| { |
| "name": "root", |
| "gauges": { |
| "Pyramids.Policy.Entropy.mean": { |
| "value": 0.40133917331695557, |
| "min": 0.39024877548217773, |
| "max": 0.9190311431884766, |
| "count": 30 |
| }, |
| "Pyramids.Policy.Entropy.sum": { |
| "value": 12078.7041015625, |
| "min": 11638.779296875, |
| "max": 27526.8203125, |
| "count": 30 |
| }, |
| "Pyramids.Step.mean": { |
| "value": 989902.0, |
| "min": 119990.0, |
| "max": 989902.0, |
| "count": 30 |
| }, |
| "Pyramids.Step.sum": { |
| "value": 989902.0, |
| "min": 119990.0, |
| "max": 989902.0, |
| "count": 30 |
| }, |
| "Pyramids.Policy.ExtrinsicValueEstimate.mean": { |
| "value": 0.592274010181427, |
| "min": -0.1003870815038681, |
| "max": 0.592274010181427, |
| "count": 30 |
| }, |
| "Pyramids.Policy.ExtrinsicValueEstimate.sum": { |
| "value": 167.02127075195312, |
| "min": -24.29367446899414, |
| "max": 167.02127075195312, |
| "count": 30 |
| }, |
| "Pyramids.Policy.RndValueEstimate.mean": { |
| "value": 0.015674160793423653, |
| "min": -0.02970687858760357, |
| "max": 0.11610475927591324, |
| "count": 30 |
| }, |
| "Pyramids.Policy.RndValueEstimate.sum": { |
| "value": 4.4201130867004395, |
| "min": -8.139684677124023, |
| "max": 27.284618377685547, |
| "count": 30 |
| }, |
| "Pyramids.Losses.PolicyLoss.mean": { |
| "value": 0.06571317812103741, |
| "min": 0.06530649958932329, |
| "max": 0.07437105273696006, |
| "count": 30 |
| }, |
| "Pyramids.Losses.PolicyLoss.sum": { |
| "value": 0.9199844936945238, |
| "min": 0.6453641735066445, |
| "max": 1.0480747271891837, |
| "count": 30 |
| }, |
| "Pyramids.Losses.ValueLoss.mean": { |
| "value": 0.014430342710636302, |
| "min": 0.00013537428360679862, |
| "max": 0.015816135720732354, |
| "count": 30 |
| }, |
| "Pyramids.Losses.ValueLoss.sum": { |
| "value": 0.20202479794890824, |
| "min": 0.0018952399704951807, |
| "max": 0.22990176156499909, |
| "count": 30 |
| }, |
| "Pyramids.Policy.LearningRate.mean": { |
| "value": 7.66745458707143e-06, |
| "min": 7.66745458707143e-06, |
| "max": 0.00026757491080836663, |
| "count": 30 |
| }, |
| "Pyramids.Policy.LearningRate.sum": { |
| "value": 0.00010734436421900003, |
| "min": 0.00010734436421900003, |
| "max": 0.003257978614007199, |
| "count": 30 |
| }, |
| "Pyramids.Policy.Epsilon.mean": { |
| "value": 0.10255578571428572, |
| "min": 0.10255578571428572, |
| "max": 0.18919163333333333, |
| "count": 30 |
| }, |
| "Pyramids.Policy.Epsilon.sum": { |
| "value": 1.4357810000000002, |
| "min": 1.4357810000000002, |
| "max": 2.4853319, |
| "count": 30 |
| }, |
| "Pyramids.Policy.Beta.mean": { |
| "value": 0.0002653229928571429, |
| "min": 0.0002653229928571429, |
| "max": 0.008920244170000001, |
| "count": 30 |
| }, |
| "Pyramids.Policy.Beta.sum": { |
| "value": 0.0037145219000000004, |
| "min": 0.0037145219000000004, |
| "max": 0.10862068072000002, |
| "count": 30 |
| }, |
| "Pyramids.Losses.RNDLoss.mean": { |
| "value": 0.012348522432148457, |
| "min": 0.012348522432148457, |
| "max": 0.08281976729631424, |
| "count": 30 |
| }, |
| "Pyramids.Losses.RNDLoss.sum": { |
| "value": 0.17287930846214294, |
| "min": 0.17287930846214294, |
| "max": 0.7453778982162476, |
| "count": 30 |
| }, |
| "Pyramids.Environment.EpisodeLength.mean": { |
| "value": 350.4835164835165, |
| "min": 329.7586206896552, |
