{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.07455726712942123, "min": 0.07132061570882797, "max": 1.3283107280731201, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 2233.13916015625, "min": 2135.053955078125, "max": 40295.6328125, "count": 33 }, "Pyramids.Step.mean": { "value": 989993.0, "min": 29936.0, "max": 989993.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989993.0, "min": 29936.0, "max": 989993.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": -0.07817629724740982, "min": -0.1059875339269638, "max": -0.0019704073201864958, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": -18.84048843383789, "min": -25.437007904052734, "max": -0.46895694732666016, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 2.491220474243164, "min": 1.0348438024520874, "max": 2.539546251296997, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 600.3841552734375, "min": 246.29283142089844, "max": 614.0382080078125, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.065614514083378, "min": 0.0645075750368747, "max": 0.07181220632628539, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9186031971672919, "min": 0.5738096991478857, "max": 1.0172520895281978, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.005526476083120366, "min": 0.0033118486424310637, "max": 0.05471255845147784, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.07737066516368513, "min": 0.046365880994034894, "max": 0.43770046761182274, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.555704624321432e-06, "min": 7.555704624321432e-06, "max": 0.0002949271891909375, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010577986474050005, "min": 0.00010577986474050005, "max": 0.0036340867886378, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.1025185357142857, "min": 0.1025185357142857, "max": 0.19830906250000002, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4352594999999997, "min": 1.4352594999999997, "max": 2.6113622000000003, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00026160171785714296, "min": 0.00026160171785714296, "max": 0.009831075343749999, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.003662424050000001, "min": 0.003662424050000001, "max": 0.12115508378, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 2.4843578338623047, "min": 1.1381711959838867, "max": 2.532205820083618, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 34.781009674072266, "min": 9.105369567871094, "max": 37.70604705810547, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 959.1935483870968, "min": 878.6, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29735.0, "min": 16734.0, "max": 33430.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": -0.8307355313051131, "min": -0.9997677937630685, "max": -0.479148619728429, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": -25.752801470458508, "min": -30.99280160665512, "max": -12.75000087916851, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": -0.8307355313051131, "min": -0.9997677937630685, "max": -0.479148619728429, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": -25.752801470458508, "min": -30.99280160665512, "max": -12.75000087916851, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 24.168192972098627, "min": 12.799532570772701, "max": 25.182880740011893, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 749.2139821350574, "min": 337.66693917661905, "max": 820.8074612617493, "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": "1714982720", "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 Training --no-graphics", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.2.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1714985571" }, "total": 2851.334854015, "count": 1, "self": 0.6444775009995283, "children": { "run_training.setup": { "total": 0.0703482950000307, "count": 1, "self": 0.0703482950000307 }, "TrainerController.start_learning": { "total": 2850.6200282190002, "count": 1, "self": 2.1801448129285745, "children": { "TrainerController._reset_env": { "total": 3.7731822739999643, "count": 1, "self": 3.7731822739999643 }, "TrainerController.advance": { "total": 2844.5752912720714, "count": 63166, "self": 2.4229753350377905, "children": { "env_step": { "total": 1742.0621759190403, "count": 63166, "self": 1579.316787149144, "children": { "SubprocessEnvManager._take_step": { "total": 161.33067456894992, "count": 63166, "self": 7.031003369945893, "children": { "TorchPolicy.evaluate": { "total": 154.29967119900402, "count": 62545, "self": 154.29967119900402 } } }, "workers": { "total": 1.4147142009464915, "count": 63166, "self": 0.0, "children": { "worker_root": { "total": 2844.977574130914, "count": 63166, "is_parallel": true, "self": 1447.7276523028481, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.00715304299978925, "count": 1, "is_parallel": true, "self": 0.0055326729996068025, "children": { "_process_rank_one_or_two_observation": { "total": 0.0016203700001824473, "count": 8, "is_parallel": true, "self": 0.0016203700001824473 } } }, "UnityEnvironment.step": { "total": 0.0657242300001144, "count": 1, "is_parallel": true, "self": 0.0008261030000085157, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005049030000918719, "count": 1, "is_parallel": true, "self": 0.0005049030000918719 }, "communicator.exchange": { "total": 0.06225493700003426, "count": 1, "is_parallel": true, "self": 0.06225493700003426 }, "steps_from_proto": { "total": 0.002138286999979755, "count": 1, "is_parallel": true, "self": 0.0004544600003555388, "children": { "_process_rank_one_or_two_observation": { "total": 0.0016838269996242161, "count": 8, "is_parallel": true, "self": 0.0016838269996242161 } } } } } } }, "UnityEnvironment.step": { "total": 1397.249921828066, "count": 63165, "is_parallel": true, "self": 50.14738497017811, "children": { "UnityEnvironment._generate_step_input": { "total": 27.276636888926532, "count": 63165, "is_parallel": true, "self": 27.276636888926532 }, "communicator.exchange": { "total": 1189.330745613935, "count": 63165, "is_parallel": true, "self": 1189.330745613935 }, "steps_from_proto": { "total": 130.49515435502622, "count": 63165, "is_parallel": true, "self": 27.54295952398047, "children": { "_process_rank_one_or_two_observation": { "total": 102.95219483104574, "count": 505320, "is_parallel": true, "self": 102.95219483104574 } } } } } } } } } } }, "trainer_advance": { "total": 1100.0901400179935, "count": 63166, "self": 4.377121299980672, "children": { "process_trajectory": { "total": 167.10743509001327, "count": 63166, "self": 166.86853313101278, "children": { "RLTrainer._checkpoint": { "total": 0.23890195900048639, "count": 2, "self": 0.23890195900048639 } } }, "_update_policy": { "total": 928.6055836279995, "count": 455, "self": 369.2479338760438, "children": { "TorchPPOOptimizer.update": { "total": 559.3576497519557, "count": 22725, "self": 559.3576497519557 } } } } } } }, "trainer_threads": { "total": 1.2390000847517513e-06, "count": 1, "self": 1.2390000847517513e-06 }, "TrainerController._save_models": { "total": 0.09140862100002778, "count": 1, "self": 0.002121488999819121, "children": { "RLTrainer._checkpoint": { "total": 0.08928713200020866, "count": 1, "self": 0.08928713200020866 } } } } } } }