.207140285904643 } } } } } } } } } } } } }, "trainer_threads": { "total": 8.334499943885021e-05, "count": 1, "self": 8.334499943885021e-05, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 217.49248664005972, "count": 172152, "is_parallel": true, "self": 1.5209595278947745, "children": { "process_trajectory": { "total": 120.30124847616571, "count": 172152, "is_parallel": true, "self": 119.78637192116639, "children": { "RLTrainer._checkpoint": { "total": 0.5148765549993186, "count": 4, "is_parallel": true, "self": 0.5148765549993186 } } }, "_update_policy": { "total": 95.67027863599924, "count": 90, "is_parallel": true, "self": 24.250524946042788, "children": { "TorchPPOOptimizer.update": { "total": 71.41975368995645, "count": 4587, "is_parallel": true, "self": 71.41975368995645 } } } } } } } } }, "TrainerController._save_models": { "total": 0.07336476299951755, "count": 1, "self": 0.0005161099988981732, "children": { "RLTrainer._checkpoint": { "total": 0.07284865300061938, "count": 1, "self": 0.07284865300061938 } } } } } } }