{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.4729209244251251, "min": 0.4729209244251251, "max": 1.4945664405822754, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 14021.1591796875, "min": 14021.1591796875, "max": 45339.16796875, "count": 33 }, "Pyramids.Step.mean": { "value": 989955.0, "min": 29952.0, "max": 989955.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989955.0, "min": 29952.0, "max": 989955.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.47509822249412537, "min": -0.10370922833681107, "max": 0.47509822249412537, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 129.22671508789062, "min": -24.682796478271484, "max": 129.22671508789062, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -0.008762816898524761, "min": -0.06769336014986038, "max": 0.2648027241230011, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -2.383486270904541, "min": -18.209514617919922, "max": 63.55265426635742, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06693192906230161, "min": 0.06430447888594833, "max": 0.07397381741972493, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9370470068722225, "min": 0.4793389646285253, "max": 1.0772850778816707, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.016239532993913043, "min": 0.00020331778876221733, "max": 0.0172443276418822, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.2273534619147826, "min": 0.0026431312539088253, "max": 0.24142058698635083, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.601283180557146e-06, "min": 7.601283180557146e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010641796452780004, "min": 0.00010641796452780004, "max": 0.0032246461251179996, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10253372857142855, "min": 0.10253372857142855, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4354721999999998, "min": 1.3691136000000002, "max": 2.3585886, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00026311948428571437, "min": 0.00026311948428571437, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0036836727800000015, "min": 0.0036836727800000015, "max": 0.10750071179999998, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.009761780500411987, "min": 0.009529407136142254, "max": 0.3894886076450348, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.13666492700576782, "min": 0.133411705493927, "max": 2.7264201641082764, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 350.2926829268293, "min": 350.2926829268293, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 28724.0, "min": 15984.0, "max": 33017.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.5758073852386003, "min": -1.0000000521540642, "max": 1.5758073852386003, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 127.64039820432663, "min": -32.000001668930054, "max": 127.64039820432663, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.5758073852386003, "min": -1.0000000521540642, "max": 1.5758073852386003, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 127.64039820432663, "min": -32.000001668930054, "max": 127.64039820432663, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.03521679207627995, "min": 0.03521679207627995, "max": 7.799326696433127, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 2.852560158178676, "min": 2.852560158178676, "max": 124.78922714293003, "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": "1701355861", "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-executables/linux/Pyramids/Pyramids --run-id=Pyramids 1 Training --no-graphics --force", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.1.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1701358765" }, "total": 2903.7680588349995, "count": 1, "self": 0.5298963700006425, "children": { "run_training.setup": { "total": 0.05493593999926816, "count": 1, "self": 0.05493593999926816 }, "TrainerController.start_learning": { "total": 2903.1832265249996, "count": 1, "self": 2.1014258592476835, "children": { "TrainerController._reset_env": { "total": 2.159203424000225, "count": 1, "self": 2.159203424000225 }, "TrainerController.advance": { "total": 2898.843445228751, "count": 63656, "self": 2.1356158223716193, "children": { "env_step": { "total": 1918.6850752592327, "count": 63656, "self": 1779.5253839100296, "children": { "SubprocessEnvManager._take_step": { "total": 137.8975570879411, "count": 63656, "self": 5.903816484798881, "children": { "TorchPolicy.evaluate": { "total": 131.99374060314221, "count": 62553, "self": 131.99374060314221 } } }, "workers": { "total": 1.2621342612619628, "count": 63656, "self": 0.0, "children": { "worker_root": { "total": 2897.752274947219, "count": 63656, "is_parallel": true, "self": 1266.7386992885058, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.004027860999485711, "count": 1, "is_parallel": true, "self": 0.0010848980018636212, "children": { "_process_rank_one_or_two_observation": { "total": 0.0029429629976220895, "count": 8, "is_parallel": true, "self": 0.0029429629976220895 } } }, "UnityEnvironment.step": { "total": 0.05615642900011153, "count": 1, "is_parallel": true, "self": 0.0006614539997826796, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005306700004439335, "count": 1, "is_parallel": true, "self": 0.0005306700004439335 }, "communicator.exchange": { "total": 0.053040733000671025, "count": 1, "is_parallel": true, "self": 0.053040733000671025 }, "steps_from_proto": { "total": 0.001923571999213891, "count": 1, "is_parallel": true, "self": 0.00039870699947641697, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015248649997374741, "count": 8, "is_parallel": true, "self": 0.0015248649997374741 } } } } } } }, "UnityEnvironment.step": { "total": 1631.0135756587133, "count": 63655, "is_parallel": true, "self": 41.47748848514311, "children": { "UnityEnvironment._generate_step_input": { "total": 23.09231164121411, "count": 63655, "is_parallel": true, "self": 23.09231164121411 }, "communicator.exchange": { "total": 1446.7658022952219, "count": 63655, "is_parallel": true, "self": 1446.7658022952219 }, "steps_from_proto": { "total": 119.67797323713421, "count": 63655, "is_parallel": true, "self": 25.081985502212774, "children": { "_process_rank_one_or_two_observation": { "total": 94.59598773492144, "count": 509240, "is_parallel": true, "self": 94.59598773492144 } } } } } } } } } } }, "trainer_advance": { "total": 978.0227541471468, "count": 63656, "self": 3.6171067574414337, "children": { "process_trajectory": { "total": 149.21890759073176, "count": 63656, "self": 149.04684378973252, "children": { "RLTrainer._checkpoint": { "total": 0.1720638009992399, "count": 2, "self": 0.1720638009992399 } } }, "_update_policy": { "total": 825.1867397989736, "count": 438, "self": 354.1286201930543, "children": { "TorchPPOOptimizer.update": { "total": 471.0581196059193, "count": 22863, "self": 471.0581196059193 } } } } } } }, "trainer_threads": { "total": 1.001000782707706e-06, "count": 1, "self": 1.001000782707706e-06 }, "TrainerController._save_models": { "total": 0.0791510119997838, "count": 1, "self": 0.002387088999967091, "children": { "RLTrainer._checkpoint": { "total": 0.07676392299981671, "count": 1, "self": 0.07676392299981671 } } } } } } }