{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.3553783595561981, "min": 0.346317857503891, "max": 1.435851812362671, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 10695.466796875, "min": 10361.830078125, "max": 43558.0, "count": 33 }, "Pyramids.Step.mean": { "value": 989926.0, "min": 29952.0, "max": 989926.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989926.0, "min": 29952.0, "max": 989926.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.43260225653648376, "min": -0.12665030360221863, "max": 0.45175886154174805, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 115.93740844726562, "min": -30.396072387695312, "max": 121.97489166259766, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.005802266299724579, "min": -0.018867891281843185, "max": 0.5685024857521057, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 1.5550073385238647, "min": -4.9245195388793945, "max": 134.73509216308594, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06774500681268465, "min": 0.06405509753229015, "max": 0.07140618503104808, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 1.0161751021902699, "min": 0.4845990476948838, "max": 1.0191539609513711, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.01585449717790147, "min": 0.0004049673634519863, "max": 0.020843925277719305, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.23781745766852205, "min": 0.005669543088327808, "max": 0.23781745766852205, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.461177512973335e-06, "min": 7.461177512973335e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00011191766269460003, "min": 0.00011191766269460003, "max": 0.0032593769135410987, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10248702666666666, "min": 0.10248702666666666, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.5373054, "min": 1.3886848, "max": 2.4012597999999996, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002584539640000001, "min": 0.0002584539640000001, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.003876809460000002, "min": 0.003876809460000002, "max": 0.10866724410999999, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.015416407026350498, "min": 0.015260426327586174, "max": 0.7827287912368774, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.23124609887599945, "min": 0.21364596486091614, "max": 5.479101657867432, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 420.97222222222223, "min": 376.94666666666666, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30310.0, "min": 15984.0, "max": 33183.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.440086082658834, "min": -1.0000000521540642, "max": 1.4896959795554479, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 103.68619795143604, "min": -31.99760165810585, "max": 111.72719846665859, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.440086082658834, "min": -1.0000000521540642, "max": 1.4896959795554479, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 103.68619795143604, "min": -31.99760165810585, "max": 111.72719846665859, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.06699393497122703, "min": 0.06059273347103347, "max": 17.562319481745362, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 4.823563317928347, "min": 4.5444550103275105, "max": 280.9971117079258, "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": "1739108719", "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", "mlagents_version": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.6.0+cu124", "numpy_version": "1.23.5", "end_time_seconds": "1739110904" }, "total": 2184.5702345870004, "count": 1, "self": 0.47835737700006575, "children": { "run_training.setup": { "total": 0.020504545000221697, "count": 1, "self": 0.020504545000221697 }, "TrainerController.start_learning": { "total": 2184.071372665, "count": 1, "self": 1.4008238769870331, "children": { "TrainerController._reset_env": { "total": 2.2087103169997135, "count": 1, "self": 2.2087103169997135 }, "TrainerController.advance": { "total": 2180.3783422570136, "count": 63557, "self": 1.3969407978966046, "children": { "env_step": { "total": 1491.965987681016, "count": 63557, "self": 1336.9593200831728, "children": { "SubprocessEnvManager._take_step": { "total": 154.17217848386326, "count": 63557, "self": 4.625525315905634, "children": { "TorchPolicy.evaluate": { "total": 149.54665316795763, "count": 62556, "self": 149.54665316795763 } } }, "workers": { "total": 0.8344891139799984, "count": 63557, "self": 0.0, "children": { "worker_root": { "total": 2179.0516729129495, "count": 63557, "is_parallel": true, "self": 954.8816518348685, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.00202972100032639, "count": 1, "is_parallel": true, "self": 0.0006579059991054237, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013718150012209662, "count": 8, "is_parallel": true, "self": 0.0013718150012209662 } } }, "UnityEnvironment.step": { "total": 0.047824443000081374, "count": 1, "is_parallel": true, "self": 0.0005000560004191357, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004484719997890352, "count": 1, "is_parallel": true, "self": 0.0004484719997890352 }, "communicator.exchange": { "total": 0.04532555700006924, "count": 1, "is_parallel": true, "self": 0.04532555700006924 }, "steps_from_proto": { "total": 0.001550357999803964, "count": 1, "is_parallel": true, "self": 0.0003488219999780995, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012015359998258646, "count": 8, "is_parallel": true, "self": 0.0012015359998258646 } } } } } } }, "UnityEnvironment.step": { "total": 1224.170021078081, "count": 63556, "is_parallel": true, "self": 30.906059576126154, "children": { "UnityEnvironment._generate_step_input": { "total": 21.977312766067826, "count": 63556, "is_parallel": true, "self": 21.977312766067826 }, "communicator.exchange": { "total": 1078.1902389279762, "count": 63556, "is_parallel": true, "self": 1078.1902389279762 }, "steps_from_proto": { "total": 93.09640980791073, "count": 63556, "is_parallel": true, "self": 18.53123562672681, "children": { "_process_rank_one_or_two_observation": { "total": 74.56517418118392, "count": 508448, "is_parallel": true, "self": 74.56517418118392 } } } } } } } } } } }, "trainer_advance": { "total": 687.015413778101, "count": 63557, "self": 2.6010595190668937, "children": { "process_trajectory": { "total": 127.34816791603635, "count": 63557, "self": 127.1437272340363, "children": { "RLTrainer._checkpoint": { "total": 0.2044406820000404, "count": 2, "self": 0.2044406820000404 } } }, "_update_policy": { "total": 557.0661863429978, "count": 442, "self": 305.59626562004996, "children": { "TorchPPOOptimizer.update": { "total": 251.4699207229478, "count": 22812, "self": 251.4699207229478 } } } } } } }, "trainer_threads": { "total": 8.39999302115757e-07, "count": 1, "self": 8.39999302115757e-07 }, "TrainerController._save_models": { "total": 0.08349537400044937, "count": 1, "self": 0.0013982339996800874, "children": { "RLTrainer._checkpoint": { "total": 0.08209714000076929, "count": 1, "self": 0.08209714000076929 } } } } } } }