| { |
| "name": "root", |
| "gauges": { |
| "Pyramids.Policy.Entropy.mean": { |
| "value": 0.22584600746631622, |
| "min": 0.2226453721523285, |
| "max": 1.4426076412200928, |
| "count": 50 |
| }, |
| "Pyramids.Policy.Entropy.sum": { |
| "value": 6771.7666015625, |
| "min": 6654.4248046875, |
| "max": 43762.9453125, |
| "count": 50 |
| }, |
| "Pyramids.Step.mean": { |
| "value": 1499939.0, |
| "min": 29922.0, |
| "max": 1499939.0, |
| "count": 50 |
| }, |
| "Pyramids.Step.sum": { |
| "value": 1499939.0, |
| "min": 29922.0, |
| "max": 1499939.0, |
| "count": 50 |
| }, |
| "Pyramids.Policy.ExtrinsicValueEstimate.mean": { |
| "value": 0.6199408173561096, |
| "min": -0.11817127466201782, |
| "max": 0.755702018737793, |
| "count": 50 |
| }, |
| "Pyramids.Policy.ExtrinsicValueEstimate.sum": { |
| "value": 174.8233184814453, |
| "min": -28.006591796875, |
| "max": 222.93209838867188, |
| "count": 50 |
| }, |
| "Pyramids.Policy.RndValueEstimate.mean": { |
| "value": -0.004071508068591356, |
| "min": -0.011213291436433792, |
| "max": 0.4749000370502472, |
| "count": 50 |
| }, |
| "Pyramids.Policy.RndValueEstimate.sum": { |
| "value": -1.148165225982666, |
| "min": -3.251854419708252, |
| "max": 112.55130767822266, |
| "count": 50 |
| }, |
| "Pyramids.Losses.PolicyLoss.mean": { |
| "value": 0.06842014983424223, |
| "min": 0.06512405517914936, |
| "max": 0.07405228710408195, |
| "count": 50 |
| }, |
| "Pyramids.Losses.PolicyLoss.sum": { |
| "value": 1.0263022475136334, |
| "min": 0.5183660097285736, |
| "max": 1.094291228791311, |
| "count": 50 |
| }, |
| "Pyramids.Losses.ValueLoss.mean": { |
| "value": 0.013262247259491215, |
| "min": 0.0007009630764837433, |
| "max": 0.0167980060425526, |
| "count": 50 |
| }, |
| "Pyramids.Losses.ValueLoss.sum": { |
| "value": 0.19893370889236822, |
| "min": 0.009813483070772405, |
| "max": 0.25183738928171806, |
| "count": 50 |
| }, |
| "Pyramids.Policy.LearningRate.mean": { |
| "value": 2.99384566875111e-06, |
| "min": 2.99384566875111e-06, |
| "max": 0.00029676708679192377, |
| "count": 50 |
| }, |
| "Pyramids.Policy.LearningRate.sum": { |
| "value": 4.490768503126665e-05, |
| "min": 4.490768503126665e-05, |
| "max": 0.0038225965258012, |
| "count": 50 |
| }, |
| "Pyramids.Policy.Epsilon.mean": { |
| "value": 0.10099791555555555, |
| "min": 0.10099791555555555, |
| "max": 0.19892236190476195, |
| "count": 50 |
| }, |
| "Pyramids.Policy.Epsilon.sum": { |
| "value": 1.5149687333333333, |
| "min": 1.3924565333333336, |
| "max": 2.6741988000000005, |
| "count": 50 |
| }, |
| "Pyramids.Policy.Beta.mean": { |
| "value": 0.00010969176399999997, |
| "min": 0.00010969176399999997, |
| "max": 0.009892343954285714, |
| "count": 50 |
| }, |
| "Pyramids.Policy.Beta.sum": { |
| "value": 0.0016453764599999995, |
| "min": 0.0016453764599999995, |
| "max": 0.12743246012000004, |
| "count": 50 |
| }, |
| "Pyramids.Losses.RNDLoss.mean": { |
| "value": 0.0068207415752112865, |
| "min": 0.0068207415752112865, |
| "max": 0.5988480448722839, |
| "count": 50 |
| }, |
| "Pyramids.Losses.RNDLoss.sum": { |
| "value": 0.10231112688779831, |
| "min": 0.09818366169929504, |
| "max": 4.191936492919922, |
| "count": 50 |
| }, |
| "Pyramids.Environment.EpisodeLength.mean": { |
| "value": 303.83838383838383, |
| "min": 246.30578512396696, |
| "max": 998.4516129032259, |
| "count": 50 |
| }, |
| "Pyramids.Environment.EpisodeLength.sum": { |
| "value": 30080.0, |
| "min": 16849.0, |
| "max": 33861.0, |
| "count": 50 |
| }, |
| "Pyramids.Environment.CumulativeReward.mean": { |
| "value": 1.5749110948256773, |
| "min": -0.9348839216174618, |
| "max": 1.7471680546007236, |
| "count": 50 |
| }, |
| "Pyramids.Environment.CumulativeReward.sum": { |
| "value": 155.91619838774204, |
| "min": -29.83880167454481, |
| "max": 207.91299849748611, |
| "count": 50 |
| }, |
| "Pyramids.Policy.ExtrinsicReward.mean": { |
| "value": 1.5749110948256773, |
| "min": -0.9348839216174618, |
| "max": 1.7471680546007236, |
| "count": 50 |
| }, |
| "Pyramids.Policy.ExtrinsicReward.sum": { |
| "value": 155.91619838774204, |
| "min": -29.83880167454481, |
| "max": 207.91299849748611, |
| "count": 50 |
| }, |
| "Pyramids.Policy.RndReward.mean": { |
| "value": 0.021247621477790874, |
| "min": 0.018652499381217543, |
| "max": 12.110329354510588, |
| "count": 50 |
| }, |
| "Pyramids.Policy.RndReward.sum": { |
| "value": 2.1035145263012964, |
| "min": 2.1035145263012964, |
| "max": 205.87559902668, |
| "count": 50 |
| }, |
| "Pyramids.IsTraining.mean": { |
| "value": 1.0, |
| "min": 1.0, |
| "max": 1.0, |
| "count": 50 |
| }, |
| "Pyramids.IsTraining.sum": { |
| "value": 1.0, |
| "min": 1.0, |
| "max": 1.0, |
| "count": 50 |
| } |
| }, |
| "metadata": { |
| "timer_format_version": "0.1.0", |
| "start_time_seconds": "1676983073", |
| "python_version": "3.8.10 (default, Nov 14 2022, 12:59:47) \n[GCC 9.4.0]", |
| "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids Training --no-graphics", |
| "mlagents_version": "0.29.0.dev0", |
| "mlagents_envs_version": "0.29.0.dev0", |
| "communication_protocol_version": "1.5.0", |
| "pytorch_version": "1.8.1+cu102", |
| "numpy_version": "1.21.6", |
| "end_time_seconds": "1676986541" |
| }, |
| "total": 3468.108217849, |
| "count": 1, |
| "self": 1.223811310000201, |
| "children": { |
| "run_training.setup": { |
| "total": 0.18848909200005437, |
| "count": 1, |
| "self": 0.18848909200005437 |
| }, |
| "TrainerController.start_learning": { |
| "total": 3466.695917447, |
| "count": 1, |
| "self": 1.9729478351673606, |
| "children": { |
| "TrainerController._reset_env": { |
| "total": 7.14927036500012, |
| "count": 1, |
| "self": 7.14927036500012 |
| }, |
| "TrainerController.advance": { |
| "total": 3457.439610180833, |
| "count": 96473, |
| "self": 2.0655312508752104, |
| "children": { |
| "env_step": { |
| "total": 2348.815149980917, |
| "count": 96473, |
| "self": 2181.891144852954, |
| "children": { |
| "SubprocessEnvManager._take_step": { |
| "total": 165.71798869398935, |
| "count": 96473, |
| "self": 6.682191134097138, |
| "children": { |
| "TorchPolicy.evaluate": { |
| "total": 159.03579755989222, |
| "count": 93808, |
| "self": 53.65109205200042, |
| "children": { |
| "TorchPolicy.sample_actions": { |
| "total": 105.3847055078918, |
| "count": 93808, |
| "self": 105.3847055078918 |
| } |
| } |
| } |
| } |
| }, |
| "workers": { |
| "total": 1.206016433973673, |
| "count": 96473, |
| "self": 0.0, |
| "children": { |
| "worker_root": { |
| "total": 3459.416825108021, |
| "count": 96473, |
| "is_parallel": true, |
