{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.6118541359901428, "min": 0.6042649149894714, "max": 1.4877822399139404, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 18443.73046875, "min": 18098.943359375, "max": 45133.36328125, "count": 33 }, "Pyramids.Step.mean": { "value": 989906.0, "min": 29952.0, "max": 989906.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989906.0, "min": 29952.0, "max": 989906.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.01881656050682068, "min": -0.1796354204416275, "max": 0.029924016445875168, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 4.628873825073242, "min": -42.57359313964844, "max": 7.271535873413086, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.0044397288002073765, "min": 0.0044397288002073765, "max": 0.34724897146224976, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 1.0921733379364014, "min": 1.0921733379364014, "max": 82.29800415039062, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.04831282798674822, "min": 0.046394528289342166, "max": 0.05551978501172124, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.676379591814475, "min": 0.3777116785383052, "max": 0.7307206163047039, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.003883398339946455, "min": 1.589634642315128e-05, "max": 0.004364175848704875, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.054367576759250365, "min": 0.00020665250350096663, "max": 0.056703156740331905, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.677461726592862e-06, "min": 7.677461726592862e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010748446417230007, "min": 0.00010748446417230007, "max": 0.0030202826932392, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10255912142857142, "min": 0.10255912142857142, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4358277, "min": 1.3886848, "max": 2.3067608000000006, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00026565623071428586, "min": 0.00026565623071428586, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0037191872300000022, "min": 0.0037191872300000022, "max": 0.10070540392, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.007207625079900026, "min": 0.007207625079900026, "max": 0.3268340229988098, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.10090675204992294, "min": 0.10090675204992294, "max": 2.2878382205963135, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 854.5384615384615, "min": 846.4324324324324, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 33327.0, "min": 15984.0, "max": 33327.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": -0.18343162673868632, "min": -1.0000000521540642, "max": -0.18343162673868632, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": -6.97040181607008, "min": -31.99920167028904, "max": -6.888801530003548, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": -0.18343162673868632, "min": -1.0000000521540642, "max": -0.18343162673868632, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": -6.97040181607008, "min": -31.99920167028904, "max": -6.888801530003548, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.06824262138137496, "min": 0.06824262138137496, "max": 8.22541143745184, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 2.5932196124922484, "min": 2.4320547848474234, "max": 131.60658299922943, "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": "1694363353", "python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [GCC 11.4.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn /content/ml-agents/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": "1694366166" }, "total": 2812.977372434, "count": 1, "self": 0.476228584999717, "children": { "run_training.setup": { "total": 0.0399664040000971, "count": 1, "self": 0.0399664040000971 }, "TrainerController.start_learning": { "total": 2812.461177445, "count": 1, "self": 1.2256547349475113, "children": { "TrainerController._reset_env": { "total": 5.49593650099996, "count": 1, "self": 5.49593650099996 }, "TrainerController.advance": { "total": 2805.646788952052, "count": 63051, "self": 1.2930477770864854, "children": { "env_step": { "total": 1345.6869900680385, "count": 63051, "self": 1241.3889267122195, "children": { "SubprocessEnvManager._take_step": { "total": 103.53551720887754, "count": 63051, "self": 4.430106013912791, "children": { "TorchPolicy.evaluate": { "total": 99.10541119496474, "count": 62549, "self": 99.10541119496474 } } }, "workers": { "total": 0.7625461469415313, "count": 63051, "self": 0.0, "children": { "worker_root": { "total": 2808.0504638270118, "count": 63051, "is_parallel": true, "self": 1672.255148211926, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.002515704000416008, "count": 1, "is_parallel": true, "self": 0.0006441830009862315, "children": { "_process_rank_one_or_two_observation": { "total": 0.0018715209994297766, "count": 8, "is_parallel": true, "self": 0.0018715209994297766 } } }, "UnityEnvironment.step": { "total": 0.04928174599990598, "count": 1, "is_parallel": true, "self": 0.0005867610002496804, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00047460999985560193, "count": 1, "is_parallel": true, "self": 0.00047460999985560193 }, "communicator.exchange": { "total": 0.04631866399995488, "count": 1, "is_parallel": true, "self": 0.04631866399995488 }, "steps_from_proto": { "total": 0.0019017109998458182, "count": 1, "is_parallel": true, "self": 0.0003647819994512247, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015369290003945935, "count": 8, "is_parallel": true, "self": 0.0015369290003945935 } } } } } } }, "UnityEnvironment.step": { "total": 1135.7953156150857, "count": 63050, "is_parallel": true, "self": 33.16466348005497, "children": { "UnityEnvironment._generate_step_input": { "total": 22.829767236831685, "count": 63050, "is_parallel": true, "self": 22.829767236831685 }, "communicator.exchange": { "total": 977.3860234761041, "count": 63050, "is_parallel": true, "self": 977.3860234761041 }, "steps_from_proto": { "total": 102.41486142209487, "count": 63050, "is_parallel": true, "self": 19.590705066998453, "children": { "_process_rank_one_or_two_observation": { "total": 82.82415635509642, "count": 504400, "is_parallel": true, "self": 82.82415635509642 } } } } } } } } } } }, "trainer_advance": { "total": 1458.6667511069268, "count": 63051, "self": 2.0972078068516566, "children": { "process_trajectory": { "total": 103.4259296230739, "count": 63051, "self": 103.21784249007396, "children": { "RLTrainer._checkpoint": { "total": 0.20808713299993542, "count": 2, "self": 0.20808713299993542 } } }, "_update_policy": { "total": 1353.1436136770012, "count": 428, "self": 1017.8563981689113, "children": { "TorchPPOOptimizer.update": { "total": 335.28721550808996, "count": 37510, "self": 335.28721550808996 } } } } } } }, "trainer_threads": { "total": 1.410000550094992e-06, "count": 1, "self": 1.410000550094992e-06 }, "TrainerController._save_models": { "total": 0.0927958470001613, "count": 1, "self": 0.0017123339994213893, "children": { "RLTrainer._checkpoint": { "total": 0.09108351300073991, "count": 1, "self": 0.09108351300073991 } } } } } } }