| { | |
| "name": "root", | |
| "gauges": { | |
| "Pyramids.Policy.Entropy.mean": { | |
| "value": 0.47896048426628113, | |
| "min": 0.4614264965057373, | |
| "max": 1.520114541053772, | |
| "count": 33 | |
| }, | |
| "Pyramids.Policy.Entropy.sum": { | |
| "value": 14399.4677734375, | |
| "min": 13717.287109375, | |
| "max": 46114.1953125, | |
| "count": 33 | |
| }, | |
| "Pyramids.Step.mean": { | |
| "value": 989916.0, | |
| "min": 29952.0, | |
| "max": 989916.0, | |
| "count": 33 | |
| }, | |
| "Pyramids.Step.sum": { | |
| "value": 989916.0, | |
| "min": 29952.0, | |
| "max": 989916.0, | |
| "count": 33 | |
| }, | |
| "Pyramids.Policy.ExtrinsicValueEstimate.mean": { | |
| "value": 0.0069882567040622234, | |
| "min": -0.09566480666399002, | |
| "max": 0.07493434101343155, | |
| "count": 33 | |
| }, | |
| "Pyramids.Policy.ExtrinsicValueEstimate.sum": { | |
| "value": 1.6981463432312012, | |
| "min": -22.959552764892578, | |
| "max": 18.35891342163086, | |
| "count": 33 | |
| }, | |
| "Pyramids.Policy.RndValueEstimate.mean": { | |
| "value": 0.01579887419939041, | |
| "min": 0.004303178749978542, | |
| "max": 0.3437757194042206, | |
| "count": 33 | |
| }, | |
| "Pyramids.Policy.RndValueEstimate.sum": { | |
| "value": 3.8391263484954834, | |
| "min": 1.0499756336212158, | |
| "max": 81.47484588623047, | |
| "count": 33 | |
| }, | |
| "Pyramids.Losses.PolicyLoss.mean": { | |
| "value": 0.0665901009616959, | |
| "min": 0.06569635276143805, | |
| "max": 0.07320060241696569, | |
| "count": 33 | |
| }, | |
| "Pyramids.Losses.PolicyLoss.sum": { | |
| "value": 0.9322614134637427, | |
| "min": 0.5124042169187598, | |
| "max": 1.0263862524606178, | |
| "count": 33 | |
| }, | |
| "Pyramids.Losses.ValueLoss.mean": { | |
| "value": 0.004070884649687893, | |
| "min": 0.0003621674075566953, | |
| "max": 0.006026180094609333, | |
| "count": 33 | |
| }, | |
| "Pyramids.Losses.ValueLoss.sum": { | |
| "value": 0.05699238509563051, | |
| "min": 0.003259506668010258, | |
| "max": 0.08436652132453067, | |
| "count": 33 | |
| }, | |
| "Pyramids.Policy.LearningRate.mean": { | |
| "value": 7.265154721171429e-06, | |
| "min": 7.265154721171429e-06, | |
| "max": 0.00029515063018788575, | |
| "count": 33 | |
| }, | |
| "Pyramids.Policy.LearningRate.sum": { | |
| "value": 0.00010171216609640001, | |
| "min": 0.00010171216609640001, | |
| "max": 0.0031401659532781, | |
| "count": 33 | |
| }, | |
| "Pyramids.Policy.Epsilon.mean": { | |
| "value": 0.1024216857142857, | |
| "min": 0.1024216857142857, | |
| "max": 0.19838354285714285, | |
| "count": 33 | |
| }, | |
| "Pyramids.Policy.Epsilon.sum": { | |
| "value": 1.4339035999999998, | |
| "min": 1.3886848, | |
| "max": 2.4426945, | |
| "count": 33 | |
| }, | |
| "Pyramids.Policy.Beta.mean": { | |
| "value": 0.0002519264028571429, | |
| "min": 0.0002519264028571429, | |
| "max": 0.00983851593142857, | |
| "count": 33 | |
| }, | |
| "Pyramids.Policy.Beta.sum": { | |
| "value": 0.003526969640000001, | |
| "min": 0.003526969640000001, | |
| "max": 0.10469751781, | |
| "count": 33 | |
| }, | |
| "Pyramids.Losses.RNDLoss.mean": { | |
| "value": 0.012312233448028564, | |
| "min": 0.012282622046768665, | |
| "max": 0.33306795358657837, | |
| "count": 33 | |
| }, | |
| "Pyramids.Losses.RNDLoss.sum": { | |
| "value": 0.1723712682723999, | |
| "min": 0.1723712682723999, | |
| "max": 2.3314757347106934, | |
| "count": 33 | |
| }, | |
| "Pyramids.Environment.EpisodeLength.mean": { | |
| "value": 851.5277777777778, | |
| "min": 831.1290322580645, | |
| "max": 999.0, | |
| "count": 33 | |
| }, | |
| "Pyramids.Environment.EpisodeLength.sum": { | |
| "value": 30655.0, | |
| "min": 15984.0, | |
| "max": 33431.0, | |
| "count": 33 | |
| }, | |
| "Pyramids.Environment.CumulativeReward.mean": { | |
| "value": -0.1852944940328598, | |
| "min": -1.0000000521540642, | |
| "max": -0.006744480795330471, | |
| "count": 33 | |
| }, | |
| "Pyramids.Environment.CumulativeReward.sum": { | |
| "value": -6.670601785182953, | |
| "min": -31.99920167028904, | |
| "max": -0.24280130863189697, | |
| "count": 33 | |
| }, | |
| "Pyramids.Policy.ExtrinsicReward.mean": { | |
| "value": -0.1852944940328598, | |
| "min": -1.0000000521540642, | |
| "max": -0.006744480795330471, | |
| "count": 33 | |
| }, | |
| "Pyramids.Policy.ExtrinsicReward.sum": { | |
| "value": -6.670601785182953, | |
| "min": -31.99920167028904, | |
| "max": -0.24280130863189697, | |
| "count": 33 | |
| }, | |
| "Pyramids.Policy.RndReward.mean": { | |
| "value": 0.10621002007004184, | |
| "min": 0.10621002007004184, | |
| "max": 6.74397265445441, | |
| "count": 33 | |
| }, | |
| "Pyramids.Policy.RndReward.sum": { | |
| "value": 3.8235607225215062, | |
| "min": 3.809416241943836, | |
| "max": 107.90356247127056, | |
| "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": "1724312267", | |
| "python_version": "3.10.12 | packaged by conda-forge | (main, Jun 23 2023, 22:40:32) [GCC 12.3.0]", | |
| "command_line_arguments": "/home/ai24/miniconda3/envs/hfrl5/bin/mlagents-learn ./config/ppo/PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids Training --no-graphics", | |
| "mlagents_version": "1.1.0.dev0", | |
| "mlagents_envs_version": "1.1.0.dev0", | |
| "communication_protocol_version": "1.5.0", | |
| "pytorch_version": "2.4.0+cu121", | |
| "numpy_version": "1.23.5", | |
| "end_time_seconds": "1724313326" | |
| }, | |
| "total": 1058.6388215419993, | |
| "count": 1, | |
| "self": 0.21766577699963818, | |
| "children": { | |
| "run_training.setup": { | |
| "total": 0.007526123999923584, | |
| "count": 1, | |
| "self": 0.007526123999923584 | |
| }, | |
| "TrainerController.start_learning": { | |
| "total": 1058.4136296409997, | |
| "count": 1, | |
| "self": 0.6477096890539542, | |
| "children": { | |
| "TrainerController._reset_env": { | |
| "total": 1.4656800230004592, | |
| "count": 1, | |
| "self": 1.4656800230004592 | |
| }, | |
| "TrainerController.advance": { | |
| "total": 1056.2557814999454, | |
| "count": 63206, | |
| "self": 0.5535843337220285, | |
| "children": { | |
| "env_step": { | |
| "total": 679.2111876812269, | |
| "count": 63206, | |
| "self": 548.7502468431112, | |
| "children": { | |
| "SubprocessEnvManager._take_step": { | |
| "total": 130.06520477907998, | |
| "count": 63206, | |
| "self": 1.9480628521714607, | |
| "children": { | |
| "TorchPolicy.evaluate": { | |
| "total": 128.11714192690852, | |
| "count": 62576, | |
| "self": 128.11714192690852 | |
| } | |
| } | |
| }, | |
| "workers": { | |
| "total": 0.3957360590356984, | |
| "count": 63206, | |
| "self": 0.0, | |
| "children": { | |
| "worker_root": { | |
| "total": 1056.9356853276977, | |
| "count": 63206, | |
| "is_parallel": true, | |
| "self": 547.4889520576689, | |
| "children": { | |
| "run_training.setup": { | |
| "total": 0.0, | |
| "count": 0, | |
| "is_parallel": true, | |
| "self": 0.0, | |
| "children": { | |
| "steps_from_proto": { | |
| "total": 0.0011627289995885803, | |
| "count": 1, | |
| "is_parallel": true, | |
| "self": 0.0005723660033254419, | |
| "children": { | |
| "_process_rank_one_or_two_observation": { | |
| "total": 0.0005903629962631385, | |
| "count": 8, | |
| "is_parallel": true, | |
| "self": 0.0005903629962631385 | |
| } | |
| } | |
| }, | |
| "UnityEnvironment.step": { | |
| "total": 0.019436378999671433, | |
| "count": 1, | |
| "is_parallel": true, | |
| "self": 0.00013734599906456424, | |
| "children": { | |
| "UnityEnvironment._generate_step_input": { | |
| "total": 0.00019566599985409994, | |
| "count": 1, | |
| "is_parallel": true, | |
| "self": 0.00019566599985409994 | |
| }, | |
| "communicator.exchange": { | |
| "total": 0.018738763000328618, | |
| "count": 1, | |
| "is_parallel": true, | |
| "self": 0.018738763000328618 | |
| }, | |
| "steps_from_proto": { | |
| "total": 0.0003646040004241513, | |
| "count": 1, | |
| "is_parallel": true, | |
| "self": 9.184699865727453e-05, | |
| "children": { | |
| "_process_rank_one_or_two_observation": { | |
| "total": 0.0002727570017668768, | |
| "count": 8, | |
| "is_parallel": true, | |
| "self": 0.0002727570017668768 | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| }, | |
| "UnityEnvironment.step": { | |
| "total": 509.44673327002874, | |
| "count": 63205, | |
| "is_parallel": true, | |
| "self": 7.571770705257222, | |
| "children": { | |
| "UnityEnvironment._generate_step_input": { | |
| "total": 5.232139390056545, | |
| "count": 63205, | |
| "is_parallel": true, | |
| "self": 5.232139390056545 | |
| }, | |
| "communicator.exchange": { | |
| "total": 476.6110483297871, | |
| "count": 63205, | |
| "is_parallel": true, | |
| "self": 476.6110483297871 | |
| }, | |
| "steps_from_proto": { | |
| "total": 20.031774844927895, | |
| "count": 63205, | |
| "is_parallel": true, | |
| "self": 4.559768108249045, | |
| "children": { | |
| "_process_rank_one_or_two_observation": { | |
| "total": 15.47200673667885, | |
| "count": 505640, | |
| "is_parallel": true, | |
| "self": 15.47200673667885 | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| }, | |
| "trainer_advance": { | |
| "total": 376.49100948499654, | |
| "count": 63206, | |
| "self": 1.0926251529854198, | |
| "children": { | |
| "process_trajectory": { | |
| "total": 63.27863102801166, | |
| "count": 63206, | |
| "self": 63.1617281120125, | |
| "children": { | |
| "RLTrainer._checkpoint": { | |
| "total": 0.11690291599916236, | |
| "count": 2, | |
| "self": 0.11690291599916236 | |
| } | |
| } | |
| }, | |
| "_update_policy": { | |
| "total": 312.11975330399946, | |
| "count": 439, | |
| "self": 138.31161594701825, | |
| "children": { | |
| "TorchPPOOptimizer.update": { | |
| "total": 173.8081373569812, | |
| "count": 22827, | |
| "self": 173.8081373569812 | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| }, | |
| "trainer_threads": { | |
| "total": 4.4999978854320943e-07, | |
| "count": 1, | |
| "self": 4.4999978854320943e-07 | |
| }, | |
| "TrainerController._save_models": { | |
| "total": 0.044457979000071646, | |
| "count": 1, | |
| "self": 0.0004818719999093446, | |
| "children": { | |
| "RLTrainer._checkpoint": { | |
| "total": 0.0439761070001623, | |
| "count": 1, | |
| "self": 0.0439761070001623 | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } |