{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.4289659857749939, "min": 0.4289659857749939, "max": 1.31809401512146, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 12827.798828125, "min": 12827.798828125, "max": 39985.69921875, "count": 33 }, "Pyramids.Step.mean": { "value": 989912.0, "min": 29952.0, "max": 989912.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989912.0, "min": 29952.0, "max": 989912.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.508364737033844, "min": -0.19363939762115479, "max": 0.5636441111564636, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 139.80030822753906, "min": -45.89253616333008, "max": 156.6930694580078, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.17498508095741272, "min": -0.004486272111535072, "max": 0.6072382926940918, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 48.12089920043945, "min": -1.1439993381500244, "max": 143.9154815673828, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06723515045069646, "min": 0.06648845359588797, "max": 0.07345523796231304, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9412921063097504, "min": 0.508330280637307, "max": 1.0283733314723826, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.01812535998137069, "min": 0.000507436916675891, "max": 0.020018696852882083, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.25375503973918967, "min": 0.0055818060834348015, "max": 0.2802617559403492, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.519254636471429e-06, "min": 7.519254636471429e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010526956491060001, "min": 0.00010526956491060001, "max": 0.0035077898307368, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10250638571428573, "min": 0.10250638571428573, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4350894000000003, "min": 1.3886848, "max": 2.5692632, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002603879328571429, "min": 0.0002603879328571429, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0036454310600000004, "min": 0.0036454310600000004, "max": 0.11694939368, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.012963595800101757, "min": 0.012963595800101757, "max": 0.5573433041572571, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.18149034678936005, "min": 0.18149034678936005, "max": 3.9014031887054443, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 360.0617283950617, "min": 336.04395604395603, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29165.0, "min": 15984.0, "max": 32508.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.5411481364273731, "min": -1.0000000521540642, "max": 1.6213487612038124, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 124.83299905061722, "min": -31.99920167028904, "max": 147.4189984947443, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.5411481364273731, "min": -1.0000000521540642, "max": 1.6213487612038124, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 124.83299905061722, "min": -31.99920167028904, "max": 147.4189984947443, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.04818870840927609, "min": 0.04584684555775711, "max": 11.247974168509245, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.9032853811513633, "min": 3.9032853811513633, "max": 179.96758669614792, "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": "1711621065", "python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [GCC 11.4.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/PyramidsRND.yaml --env=./training-envs-executable/linux/Pyramids/Pyramids --run-id=PyramidsTraining --no-graphics", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.2.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1711623249" }, "total": 2183.79927541, "count": 1, "self": 0.5281713340004899, "children": { "run_training.setup": { "total": 0.04975011800001994, "count": 1, "self": 0.04975011800001994 }, "TrainerController.start_learning": { "total": 2183.221353958, "count": 1, "self": 1.3033407250240998, "children": { "TrainerController._reset_env": { "total": 2.8682284879999997, "count": 1, "self": 2.8682284879999997 }, "TrainerController.advance": { "total": 2178.9671756909756, "count": 63747, "self": 1.3575641439238098, "children": { "env_step": { "total": 1559.7008290100096, "count": 63747, "self": 1430.8532502829635, "children": { "SubprocessEnvManager._take_step": { "total": 128.03548417902869, "count": 63747, "self": 4.585432906048027, "children": { "TorchPolicy.evaluate": { "total": 123.45005127298066, "count": 62561, "self": 123.45005127298066 } } }, "workers": { "total": 0.8120945480175124, "count": 63747, "self": 0.0, "children": { "worker_root": { "total": 2178.3120208219507, "count": 63747, "is_parallel": true, "self": 864.9351713520091, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.007843702999934976, "count": 1, "is_parallel": true, "self": 0.004084966999812423, "children": { "_process_rank_one_or_two_observation": { "total": 0.0037587360001225534, "count": 8, "is_parallel": true, "self": 0.0037587360001225534 } } }, "UnityEnvironment.step": { "total": 0.0802447519999987, "count": 1, "is_parallel": true, "self": 0.0007285710000815016, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004132469999831301, "count": 1, "is_parallel": true, "self": 0.0004132469999831301 }, "communicator.exchange": { "total": 0.07637481099993693, "count": 1, "is_parallel": true, "self": 0.07637481099993693 }, "steps_from_proto": { "total": 0.00272812299999714, "count": 1, "is_parallel": true, "self": 0.00040108599978339043, "children": { "_process_rank_one_or_two_observation": { "total": 0.0023270370002137497, "count": 8, "is_parallel": true, "self": 0.0023270370002137497 } } } } } } }, "UnityEnvironment.step": { "total": 1313.3768494699416, "count": 63746, "is_parallel": true, "self": 34.13095525298968, "children": { "UnityEnvironment._generate_step_input": { "total": 23.306391009997355, "count": 63746, "is_parallel": true, "self": 23.306391009997355 }, "communicator.exchange": { "total": 1158.5245717029602, "count": 63746, "is_parallel": true, "self": 1158.5245717029602 }, "steps_from_proto": { "total": 97.41493150399435, "count": 63746, "is_parallel": true, "self": 19.4339367030866, "children": { "_process_rank_one_or_two_observation": { "total": 77.98099480090775, "count": 509968, "is_parallel": true, "self": 77.98099480090775 } } } } } } } } } } }, "trainer_advance": { "total": 617.908782537042, "count": 63747, "self": 2.615125084057695, "children": { "process_trajectory": { "total": 126.1011633499819, "count": 63747, "self": 125.75416057098153, "children": { "RLTrainer._checkpoint": { "total": 0.3470027790003769, "count": 2, "self": 0.3470027790003769 } } }, "_update_policy": { "total": 489.19249410300245, "count": 451, "self": 284.8845118409936, "children": { "TorchPPOOptimizer.update": { "total": 204.30798226200886, "count": 22809, "self": 204.30798226200886 } } } } } } }, "trainer_threads": { "total": 1.193000116472831e-06, "count": 1, "self": 1.193000116472831e-06 }, "TrainerController._save_models": { "total": 0.08260786099981487, "count": 1, "self": 0.0013252549997559981, "children": { "RLTrainer._checkpoint": { "total": 0.08128260600005888, "count": 1, "self": 0.08128260600005888 } } } } } } }