| "self": 1446.363935792926, |
| "children": { |
| "run_training.setup": { |
| "total": 0.0, |
| "count": 0, |
| "is_parallel": true, |
| "self": 0.0, |
| "children": { |
| "steps_from_proto": { |
| "total": 0.002489697999862983, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.0008128120002766082, |
| "children": { |
| "_process_rank_one_or_two_observation": { |
| "total": 0.001676885999586375, |
| "count": 8, |
| "is_parallel": true, |
| "self": 0.001676885999586375 |
| } |
| } |
| }, |
| "UnityEnvironment.step": { |
| "total": 0.04930837400024757, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.0005442950000542623, |
| "children": { |
| "UnityEnvironment._generate_step_input": { |
| "total": 0.0004998600002181774, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.0004998600002181774 |
| }, |
| "communicator.exchange": { |
| "total": 0.046651129000110814, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.046651129000110814 |
| }, |
| "steps_from_proto": { |
| "total": 0.0016130899998643144, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.00044049999905837467, |
| "children": { |
| "_process_rank_one_or_two_observation": { |
| "total": 0.0011725900008059398, |
| "count": 8, |
| "is_parallel": true, |
| "self": 0.0011725900008059398 |
| } |
| } |
| } |
| } |
| } |
| } |
| }, |
| "UnityEnvironment.step": { |
| "total": 2013.052889315095, |
| "count": 96472, |
| "is_parallel": true, |
| "self": 46.66657504624209, |
| "children": { |
| "UnityEnvironment._generate_step_input": { |
| "total": 33.57954540988885, |
| "count": 96472, |
| "is_parallel": true, |
| "self": 33.57954540988885 |
| }, |
| "communicator.exchange": { |
| "total": 1792.7428356229716, |
| "count": 96472, |
| "is_parallel": true, |
| "self": 1792.7428356229716 |
| }, |
| "steps_from_proto": { |
| "total": 140.0639332359924, |
| "count": 96472, |
| "is_parallel": true, |
| "self": 32.886443789318946, |
| "children": { |
| "_process_rank_one_or_two_observation": { |
| "total": 107.17748944667346, |
| "count": 771776, |
| "is_parallel": true, |
| "self": 107.17748944667346 |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
| }, |
| "trainer_advance": { |
| "total": 1106.5589289490408, |
| "count": 96473, |
| "self": 3.936769507037752, |
| "children": { |
| "process_trajectory": { |
| "total": 240.19422243701501, |
| "count": 96473, |
| "self": 239.87085451401526, |
| "children": { |
| "RLTrainer._checkpoint": { |
| "total": 0.3233679229997506, |
| "count": 3, |
| "self": 0.3233679229997506 |
| } |
| } |
| }, |
| "_update_policy": { |
| "total": 862.427937004988, |
| "count": 692, |
| "self": 329.95906781097483, |
| "children": { |
| "TorchPPOOptimizer.update": { |
| "total": 532.4688691940132, |
| "count": 34197, |
| "self": 532.4688691940132 |
| } |
| } |
| } |
| } |
| } |
| } |
| }, |
| "trainer_threads": { |
| "total": 1.3489998309523799e-06, |
| "count": 1, |
| "self": 1.3489998309523799e-06 |
| }, |
| "TrainerController._save_models": { |
| "total": 0.13408771699960198, |
| "count": 1, |
| "self": 0.0019036319999941043, |
| "children": { |
| "RLTrainer._checkpoint": { |
| "total": 0.13218408499960788, |
| "count": 1, |
| "self": 0.13218408499960788 |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