| "max": 999.0, |
| "count": 30 |
| }, |
| "Pyramids.Environment.EpisodeLength.sum": { |
| "value": 31894.0, |
| "min": 17581.0, |
| "max": 34156.0, |
| "count": 30 |
| }, |
| "Pyramids.Environment.CumulativeReward.mean": { |
| "value": 1.6275296555115626, |
| "min": -0.9997250507585704, |
| "max": 1.647245955021902, |
| "count": 30 |
| }, |
| "Pyramids.Environment.CumulativeReward.sum": { |
| "value": 148.1051986515522, |
| "min": -31.991201624274254, |
| "max": 148.1051986515522, |
| "count": 30 |
| }, |
| "Pyramids.Policy.ExtrinsicReward.mean": { |
| "value": 1.6275296555115626, |
| "min": -0.9997250507585704, |
| "max": 1.647245955021902, |
| "count": 30 |
| }, |
| "Pyramids.Policy.ExtrinsicReward.sum": { |
| "value": 148.1051986515522, |
| "min": -31.991201624274254, |
| "max": 148.1051986515522, |
| "count": 30 |
| }, |
| "Pyramids.Policy.RndReward.mean": { |
| "value": 0.04432048587637677, |
| "min": 0.04321335142686757, |
| "max": 0.8873915572961172, |
| "count": 30 |
| }, |
| "Pyramids.Policy.RndReward.sum": { |
| "value": 4.033164214750286, |
| "min": 3.7595615741374786, |
| "max": 23.118023794144392, |
| "count": 30 |
| }, |
| "Pyramids.IsTraining.mean": { |
| "value": 1.0, |
| "min": 1.0, |
| "max": 1.0, |
| "count": 30 |
| }, |
| "Pyramids.IsTraining.sum": { |
| "value": 1.0, |
| "min": 1.0, |
| "max": 1.0, |
| "count": 30 |
| } |
| }, |
| "metadata": { |
| "timer_format_version": "0.1.0", |
| "start_time_seconds": "1675521826", |
| "python_version": "3.8.16 (default, Dec 7 2022, 01:12:06) \n[GCC 11.3.0]", |
| "command_line_arguments": "/home/antoine/.local/bin/mlagents-learn ./config/ppo/PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids Training --no-graphics --resume", |
| "mlagents_version": "0.29.0", |
| "mlagents_envs_version": "0.29.0", |
| "communication_protocol_version": "1.5.0", |
| "pytorch_version": "1.13.1+cu117", |
| "numpy_version": "1.21.2", |
| "end_time_seconds": "1675523358" |
| }, |
| "total": 1532.0677022159998, |
| "count": 1, |
| "self": 0.2693895850006811, |
| "children": { |
| "run_training.setup": { |
| "total": 0.01934928199989372, |
| "count": 1, |
| "self": 0.01934928199989372 |
| }, |
| "TrainerController.start_learning": { |
| "total": 1531.7789633489992, |
| "count": 1, |
| "self": 1.0567639920045622, |
| "children": { |
| "TrainerController._reset_env": { |
| "total": 2.200875892000113, |
| "count": 1, |
| "self": 2.200875892000113 |
| }, |
| "TrainerController.advance": { |
| "total": 1528.4606921109935, |
| "count": 57924, |
| "self": 1.0319407319966558, |
| "children": { |
| "env_step": { |
| "total": 895.5223525339143, |
| "count": 57924, |
| "self": 728.1857295537957, |
| "children": { |
| "SubprocessEnvManager._take_step": { |
| "total": 166.67853063105122, |
| "count": 57924, |
| "self": 2.80623972815647, |
| "children": { |
| "TorchPolicy.evaluate": { |
| "total": 163.87229090289475, |
| "count": 56908, |
| "self": 82.71855917885023, |
| "children": { |
| "TorchPolicy.sample_actions": { |
| "total": 81.15373172404452, |
| "count": 56908, |
| "self": 81.15373172404452 |
| } |
| } |
| } |
| } |
| }, |
| "workers": { |
| "total": 0.658092349067374, |
| "count": 57924, |
| "self": 0.0, |
| "children": { |
| "worker_root": { |
| "total": 1529.356982861149, |
