| { |
| "name": "root", |
| "gauges": { |
| "Pyramids.Policy.Entropy.mean": { |
| "value": 0.7615676522254944, |
| "min": 0.7366476655006409, |
| "max": 1.4750863313674927, |
| "count": 33 |
| }, |
| "Pyramids.Policy.Entropy.sum": { |
| "value": 23041.990234375, |
| "min": 22170.1484375, |
| "max": 44748.21875, |
| "count": 33 |
| }, |
| "Pyramids.Step.mean": { |
| "value": 989941.0, |
| "min": 29952.0, |
| "max": 989941.0, |
| "count": 33 |
| }, |
| "Pyramids.Step.sum": { |
| "value": 989941.0, |
| "min": 29952.0, |
| "max": 989941.0, |
| "count": 33 |
| }, |
| "Pyramids.Policy.ExtrinsicValueEstimate.mean": { |
| "value": 0.1887703686952591, |
| "min": -0.11251546442508698, |
| "max": 0.1887703686952591, |
| "count": 33 |
| }, |
| "Pyramids.Policy.ExtrinsicValueEstimate.sum": { |
| "value": 47.75890350341797, |
| "min": -27.003711700439453, |
| "max": 47.75890350341797, |
| "count": 33 |
| }, |
| "Pyramids.Policy.RndValueEstimate.mean": { |
| "value": 0.35893896222114563, |
| "min": -0.03557216748595238, |
| "max": 0.3744964599609375, |
| "count": 33 |
| }, |
| "Pyramids.Policy.RndValueEstimate.sum": { |
| "value": 90.81155395507812, |
| "min": -8.893041610717773, |
| "max": 90.81155395507812, |
| "count": 33 |
| }, |
| "Pyramids.Losses.PolicyLoss.mean": { |
| "value": 0.07127098914032674, |
| "min": 0.06421439810208167, |
| "max": 0.07406754818855793, |
| "count": 33 |
| }, |
| "Pyramids.Losses.PolicyLoss.sum": { |
| "value": 1.0690648371049012, |
| "min": 0.4993229856267679, |
| "max": 1.0690648371049012, |
| "count": 33 |
| }, |
| "Pyramids.Losses.ValueLoss.mean": { |
| "value": 0.051294526947434735, |
| "min": 0.0004945802782409725, |
| "max": 0.051294526947434735, |
| "count": 33 |
| }, |
| "Pyramids.Losses.ValueLoss.sum": { |
| "value": 0.769417904211521, |
| "min": 0.004451222504168752, |
| "max": 0.769417904211521, |
| "count": 33 |
| }, |
| "Pyramids.Policy.LearningRate.mean": { |
| "value": 7.5077174974599986e-06, |
| "min": 7.5077174974599986e-06, |
| "max": 0.00029515063018788575, |
| "count": 33 |
| }, |
| "Pyramids.Policy.LearningRate.sum": { |
| "value": 0.00011261576246189998, |
| "min": 0.00011261576246189998, |
| "max": 0.0029053566315479, |
| "count": 33 |
| }, |
| "Pyramids.Policy.Epsilon.mean": { |
| "value": 0.10250253999999999, |
| "min": 0.10250253999999999, |
| "max": 0.19838354285714285, |
| "count": 33 |
| }, |
| "Pyramids.Policy.Epsilon.sum": { |
| "value": 1.5375381, |
| "min": 1.3886848, |
| "max": 2.2750547, |
| "count": 33 |
| }, |
| "Pyramids.Policy.Beta.mean": { |
| "value": 0.0002600037459999999, |
| "min": 0.0002600037459999999, |
| "max": 0.00983851593142857, |
| "count": 33 |
| }, |
| "Pyramids.Policy.Beta.sum": { |
| "value": 0.003900056189999999, |
| "min": 0.003900056189999999, |
| "max": 0.09687836479, |
| "count": 33 |
| }, |
| "Pyramids.Losses.RNDLoss.mean": { |
| "value": 0.010838523507118225, |
| "min": 0.010409833863377571, |
| "max": 0.5958119034767151, |
| "count": 33 |
| }, |
| "Pyramids.Losses.RNDLoss.sum": { |
| "value": 0.16257785260677338, |
| "min": 0.1457376778125763, |
| "max": 4.17068338394165, |
| "count": 33 |
| }, |
| "Pyramids.Environment.EpisodeLength.mean": { |
