{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.11727878451347351, "min": 0.11537830531597137, "max": 1.3033181428909302, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 3512.734130859375, "min": 3455.81103515625, "max": 39537.4609375, "count": 33 }, "Pyramids.Step.mean": { "value": 989939.0, "min": 29875.0, "max": 989939.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989939.0, "min": 29875.0, "max": 989939.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": -0.08393924683332443, "min": -0.10330682247877121, "max": 0.019485486671328545, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": -20.14542007446289, "min": -24.793638229370117, "max": 4.69600248336792, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 1.6878089904785156, "min": 1.048180341720581, "max": 1.763006567955017, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 405.07415771484375, "min": 248.4187469482422, "max": 423.12158203125, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06541793363649298, "min": 0.06453725416906222, "max": 0.07317445483948312, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9158510709109017, "min": 0.5779221702859627, "max": 1.0783769823188492, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.011727771771024924, "min": 0.008855445069724315, "max": 0.052297414268774, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.16418880479434894, "min": 0.0949367318950128, "max": 0.418379314150192, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.4157975281e-06, "min": 7.4157975281e-06, "max": 0.0002948486642171125, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010382116539339999, "min": 0.00010382116539339999, "max": 0.0032247289250903997, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10247189999999999, "min": 0.10247189999999999, "max": 0.1982828875, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4346066, "min": 1.4346066, "max": 2.3594592, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00025694281000000004, "min": 0.00025694281000000004, "max": 0.009828460461249999, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0035971993400000005, "min": 0.0035971993400000005, "max": 0.10750346904000001, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 1.7030973434448242, "min": 1.1904410123825073, "max": 1.7541483640670776, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 23.84336280822754, "min": 9.523528099060059, "max": 25.720483779907227, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 985.4516129032259, "min": 915.5294117647059, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30549.0, "min": 16418.0, "max": 32519.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": -0.9213419854640961, "min": -0.999962551984936, "max": -0.5571250508073717, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": -28.561601549386978, "min": -31.998801663517952, "max": -14.434000805020332, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": -0.9213419854640961, "min": -0.999962551984936, "max": -0.5571250508073717, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": -28.561601549386978, "min": -31.998801663517952, "max": -14.434000805020332, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 16.759374566999593, "min": 11.888948411680758, "max": 19.582620084285736, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 519.5406115769874, "min": 332.9045414328575, "max": 536.1754525303841, "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": "1748631886", "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]", "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 --force", "mlagents_version": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.7.0+cu126", "numpy_version": "1.23.5", "end_time_seconds": "1748634002" }, "total": 2115.6378455759996, "count": 1, "self": 0.47689184700084297, "children": { "run_training.setup": { "total": 0.02150907599934726, "count": 1, "self": 0.02150907599934726 }, "TrainerController.start_learning": { "total": 2115.1394446529994, "count": 1, "self": 1.352522110897553, "children": { "TrainerController._reset_env": { "total": 2.5895411110004716, "count": 1, "self": 2.5895411110004716 }, "TrainerController.advance": { "total": 2111.1148638371005, "count": 63259, "self": 1.540222501230346, "children": { "env_step": { "total": 1442.6756700799697, "count": 63259, "self": 1289.0098628557507, "children": { "SubprocessEnvManager._take_step": { "total": 152.87008870005047, "count": 63259, "self": 4.574176225962219, "children": { "TorchPolicy.evaluate": { "total": 148.29591247408825, "count": 62580, "self": 148.29591247408825 } } }, "workers": { "total": 0.7957185241684783, "count": 63259, "self": 0.0, "children": { "worker_root": { "total": 2110.3995245019187, "count": 63259, "is_parallel": true, "self": 932.1839104439587, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.001917501999741944, "count": 1, "is_parallel": true, "self": 0.0006387780003933585, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012787239993485855, "count": 8, "is_parallel": true, "self": 0.0012787239993485855 } } }, "UnityEnvironment.step": { "total": 0.09024574399973062, "count": 1, "is_parallel": true, "self": 0.000537002999408287, "children": { "UnityEnvironment._generate_step_input": { "total": 0.000397312000131933, "count": 1, "is_parallel": true, "self": 0.000397312000131933 }, "communicator.exchange": { "total": 0.0877936150000096, "count": 1, "is_parallel": true, "self": 0.0877936150000096 }, "steps_from_proto": { "total": 0.001517814000180806, "count": 1, "is_parallel": true, "self": 0.0002998710006067995, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012179429995740065, "count": 8, "is_parallel": true, "self": 0.0012179429995740065 } } } } } } }, "UnityEnvironment.step": { "total": 1178.21561405796, "count": 63258, "is_parallel": true, "self": 31.132442607053235, "children": { "UnityEnvironment._generate_step_input": { "total": 22.41987773017354, "count": 63258, "is_parallel": true, "self": 22.41987773017354 }, "communicator.exchange": { "total": 1030.7513862279557, "count": 63258, "is_parallel": true, "self": 1030.7513862279557 }, "steps_from_proto": { "total": 93.91190749277757, "count": 63258, "is_parallel": true, "self": 18.806460532749952, "children": { "_process_rank_one_or_two_observation": { "total": 75.10544696002762, "count": 506064, "is_parallel": true, "self": 75.10544696002762 } } } } } } } } } } }, "trainer_advance": { "total": 666.8989712559005, "count": 63259, "self": 2.457798588948208, "children": { "process_trajectory": { "total": 127.16368415295256, "count": 63259, "self": 126.96304914595203, "children": { "RLTrainer._checkpoint": { "total": 0.20063500700052828, "count": 2, "self": 0.20063500700052828 } } }, "_update_policy": { "total": 537.2774885139997, "count": 442, "self": 299.0454969221173, "children": { "TorchPPOOptimizer.update": { "total": 238.23199159188243, "count": 22794, "self": 238.23199159188243 } } } } } } }, "trainer_threads": { "total": 9.780005711945705e-07, "count": 1, "self": 9.780005711945705e-07 }, "TrainerController._save_models": { "total": 0.08251661600024818, "count": 1, "self": 0.0018325820001336979, "children": { "RLTrainer._checkpoint": { "total": 0.08068403400011448, "count": 1, "self": 0.08068403400011448 } } } } } } }