| "count": 57924, |
| "is_parallel": true, |
| "self": 862.3219712841974, |
| "children": { |
| "run_training.setup": { |
| "total": 0.0, |
| "count": 0, |
| "is_parallel": true, |
| "self": 0.0, |
| "children": { |
| "steps_from_proto": { |
| "total": 0.001134875999923679, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.0004583429990816512, |
| "children": { |
| "_process_rank_one_or_two_observation": { |
| "total": 0.0006765330008420278, |
| "count": 8, |
| "is_parallel": true, |
| "self": 0.0006765330008420278 |
| } |
| } |
| }, |
| "UnityEnvironment.step": { |
| "total": 0.025187721999827772, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.0002006779986913898, |
| "children": { |
| "UnityEnvironment._generate_step_input": { |
| "total": 0.00023382700055663008, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.00023382700055663008 |
| }, |
| "communicator.exchange": { |
| "total": 0.02405777600051806, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.02405777600051806 |
| }, |
| "steps_from_proto": { |
| "total": 0.0006954410000616917, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.00016682799923728453, |
| "children": { |
| "_process_rank_one_or_two_observation": { |
| "total": 0.0005286130008244072, |
| "count": 8, |
| "is_parallel": true, |
| "self": 0.0005286130008244072 |
| } |
| } |
| } |
| } |
| } |
| } |
| }, |
| "UnityEnvironment.step": { |
| "total": 667.0350115769515, |
| "count": 57923, |
| "is_parallel": true, |
| "self": 11.878453123796135, |
| "children": { |
| "UnityEnvironment._generate_step_input": { |
| "total": 8.145748095083945, |
| "count": 57923, |
| "is_parallel": true, |
| "self": 8.145748095083945 |
| }, |
| "communicator.exchange": { |
| "total": 613.0047714201792, |
| "count": 57923, |
| "is_parallel": true, |
| "self": 613.0047714201792 |
| }, |
| "steps_from_proto": { |
| "total": 34.0060389378923, |
| "count": 57923, |
| "is_parallel": true, |
| "self": 8.894773156672272, |
| "children": { |
| "_process_rank_one_or_two_observation": { |
| "total": 25.111265781220027, |
| "count": 463384, |
| "is_parallel": true, |
| "self": 25.111265781220027 |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
| }, |
| "trainer_advance": { |
| "total": 631.9063988450825, |
| "count": 57924, |
| "self": 2.0132381559678834, |
| "children": { |
| "process_trajectory": { |
| "total": 119.09942889010745, |
| "count": 57924, |
| "self": 118.95852554010708, |
| "children": { |
| "RLTrainer._checkpoint": { |
| "total": 0.14090335000037157, |
| "count": 2, |
| "self": 0.14090335000037157 |
| } |
| } |
| }, |
| "_update_policy": { |
| "total": 510.7937317990072, |
| "count": 415, |
| "self": 108.34210230299504, |
| "children": { |
| "TorchPPOOptimizer.update": { |
| "total": 402.4516294960122, |
| "count": 20742, |
| "self": 402.4516294960122 |
| } |
| } |
| } |
| } |
| } |
| } |
| }, |
| "trainer_threads": { |
| "total": 6.30000613455195e-07, |
| "count": 1, |
| "self": 6.30000613455195e-07 |
| }, |
| "TrainerController._save_models": { |
| "total": 0.06063072400047531, |
| "count": 1, |
| "self": 0.0055338040001515765, |
| "children": { |
| "RLTrainer._checkpoint": { |
| "total": 0.055096920000323735, |
| "count": 1, |
| "self": 0.055096920000323735 |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