| "value": 612.6666666666666, |
| "min": 612.6666666666666, |
| "max": 999.0, |
| "count": 33 |
| }, |
| "Pyramids.Environment.EpisodeLength.sum": { |
| "value": 27570.0, |
| "min": 15984.0, |
| "max": 32633.0, |
| "count": 33 |
| }, |
| "Pyramids.Environment.CumulativeReward.mean": { |
| "value": 0.9872266377011935, |
| "min": -1.0000000521540642, |
| "max": 0.9872266377011935, |
| "count": 33 |
| }, |
| "Pyramids.Environment.CumulativeReward.sum": { |
| "value": 44.42519869655371, |
| "min": -32.000001668930054, |
| "max": 44.42519869655371, |
| "count": 33 |
| }, |
| "Pyramids.Policy.ExtrinsicReward.mean": { |
| "value": 0.9872266377011935, |
| "min": -1.0000000521540642, |
| "max": 0.9872266377011935, |
| "count": 33 |
| }, |
| "Pyramids.Policy.ExtrinsicReward.sum": { |
| "value": 44.42519869655371, |
| "min": -32.000001668930054, |
| "max": 44.42519869655371, |
| "count": 33 |
| }, |
| "Pyramids.Policy.RndReward.mean": { |
| "value": 0.06893579374947068, |
| "min": 0.06893579374947068, |
| "max": 12.16698963008821, |
| "count": 33 |
| }, |
| "Pyramids.Policy.RndReward.sum": { |
| "value": 3.1021107187261805, |
| "min": 3.1021107187261805, |
| "max": 194.67183408141136, |
| "count": 33 |
| }, |
| "Pyramids.IsTraining.mean": { |
| "value": 1.0, |
| "min": 1.0, |
| "max": 1.0, |
| "count": 33 |
| }, |
| "Pyramids.IsTraining.sum": { |
| "value": 1.0, |
| "min": 1.0, |
| "max": 1.0, |
| "count": 33 |
| } |
| }, |
| "metadata": { |
| "timer_format_version": "0.1.0", |
| "start_time_seconds": "1683801402", |
| "python_version": "3.10.11 (main, Apr 5 2023, 14:15:10) [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": "0.31.0.dev0", |
| "mlagents_envs_version": "0.31.0.dev0", |
| "communication_protocol_version": "1.5.0", |
| "pytorch_version": "1.11.0+cu102", |
| "numpy_version": "1.21.2", |
| "end_time_seconds": "1683803364" |
| }, |
| "total": 1962.370647868, |
| "count": 1, |
| "self": 0.894356026999958, |
| "children": { |
| "run_training.setup": { |
| "total": 0.03774204199999076, |
| "count": 1, |
| "self": 0.03774204199999076 |
| }, |
| "TrainerController.start_learning": { |
| "total": 1961.4385497990002, |
| "count": 1, |
| "self": 1.2229321371137303, |
| "children": { |
| "TrainerController._reset_env": { |
| "total": 4.282748813000126, |
| "count": 1, |
| "self": 4.282748813000126 |
| }, |
| "TrainerController.advance": { |
| "total": 1955.7949178448866, |
| "count": 63070, |
| "self": 1.2859526439888214, |
| "children": { |
| "env_step": { |
| "total": 1333.3671643509765, |
| "count": 63070, |
| "self": 1229.526667190859, |
| "children": { |
| "SubprocessEnvManager._take_step": { |
| "total": 103.09123560611351, |
| "count": 63070, |
| "self": 4.589528344928112, |
| "children": { |
| "TorchPolicy.evaluate": { |
| "total": 98.5017072611854, |
| "count": 62562, |
| "self": 98.5017072611854 |
| } |
| } |
| }, |
| "workers": { |
| "total": 0.7492615540040788, |
| "count": 63070, |
| "self": 0.0, |
| "children": { |
| "worker_root": { |
| "total": 1956.6825003117774, |
| "count": 63070, |
| "is_parallel": true, |
| "self": 834.1446016106838, |
| "children": { |
| "run_training.setup": { |
