{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.6250206828117371, "min": 0.5980008244514465, "max": 1.3863393068313599, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 18520.61328125, "min": 18143.96875, "max": 42055.98828125, "count": 33 }, "Pyramids.Step.mean": { "value": 989918.0, "min": 29952.0, "max": 989918.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989918.0, "min": 29952.0, "max": 989918.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.36092233657836914, "min": -0.11305046826601028, "max": 0.36092233657836914, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 94.92257690429688, "min": -26.79296112060547, "max": 94.93196105957031, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.016433294862508774, "min": -0.02295013889670372, "max": 0.5422762632369995, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 4.321956634521484, "min": -5.967036247253418, "max": 128.51947021484375, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.07004198653918685, "min": 0.06461773636770117, "max": 0.07306524962972698, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 1.0506297980878028, "min": 0.4691999833191205, "max": 1.0506297980878028, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.013513708031953927, "min": 0.0005638603203181045, "max": 0.016610162635472426, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.2027056204793089, "min": 0.005074742882862941, "max": 0.23254227689661394, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.580417473226666e-06, "min": 7.580417473226666e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00011370626209839999, "min": 0.00011370626209839999, "max": 0.0035086250304583997, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10252677333333335, "min": 0.10252677333333335, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.5379016000000003, "min": 1.3886848, "max": 2.5695416000000004, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.000262424656, "min": 0.000262424656, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0039363698400000004, "min": 0.0039363698400000004, "max": 0.11697720584, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.0121944360435009, "min": 0.0121944360435009, "max": 0.48069414496421814, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.1829165369272232, "min": 0.17437925934791565, "max": 3.364859104156494, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 476.0, "min": 434.03076923076924, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 31416.0, "min": 15984.0, "max": 33096.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.311815121070002, "min": -1.0000000521540642, "max": 1.473627661053951, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 86.57979799062014, "min": -30.673001691699028, "max": 95.78579796850681, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.311815121070002, "min": -1.0000000521540642, "max": 1.473627661053951, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 86.57979799062014, "min": -30.673001691699028, "max": 95.78579796850681, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.06038140391981208, "min": 0.05606997727882117, "max": 9.462827701121569, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.9851726587075973, "min": 3.644548523123376, "max": 151.4052432179451, "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": "1690702538", "python_version": "3.10.6 (main, May 29 2023, 11:10:38) [GCC 11.3.0]", "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": "0.31.0.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": "1690704684" }, "total": 2146.665549881, "count": 1, "self": 0.7774393679997047, "children": { "run_training.setup": { "total": 0.031940595000151006, "count": 1, "self": 0.031940595000151006 }, "TrainerController.start_learning": { "total": 2145.856169918, "count": 1, "self": 1.3880385020811445, "children": { "TrainerController._reset_env": { "total": 4.234977170000093, "count": 1, "self": 4.234977170000093 }, "TrainerController.advance": { "total": 2140.0772520659184, "count": 63447, "self": 1.3538839539182845, "children": { "env_step": { "total": 1478.6054591480013, "count": 63447, "self": 1369.4531770049402, "children": { "SubprocessEnvManager._take_step": { "total": 108.33309268902735, "count": 63447, "self": 4.684526995035412, "children": { "TorchPolicy.evaluate": { "total": 103.64856569399194, "count": 62545, "self": 103.64856569399194 } } }, "workers": { "total": 0.8191894540336762, "count": 63447, "self": 0.0, "children": { "worker_root": { "total": 2140.9765999859874, "count": 63447, "is_parallel": true, "self": 884.6423490559114, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0017320550000476942, "count": 1, "is_parallel": true, "self": 0.000543917000413785, "children": { "_process_rank_one_or_two_observation": { "total": 0.0011881379996339092, "count": 8, "is_parallel": true, "self": 0.0011881379996339092 } } }, "UnityEnvironment.step": { "total": 0.04741278599999532, "count": 1, "is_parallel": true, "self": 0.0005648250000831467, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004826950000733632, "count": 1, "is_parallel": true, "self": 0.0004826950000733632 }, "communicator.exchange": { "total": 0.04449043099998562, "count": 1, "is_parallel": true, "self": 0.04449043099998562 }, "steps_from_proto": { "total": 0.0018748349998531921, "count": 1, "is_parallel": true, "self": 0.00039123299984566984, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014836020000075223, "count": 8, "is_parallel": true, "self": 0.0014836020000075223 } } } } } } }, "UnityEnvironment.step": { "total": 1256.334250930076, "count": 63446, "is_parallel": true, "self": 34.37239634092407, "children": { "UnityEnvironment._generate_step_input": { "total": 22.89053177104506, "count": 63446, "is_parallel": true, "self": 22.89053177104506 }, "communicator.exchange": { "total": 1098.3270838920764, "count": 63446, "is_parallel": true, "self": 1098.3270838920764 }, "steps_from_proto": { "total": 100.74423892603045, "count": 63446, "is_parallel": true, "self": 20.005360574964698, "children": { "_process_rank_one_or_two_observation": { "total": 80.73887835106575, "count": 507568, "is_parallel": true, "self": 80.73887835106575 } } } } } } } } } } }, "trainer_advance": { "total": 660.1179089639988, "count": 63447, "self": 2.543370839988029, "children": { "process_trajectory": { "total": 109.49104920101263, "count": 63447, "self": 109.15883235301226, "children": { "RLTrainer._checkpoint": { "total": 0.3322168480003711, "count": 2, "self": 0.3322168480003711 } } }, "_update_policy": { "total": 548.0834889229982, "count": 446, "self": 356.67423549105047, "children": { "TorchPPOOptimizer.update": { "total": 191.40925343194772, "count": 22752, "self": 191.40925343194772 } } } } } } }, "trainer_threads": { "total": 1.2730001799354795e-06, "count": 1, "self": 1.2730001799354795e-06 }, "TrainerController._save_models": { "total": 0.15590090700015935, "count": 1, "self": 0.001823420000164333, "children": { "RLTrainer._checkpoint": { "total": 0.15407748699999502, "count": 1, "self": 0.15407748699999502 } } } } } } }