{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.16728255152702332, "min": 0.15525735914707184, "max": 0.21002553403377533, "count": 34 }, "Pyramids.Policy.Entropy.sum": { "value": 5053.271484375, "min": 1868.0673828125, "max": 6280.603515625, "count": 34 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 234.51181102362204, "min": 212.17948717948718, "max": 283.64761904761906, "count": 34 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29783.0, "min": 8275.0, "max": 31880.0, "count": 34 }, "Pyramids.Step.mean": { "value": 2999883.0, "min": 2009983.0, "max": 2999883.0, "count": 34 }, "Pyramids.Step.sum": { "value": 2999883.0, "min": 2009983.0, "max": 2999883.0, "count": 34 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.7479361891746521, "min": 0.6622505784034729, "max": 0.8450698852539062, "count": 34 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 224.380859375, "min": 73.65901184082031, "max": 252.65277099609375, "count": 34 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.005168822593986988, "min": -0.012601537629961967, "max": 0.01932157576084137, "count": 34 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 1.5506467819213867, "min": -3.742656707763672, "max": 5.680543422698975, "count": 34 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.7497338478959452, "min": 1.6608981324566736, "max": 1.787820503497735, "count": 34 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 222.21619868278503, "min": 69.72499963641167, "max": 244.80299776792526, "count": 34 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.7497338478959452, "min": 1.6608981324566736, "max": 1.787820503497735, "count": 34 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 222.21619868278503, "min": 69.72499963641167, "max": 244.80299776792526, "count": 34 }, "Pyramids.Policy.RndReward.mean": { "value": 0.01949155884766532, "min": 0.019372238134383223, "max": 0.028201485868443604, "count": 34 }, "Pyramids.Policy.RndReward.sum": { "value": 2.4754279736534954, "min": 0.8830385050969198, "max": 3.0416997363208793, "count": 34 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.07110694913851966, "min": 0.06405901443975467, "max": 0.07133843297612788, "count": 34 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9954972879392753, "min": 0.27638910769019276, "max": 1.0520664500654675, "count": 34 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.01526131886429302, "min": 0.012369724602710143, "max": 0.016298255188782248, "count": 34 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.21365846410010228, "min": 0.06191515453004589, "max": 0.23520687879257218, "count": 34 }, "Pyramids.Policy.LearningRate.mean": { "value": 1.5590351946404768e-06, "min": 1.5590351946404768e-06, "max": 9.947719184095832e-05, "count": 34 }, "Pyramids.Policy.LearningRate.sum": { "value": 2.1826492724966673e-05, "min": 2.1826492724966673e-05, "max": 0.0014621597126137666, "count": 34 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10051964523809527, "min": 0.10051964523809527, "max": 0.13315904166666664, "count": 34 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4072750333333337, "min": 0.5326361666666666, "max": 1.9873862333333334, "count": 34 }, "Pyramids.Policy.Beta.mean": { "value": 6.191255928571431e-05, "min": 6.191255928571431e-05, "max": 0.0033225882625, "count": 34 }, "Pyramids.Policy.Beta.sum": { "value": 0.0008667758300000004, "min": 0.0008667758300000004, "max": 0.048839884709999996, "count": 34 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.008113382384181023, "min": 0.007795785553753376, "max": 0.010242822580039501, "count": 34 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.11358735710382462, "min": 0.040971290320158005, "max": 0.14452455937862396, "count": 34 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 34 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 34 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1693050399", "python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [GCC 11.4.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=PyramidsTraining --no-graphics --resume", "mlagents_version": "0.31.0.dev0", "mlagents_envs_version": "0.31.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.11.0+cu102", "numpy_version": "1.21.2", "end_time_seconds": "1693053095" }, "total": 2695.543802821001, "count": 1, "self": 1.1324325500017949, "children": { "run_training.setup": { "total": 0.040259501000036835, "count": 1, "self": 0.040259501000036835 }, "TrainerController.start_learning": { "total": 2694.371110769999, "count": 1, "self": 1.6563902417110512, "children": { "TrainerController._reset_env": { "total": 5.44096331899982, "count": 1, "self": 5.44096331899982 }, "TrainerController.advance": { "total": 2687.100431038287, "count": 65705, "self": 1.5864545440545044, "children": { "env_step": { "total": 2001.4026687082624, "count": 65705, "self": 1886.4337987335402, "children": { "SubprocessEnvManager._take_step": { "total": 114.04875525803072, "count": 65705, "self": 4.902434129653557, "children": { "TorchPolicy.evaluate": { "total": 109.14632112837717, "count": 62569, "self": 109.14632112837717 } } }, "workers": { "total": 0.920114716691387, "count": 65705, "self": 0.0, "children": { "worker_root": { "total": 2687.969531494088, "count": 65705, "is_parallel": true, "self": 926.9245235840926, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0019770689996221336, "count": 1, "is_parallel": true, "self": 0.0006251910008359118, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013518779987862217, "count": 8, "is_parallel": true, "self": 0.0013518779987862217 } } }, "UnityEnvironment.step": { "total": 0.08333673800007091, "count": 1, "is_parallel": true, "self": 0.0005924659999436699, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00046607700005552033, "count": 1, "is_parallel": true, "self": 0.00046607700005552033 }, "communicator.exchange": { "total": 0.07168196800012083, "count": 1, "is_parallel": true, "self": 0.07168196800012083 }, "steps_from_proto": { "total": 0.010596226999950886, "count": 1, "is_parallel": true, "self": 0.009075192998352577, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015210340015983093, "count": 8, "is_parallel": true, "self": 0.0015210340015983093 } } } } } } }, "UnityEnvironment.step": { "total": 1761.0450079099955, "count": 65704, "is_parallel": true, "self": 34.77587164081251, "children": { "UnityEnvironment._generate_step_input": { "total": 23.156331481118286, "count": 65704, "is_parallel": true, "self": 23.156331481118286 }, "communicator.exchange": { "total": 1592.8627225269947, "count": 65704, "is_parallel": true, "self": 1592.8627225269947 }, "steps_from_proto": { "total": 110.25008226107002, "count": 65704, "is_parallel": true, "self": 22.365261638236916, "children": { "_process_rank_one_or_two_observation": { "total": 87.8848206228331, "count": 525632, "is_parallel": true, "self": 87.8848206228331 } } } } } } } } } } }, "trainer_advance": { "total": 684.11130778597, "count": 65705, "self": 3.081327651087122, "children": { "process_trajectory": { "total": 120.54025942088992, "count": 65705, "self": 120.27275603989074, "children": { "RLTrainer._checkpoint": { "total": 0.26750338099918736, "count": 2, "self": 0.26750338099918736 } } }, "_update_policy": { "total": 560.4897207139929, "count": 473, "self": 366.8761716950967, "children": { "TorchPPOOptimizer.update": { "total": 193.61354901889626, "count": 22752, "self": 193.61354901889626 } } } } } } }, "trainer_threads": { "total": 2.3588001567986794e-05, "count": 1, "self": 2.3588001567986794e-05 }, "TrainerController._save_models": { "total": 0.1733025829998951, "count": 1, "self": 0.0039729189993522596, "children": { "RLTrainer._checkpoint": { "total": 0.16932966400054283, "count": 1, "self": 0.16932966400054283 } } } } } } }