| "total": 0.0, |
| "count": 0, |
| "is_parallel": true, |
| "self": 0.0, |
| "children": { |
| "steps_from_proto": { |
| "total": 0.002035150999745383, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.0006153979993541725, |
| "children": { |
| "_process_rank_one_or_two_observation": { |
| "total": 0.0014197530003912107, |
| "count": 8, |
| "is_parallel": true, |
| "self": 0.0014197530003912107 |
| } |
| } |
| }, |
| "UnityEnvironment.step": { |
| "total": 0.07122674499987625, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.000540603999979794, |
| "children": { |
| "UnityEnvironment._generate_step_input": { |
| "total": 0.00047536900001432514, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.00047536900001432514 |
| }, |
| "communicator.exchange": { |
| "total": 0.0685423830000218, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.0685423830000218 |
| }, |
| "steps_from_proto": { |
| "total": 0.0016683889998603263, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.00036165499932394596, |
| "children": { |
| "_process_rank_one_or_two_observation": { |
| "total": 0.0013067340005363803, |
| "count": 8, |
| "is_parallel": true, |
| "self": 0.0013067340005363803 |
| } |
| } |
| } |
| } |
| } |
| } |
| }, |
| "UnityEnvironment.step": { |
| "total": 1122.5378987010936, |
| "count": 63069, |
| "is_parallel": true, |
| "self": 30.845594963044732, |
| "children": { |
| "UnityEnvironment._generate_step_input": { |
| "total": 22.414371044051677, |
| "count": 63069, |
| "is_parallel": true, |
| "self": 22.414371044051677 |
| }, |
| "communicator.exchange": { |
| "total": 975.3357322690545, |
| "count": 63069, |
| "is_parallel": true, |
| "self": 975.3357322690545 |
| }, |
| "steps_from_proto": { |
| "total": 93.94220042494271, |
| "count": 63069, |
| "is_parallel": true, |
| "self": 18.936389694984427, |
| "children": { |
| "_process_rank_one_or_two_observation": { |
| "total": 75.00581072995828, |
| "count": 504552, |
| "is_parallel": true, |
| "self": 75.00581072995828 |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
| }, |
| "trainer_advance": { |
| "total": 621.1418008499213, |
| "count": 63070, |
| "self": 2.2230571949667137, |
| "children": { |
| "process_trajectory": { |
| "total": 103.50253521395598, |
| "count": 63070, |
| "self": 103.24785130895634, |
| "children": { |
| "RLTrainer._checkpoint": { |
| "total": 0.2546839049996379, |
| "count": 2, |
| "self": 0.2546839049996379 |
| } |
| } |
| }, |
| "_update_policy": { |
| "total": 515.4162084409986, |
| "count": 430, |
| "self": 332.1626408939819, |
| "children": { |
| "TorchPPOOptimizer.update": { |
| "total": 183.2535675470167, |
| "count": 22875, |
| "self": 183.2535675470167 |
| } |
| } |
| } |
| } |
| } |
| } |
| }, |
| "trainer_threads": { |
| "total": 1.3190001482143998e-06, |
| "count": 1, |
| "self": 1.3190001482143998e-06 |
| }, |
| "TrainerController._save_models": { |
| "total": 0.1379496849995121, |
| "count": 1, |
| "self": 0.0019190089997209725, |
| "children": { |
| "RLTrainer._checkpoint": { |
| "total": 0.13603067599979113, |
| "count": 1, |
| "self": 0.13603067599979113 |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
