{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.29529279470443726, "min": 0.29529279470443726, "max": 1.466744065284729, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 8887.1318359375, "min": 8887.1318359375, "max": 44495.1484375, "count": 33 }, "Pyramids.Step.mean": { "value": 989997.0, "min": 29977.0, "max": 989997.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989997.0, "min": 29977.0, "max": 989997.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.4516216814517975, "min": -0.1709778755903244, "max": 0.5972024202346802, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 119.67974853515625, "min": -40.69273376464844, "max": 167.2166748046875, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.016898194327950478, "min": -0.007352360058575869, "max": 0.268647700548172, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 4.478021621704102, "min": -1.9777848720550537, "max": 64.47544860839844, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.07017654815198122, "min": 0.06635188308497338, "max": 0.07264778440141872, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9824716741277371, "min": 0.49177602286371613, "max": 1.0787795265884295, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.015065880895625532, "min": 7.816436311350838e-05, "max": 0.016984816687532142, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.21092233253875745, "min": 0.001016136720475609, "max": 0.23778743362545, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 2.57350974265e-05, "min": 2.57350974265e-05, "max": 0.0009838354301878855, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.000360291363971, "min": 0.000360291363971, "max": 0.0116911982308802, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.1025735, "min": 0.1025735, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.436029, "min": 1.3886848, "max": 2.5691197999999997, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00026709265, "min": 0.00026709265, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0037392970999999995, "min": 0.0037392970999999995, "max": 0.11693506802, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.010832207277417183, "min": 0.010832207277417183, "max": 0.46387335658073425, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.15165090560913086, "min": 0.15165090560913086, "max": 3.2471134662628174, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 403.46666666666664, "min": 323.53333333333336, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30260.0, "min": 16776.0, "max": 32338.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.3297599745790163, "min": -0.9999125520698726, "max": 1.6057687299326062, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 99.73199809342623, "min": -31.997201666235924, "max": 154.1537980735302, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.3297599745790163, "min": -0.9999125520698726, "max": 1.6057687299326062, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 99.73199809342623, "min": -31.997201666235924, "max": 154.1537980735302, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.04582851284377587, "min": 0.03869405331958357, "max": 8.313625031534363, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.4371384632831905, "min": 3.370638190288446, "max": 141.33162553608418, "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": "1675370177", "python_version": "3.8.10 (default, Nov 14 2022, 12:59:47) \n[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": "0.29.0.dev0", "mlagents_envs_version": "0.29.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.8.1+cu102", "numpy_version": "1.21.6", "end_time_seconds": "1675372328" }, "total": 2150.2418567649997, "count": 1, "self": 0.4461873319996812, "children": { "run_training.setup": { "total": 0.11946402600005968, "count": 1, "self": 0.11946402600005968 }, "TrainerController.start_learning": { "total": 2149.676205407, "count": 1, "self": 1.311774699059697, "children": { "TrainerController._reset_env": { "total": 6.333074667000119, "count": 1, "self": 6.333074667000119 }, "TrainerController.advance": { "total": 2141.94625741594, "count": 63817, "self": 1.2845332158763085, "children": { "env_step": { "total": 1472.1067148750255, "count": 63817, "self": 1363.079992458991, "children": { "SubprocessEnvManager._take_step": { "total": 108.21339087602178, "count": 63817, "self": 4.50583641393996, "children": { "TorchPolicy.evaluate": { "total": 103.70755446208182, "count": 62569, "self": 34.994190919168204, "children": { "TorchPolicy.sample_actions": { "total": 68.71336354291361, "count": 62569, "self": 68.71336354291361 } } } } }, "workers": { "total": 0.8133315400127685, "count": 63817, "self": 0.0, "children": { "worker_root": { "total": 2144.9950893770038, "count": 63817, "is_parallel": true, "self": 885.1563557240329, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0019605700001648074, "count": 1, "is_parallel": true, "self": 0.0007492490001368424, "children": { "_process_rank_one_or_two_observation": { "total": 0.001211321000027965, "count": 8, "is_parallel": true, "self": 0.001211321000027965 } } }, "UnityEnvironment.step": { "total": 0.04794792900020184, "count": 1, "is_parallel": true, "self": 0.0004986509998161637, "children": { "UnityEnvironment._generate_step_input": { "total": 0.000439649000099962, "count": 1, "is_parallel": true, "self": 0.000439649000099962 }, "communicator.exchange": { "total": 0.045325726000100985, "count": 1, "is_parallel": true, "self": 0.045325726000100985 }, "steps_from_proto": { "total": 0.0016839030001847277, "count": 1, "is_parallel": true, "self": 0.0004394269999465905, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012444760002381372, "count": 8, "is_parallel": true, "self": 0.0012444760002381372 } } } } } } }, "UnityEnvironment.step": { "total": 1259.8387336529709, "count": 63816, "is_parallel": true, "self": 28.344905088870746, "children": { "UnityEnvironment._generate_step_input": { "total": 24.318936694005515, "count": 63816, "is_parallel": true, "self": 24.318936694005515 }, "communicator.exchange": { "total": 1100.6825599350593, "count": 63816, "is_parallel": true, "self": 1100.6825599350593 }, "steps_from_proto": { "total": 106.49233193503528, "count": 63816, "is_parallel": true, "self": 23.69820164102316, "children": { "_process_rank_one_or_two_observation": { "total": 82.79413029401212, "count": 510528, "is_parallel": true, "self": 82.79413029401212 } } } } } } } } } } }, "trainer_advance": { "total": 668.5550093250381, "count": 63817, "self": 2.372657367022839, "children": { "process_trajectory": { "total": 153.53406783401306, "count": 63817, "self": 153.3383845640128, "children": { "RLTrainer._checkpoint": { "total": 0.1956832700002451, "count": 2, "self": 0.1956832700002451 } } }, "_update_policy": { "total": 512.6482841240022, "count": 453, "self": 196.62581849998423, "children": { "TorchPPOOptimizer.update": { "total": 316.02246562401797, "count": 22812, "self": 316.02246562401797 } } } } } } }, "trainer_threads": { "total": 9.599998520570807e-07, "count": 1, "self": 9.599998520570807e-07 }, "TrainerController._save_models": { "total": 0.08509766499992111, "count": 1, "self": 0.001420862000031775, "children": { "RLTrainer._checkpoint": { "total": 0.08367680299988933, "count": 1, "self": 0.08367680299988933 } } } } } } }