{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.4075506329536438, "min": 0.4075506329536438, "max": 1.4132094383239746, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 12187.39453125, "min": 12187.39453125, "max": 42871.12109375, "count": 33 }, "Pyramids.Step.mean": { "value": 989982.0, "min": 29939.0, "max": 989982.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989982.0, "min": 29939.0, "max": 989982.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.5386778712272644, "min": -0.2671829164028168, "max": 0.6091722249984741, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 149.75244140625, "min": -63.322349548339844, "max": 169.95904541015625, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.010898862965404987, "min": 0.0042075542733073235, "max": 0.41153910756111145, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 3.029883861541748, "min": 1.1739076375961304, "max": 97.5347671508789, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06908576578049887, "min": 0.06298459114484665, "max": 0.07304096085788013, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9672007209269842, "min": 0.5028603549164535, "max": 1.0526413677531914, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.016135311939569998, "min": 0.0006425521534598854, "max": 0.01688640452407793, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.22589436715397998, "min": 0.008995730148438396, "max": 0.253296067861169, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.311290420078571e-06, "min": 7.311290420078571e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.0001023580658811, "min": 0.0001023580658811, "max": 0.0033732421755859996, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10243706428571431, "min": 0.10243706428571431, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4341189000000003, "min": 1.3886848, "max": 2.4860218, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00025346272214285716, "min": 0.00025346272214285716, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0035484781100000003, "min": 0.0035484781100000003, "max": 0.11245895859999999, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.011436971835792065, "min": 0.011436971835792065, "max": 0.6510106921195984, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.16011761128902435, "min": 0.16011761128902435, "max": 4.557075023651123, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 344.875, "min": 307.7717391304348, "max": 992.1176470588235, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30349.0, "min": 16866.0, "max": 33011.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.6061425080587124, "min": -0.9148933860162894, "max": 1.6307769929883125, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 139.73439820110798, "min": -28.170201621949673, "max": 149.68279860168695, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.6061425080587124, "min": -0.9148933860162894, "max": 1.6307769929883125, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 139.73439820110798, "min": -28.170201621949673, "max": 149.68279860168695, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.04156617743355201, "min": 0.040422598947770894, "max": 13.327419747324551, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.6162574367190246, "min": 3.33990849510883, "max": 226.56613570451736, "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": "1793143914", "python_version": "3.10.12 | packaged by conda-forge | (main, Jun 23 2023, 22:40:32) [GCC 12.3.0]", "command_line_arguments": "/content/mlagents-py310/bin/mlagents-learn ./config/ppo/PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids Training --no-graphics", "mlagents_version": "1.0.0", "mlagents_envs_version": "1.0.0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.2.2+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1793145998" }, "total": 2083.824769514, "count": 1, "self": 0.4793572280000262, "children": { "run_training.setup": { "total": 0.016303518999961852, "count": 1, "self": 0.016303518999961852 }, "TrainerController.start_learning": { "total": 2083.329108767, "count": 1, "self": 1.2011672249996082, "children": { "TrainerController._reset_env": { "total": 1.7243344930000148, "count": 1, "self": 1.7243344930000148 }, "TrainerController.advance": { "total": 2080.319888602, "count": 64026, "self": 1.3756397699758054, "children": { "env_step": { "total": 1483.614604699996, "count": 64026, "self": 1359.6405597020212, "children": { "SubprocessEnvManager._take_step": { "total": 123.21409820897998, "count": 64026, "self": 4.4660732209924845, "children": { "TorchPolicy.evaluate": { "total": 118.74802498798749, "count": 62564, "self": 118.74802498798749 } } }, "workers": { "total": 0.7599467889950802, "count": 64026, "self": 0.0, "children": { "worker_root": { "total": 2080.6121975099645, "count": 64026, "is_parallel": true, "self": 826.3084242560044, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0021624460000566614, "count": 1, "is_parallel": true, "self": 0.0007397699999955876, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014226760000610739, "count": 8, "is_parallel": true, "self": 0.0014226760000610739 } } }, "UnityEnvironment.step": { "total": 0.060564215999988846, "count": 1, "is_parallel": true, "self": 0.0006099819999008105, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0025082480000264695, "count": 1, "is_parallel": true, "self": 0.0025082480000264695 }, "communicator.exchange": { "total": 0.05539350000003651, "count": 1, "is_parallel": true, "self": 0.05539350000003651 }, "steps_from_proto": { "total": 0.0020524860000250555, "count": 1, "is_parallel": true, "self": 0.0003708849999384256, "children": { "_process_rank_one_or_two_observation": { "total": 0.00168160100008663, "count": 8, "is_parallel": true, "self": 0.00168160100008663 } } } } } } }, "UnityEnvironment.step": { "total": 1254.3037732539601, "count": 64025, "is_parallel": true, "self": 33.739921221936356, "children": { "UnityEnvironment._generate_step_input": { "total": 22.78136656302081, "count": 64025, "is_parallel": true, "self": 22.78136656302081 }, "communicator.exchange": { "total": 1096.805034853014, "count": 64025, "is_parallel": true, "self": 1096.805034853014 }, "steps_from_proto": { "total": 100.97745061598903, "count": 64025, "is_parallel": true, "self": 20.656929512049487, "children": { "_process_rank_one_or_two_observation": { "total": 80.32052110393954, "count": 512200, "is_parallel": true, "self": 80.32052110393954 } } } } } } } } } } }, "trainer_advance": { "total": 595.3296441320281, "count": 64026, "self": 2.361548293114879, "children": { "process_trajectory": { "total": 119.58027470091247, "count": 64026, "self": 119.39120351891256, "children": { "RLTrainer._checkpoint": { "total": 0.1890711819999069, "count": 2, "self": 0.1890711819999069 } } }, "_update_policy": { "total": 473.38782113800073, "count": 453, "self": 271.2855585329921, "children": { "TorchPPOOptimizer.update": { "total": 202.1022626050086, "count": 22812, "self": 202.1022626050086 } } } } } } }, "trainer_threads": { "total": 1.157000042439904e-06, "count": 1, "self": 1.157000042439904e-06 }, "TrainerController._save_models": { "total": 0.08371729000009509, "count": 1, "self": 0.0013521809996746015, "children": { "RLTrainer._checkpoint": { "total": 0.08236510900042049, "count": 1, "self": 0.08236510900042049 } } } } } } }