| { | |
| "name": "root", | |
| "gauges": { | |
| "Pyramids.Policy.Entropy.mean": { | |
| "value": 0.2011803835630417, | |
| "min": 0.193767711520195, | |
| "max": 1.5320097208023071, | |
| "count": 100 | |
| }, | |
| "Pyramids.Policy.Entropy.sum": { | |
| "value": 6054.724609375, | |
| "min": 5760.32666015625, | |
| "max": 46475.046875, | |
| "count": 100 | |
| }, | |
| "Pyramids.Step.mean": { | |
| "value": 2999931.0, | |
| "min": 29952.0, | |
| "max": 2999931.0, | |
| "count": 100 | |
| }, | |
| "Pyramids.Step.sum": { | |
| "value": 2999931.0, | |
| "min": 29952.0, | |
| "max": 2999931.0, | |
| "count": 100 | |
| }, | |
| "Pyramids.Policy.ExtrinsicValueEstimate.mean": { | |
| "value": 0.7848445177078247, | |
| "min": -0.1989630162715912, | |
| "max": 0.8722542524337769, | |
| "count": 100 | |
| }, | |
| "Pyramids.Policy.ExtrinsicValueEstimate.sum": { | |
| "value": 233.09881591796875, | |
| "min": -47.15423583984375, | |
| "max": 264.29302978515625, | |
| "count": 100 | |
| }, | |
| "Pyramids.Policy.RndValueEstimate.mean": { | |
| "value": 0.0014284075004979968, | |
| "min": -0.015381427481770515, | |
| "max": 0.24416615068912506, | |
| "count": 100 | |
| }, | |
| "Pyramids.Policy.RndValueEstimate.sum": { | |
| "value": 0.4242370128631592, | |
| "min": -4.59904670715332, | |
| "max": 59.08820724487305, | |
| "count": 100 | |
| }, | |
| "Pyramids.Losses.PolicyLoss.mean": { | |
| "value": 0.06740375975043408, | |
| "min": 0.06378558602277647, | |
| "max": 0.0748494335161153, | |
| "count": 100 | |
| }, | |
| "Pyramids.Losses.PolicyLoss.sum": { | |
| "value": 1.0110563962565113, | |
| "min": 0.5239460346128071, | |
| "max": 1.1151226392248645, | |
| "count": 100 | |
| }, | |
| "Pyramids.Losses.ValueLoss.mean": { | |
| "value": 0.015133762459218917, | |
| "min": 0.0005643838093559204, | |
| "max": 0.017800361092117745, | |
| "count": 100 | |
| }, | |
| "Pyramids.Losses.ValueLoss.sum": { | |
| "value": 0.22700643688828376, | |
| "min": 0.005643838093559204, | |
| "max": 0.24920505528964843, | |
| "count": 100 | |
| }, | |
| "Pyramids.Policy.LearningRate.mean": { | |
| "value": 1.4831661723111103e-06, | |
| "min": 1.4831661723111103e-06, | |
| "max": 0.00029838354339596195, | |
| "count": 100 | |
| }, | |
| "Pyramids.Policy.LearningRate.sum": { | |
| "value": 2.2247492584666655e-05, | |
| "min": 2.2247492584666655e-05, | |
| "max": 0.0037596765467745328, | |
| "count": 100 | |
| }, | |
| "Pyramids.Policy.Epsilon.mean": { | |
| "value": 0.10049435555555555, | |
| "min": 0.10049435555555555, | |
| "max": 0.19946118095238097, | |
| "count": 100 | |
| }, | |
| "Pyramids.Policy.Epsilon.sum": { | |
| "value": 1.5074153333333333, | |
| "min": 1.3962282666666668, | |
| "max": 2.752535466666667, | |
| "count": 100 | |
| }, | |
| "Pyramids.Policy.Beta.mean": { | |
| "value": 5.938611999999997e-05, | |
| "min": 5.938611999999997e-05, | |
| "max": 0.009946171977142856, | |
| "count": 100 | |
| }, | |
| "Pyramids.Policy.Beta.sum": { | |
| "value": 0.0008907917999999996, | |
| "min": 0.0008907917999999996, | |
| "max": 0.12533722412, | |
| "count": 100 | |
| }, | |
| "Pyramids.Losses.RNDLoss.mean": { | |
| "value": 0.005414103157818317, | |
| "min": 0.005414103157818317, | |
| "max": 0.40081527829170227, | |
| "count": 100 | |
| }, | |
| "Pyramids.Losses.RNDLoss.sum": { | |
| "value": 0.08121154457330704, | |
| "min": 0.07452377676963806, | |
| "max": 2.8057069778442383, | |
| "count": 100 | |
| }, | |
| "Pyramids.Environment.EpisodeLength.mean": { | |
| "value": 242.10236220472441, | |
| "min": 206.19285714285715, | |
| "max": 999.0, | |
| "count": 100 | |
| }, | |
| "Pyramids.Environment.EpisodeLength.sum": { | |
| "value": 30747.0, | |
| "min": 15984.0, | |
| "max": 33275.0, | |
| "count": 100 | |
| }, | |
| "Pyramids.Environment.CumulativeReward.mean": { | |
| "value": 1.741038083793625, | |
| "min": -1.0000000521540642, | |
| "max": 1.7938071282846586, | |
| "count": 100 | |
| }, | |
| "Pyramids.Environment.CumulativeReward.sum": { | |
| "value": 219.37079855799675, | |
| "min": -30.999801620841026, | |
| "max": 252.05299857258797, | |
| "count": 100 | |
| }, | |
| "Pyramids.Policy.ExtrinsicReward.mean": { | |
| "value": 1.741038083793625, | |
| "min": -1.0000000521540642, | |
| "max": 1.7938071282846586, | |
| "count": 100 | |
| }, | |
| "Pyramids.Policy.ExtrinsicReward.sum": { | |
| "value": 219.37079855799675, | |
| "min": -30.999801620841026, | |
| "max": 252.05299857258797, | |
| "count": 100 | |
| }, | |
| "Pyramids.Policy.RndReward.mean": { | |
| "value": 0.01365075544869782, | |
| "min": 0.012193944957669773, | |
| "max": 8.253531465306878, | |
| "count": 100 | |
| }, | |
| "Pyramids.Policy.RndReward.sum": { | |
| "value": 1.7199951865359253, | |
| "min": 1.578216268455435, | |
| "max": 132.05650344491005, | |
| "count": 100 | |
| }, | |
| "Pyramids.IsTraining.mean": { | |
| "value": 1.0, | |
| "min": 1.0, | |
| "max": 1.0, | |
| "count": 100 | |
| }, | |
| "Pyramids.IsTraining.sum": { | |
| "value": 1.0, | |
| "min": 1.0, | |
| "max": 1.0, | |
| "count": 100 | |
| } | |
| }, | |
| "metadata": { | |
| "timer_format_version": "0.1.0", | |
| "start_time_seconds": "1718385532", | |
| "python_version": "3.10.14 (main, Jun 14 2024, 18:23:26) [GCC 11.4.0]", | |
| "command_line_arguments": "/home/ivan/.env/hf310/bin/mlagents-learn ./config/ppo/PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids Training --no-graphics --force", | |
| "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": "1718388986" | |
| }, | |
| "total": 3454.202459977998, | |
| "count": 1, | |
| "self": 0.2730079870088957, | |
| "children": { | |
| "run_training.setup": { | |
| "total": 0.016478620993439108, | |
| "count": 1, | |
| "self": 0.016478620993439108 | |
| }, | |
| "TrainerController.start_learning": { | |
| "total": 3453.9129733699956, | |
| "count": 1, | |
| "self": 3.1883098795078695, | |
| "children": { | |
| "TrainerController._reset_env": { | |
| "total": 1.079360159987118, | |
| "count": 1, | |
| "self": 1.079360159987118 | |
| }, | |
| "TrainerController.advance": { | |
| "total": 3449.5827327455045, | |
| "count": 194529, | |
| "self": 3.1571178306476213, | |
| "children": { | |
| "env_step": { | |
| "total": 2299.304055316723, | |
| "count": 194529, | |
| "self": 2036.4229290371295, | |
| "children": { | |
| "SubprocessEnvManager._take_step": { | |
| "total": 260.63575810962357, | |
| "count": 194529, | |
| "self": 8.209688429138623, | |
| "children": { | |
| "TorchPolicy.evaluate": { | |
| "total": 252.42606968048494, | |
| "count": 187559, | |
| "self": 252.42606968048494 | |
| } | |
| } | |
| }, | |
| "workers": { | |
| "total": 2.245368169969879, | |
| "count": 194529, | |
| "self": 0.0, | |
| "children": { | |
| "worker_root": { | |
| "total": 3449.919804409088, | |
| "count": 194529, | |
| "is_parallel": true, | |
| "self": 1638.3160552232293, | |
| "children": { | |
| "run_training.setup": { | |
| "total": 0.0, | |
| "count": 0, | |
| "is_parallel": true, | |
| "self": 0.0, | |
| "children": { | |
| "steps_from_proto": { | |
| "total": 0.0011156299733556807, | |
| "count": 1, | |
| "is_parallel": true, | |
| "self": 0.0003170139971189201, | |
| "children": { | |
| "_process_rank_one_or_two_observation": { | |
| "total": 0.0007986159762367606, | |
| "count": 8, | |
| "is_parallel": true, | |
| "self": 0.0007986159762367606 | |
| } | |
| } | |
| }, | |
| "UnityEnvironment.step": { | |
| "total": 0.02225911198183894, | |
| "count": 1, | |
| "is_parallel": true, | |
| "self": 0.0002020609681494534, | |
| "children": { | |
| "UnityEnvironment._generate_step_input": { | |
| "total": 0.0001858019968494773, | |
| "count": 1, | |
| "is_parallel": true, | |
| "self": 0.0001858019968494773 | |
| }, | |
| "communicator.exchange": { | |
| "total": 0.02120309800375253, | |
| "count": 1, | |
| "is_parallel": true, | |
| "self": 0.02120309800375253 | |
| }, | |
| "steps_from_proto": { | |
| "total": 0.0006681510130874813, | |
| "count": 1, | |
| "is_parallel": true, | |
| "self": 0.00016805896302685142, | |
| "children": { | |
| "_process_rank_one_or_two_observation": { | |
| "total": 0.0005000920500606298, | |
| "count": 8, | |
| "is_parallel": true, | |
| "self": 0.0005000920500606298 | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| }, | |
| "UnityEnvironment.step": { | |
| "total": 1811.6037491858588, | |
| "count": 194528, | |
| "is_parallel": true, | |
| "self": 67.418146585871, | |
| "children": { | |
| "UnityEnvironment._generate_step_input": { | |
| "total": 31.605353854771238, | |
| "count": 194528, | |
| "is_parallel": true, | |
| "self": 31.605353854771238 | |
| }, | |
| "communicator.exchange": { | |
| "total": 1541.537474426499, | |
| "count": 194528, | |
| "is_parallel": true, | |
| "self": 1541.537474426499 | |
| }, | |
| "steps_from_proto": { | |
| "total": 171.04277431871742, | |
| "count": 194528, | |
| "is_parallel": true, | |
| "self": 32.998097137140576, | |
| "children": { | |
| "_process_rank_one_or_two_observation": { | |
| "total": 138.04467718157684, | |
| "count": 1556224, | |
| "is_parallel": true, | |
| "self": 138.04467718157684 | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| }, | |
| "trainer_advance": { | |
| "total": 1147.121559598134, | |
| "count": 194529, | |
| "self": 5.6806608503102325, | |
| "children": { | |
| "process_trajectory": { | |
| "total": 226.40099165728316, | |
| "count": 194529, | |
| "self": 225.89157717325725, | |
| "children": { | |
| "RLTrainer._checkpoint": { | |
| "total": 0.5094144840259105, | |
| "count": 6, | |
| "self": 0.5094144840259105 | |
| } | |
| } | |
| }, | |
| "_update_policy": { | |
| "total": 915.0399070905405, | |
| "count": 1395, | |
| "self": 550.9960433689994, | |
| "children": { | |
| "TorchPPOOptimizer.update": { | |
| "total": 364.04386372154113, | |
| "count": 68442, | |
| "self": 364.04386372154113 | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| }, | |
| "trainer_threads": { | |
| "total": 6.560003384947777e-07, | |
| "count": 1, | |
| "self": 6.560003384947777e-07 | |
| }, | |
| "TrainerController._save_models": { | |
| "total": 0.06256992899579927, | |
| "count": 1, | |
| "self": 0.00104069197550416, | |
| "children": { | |
| "RLTrainer._checkpoint": { | |
| "total": 0.06152923702029511, | |
| "count": 1, | |
| "self": 0.06152923702029511 | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } |