{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.2420235425233841, "min": 0.2252901792526245, "max": 1.3850210905075073, "count": 50 }, "Pyramids.Policy.Entropy.sum": { "value": 7225.85498046875, "min": 6701.03125, "max": 42016.0, "count": 50 }, "Pyramids.Step.mean": { "value": 1499927.0, "min": 29952.0, "max": 1499927.0, "count": 50 }, "Pyramids.Step.sum": { "value": 1499927.0, "min": 29952.0, "max": 1499927.0, "count": 50 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.699270486831665, "min": -0.09082455188035965, "max": 0.790700376033783, "count": 50 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 203.4877166748047, "min": -21.888717651367188, "max": 239.58221435546875, "count": 50 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.007752297446131706, "min": -0.0003571129927877337, "max": 0.29707929491996765, "count": 50 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 2.255918502807617, "min": -0.1046341061592102, "max": 71.59610748291016, "count": 50 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06614539291851024, "min": 0.0647650169185683, "max": 0.07733903615872025, "count": 50 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9260355008591433, "min": 0.49341082538330217, "max": 1.0827465062220833, "count": 50 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.015098810502552492, "min": 0.0008368462105235164, "max": 0.0180267707114884, "count": 50 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.2113833470357349, "min": 0.00920530831575868, "max": 0.270401560672326, "count": 50 }, "Pyramids.Policy.LearningRate.mean": { "value": 0.00015144260666200476, "min": 0.00015144260666200476, "max": 0.00029838354339596195, "count": 50 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.0021201964932680666, "min": 0.0020886848037717336, "max": 0.0040725322424893, "count": 50 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.15048085238095238, "min": 0.15048085238095238, "max": 0.19946118095238097, "count": 50 }, "Pyramids.Policy.Epsilon.sum": { "value": 2.106731933333333, "min": 1.3962282666666668, "max": 2.8575107000000006, "count": 50 }, "Pyramids.Policy.Beta.mean": { "value": 0.005053037152857142, "min": 0.005053037152857142, "max": 0.009946171977142856, "count": 50 }, "Pyramids.Policy.Beta.sum": { "value": 0.07074252013999999, "min": 0.06962320384, "max": 0.13576531893, "count": 50 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.009045292623341084, "min": 0.009045292623341084, "max": 0.5670269131660461, "count": 50 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.12663409113883972, "min": 0.12663409113883972, "max": 3.9691884517669678, "count": 50 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 265.01785714285717, "min": 245.5609756097561, "max": 999.0, "count": 50 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29682.0, "min": 15984.0, "max": 32406.0, "count": 50 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.7171178497374058, "min": -1.0000000521540642, "max": 1.7347033734165005, "count": 50 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 192.31719917058945, "min": -29.74900161474943, "max": 223.9947980493307, "count": 50 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.7171178497374058, "min": -1.0000000521540642, "max": 1.7347033734165005, "count": 50 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 192.31719917058945, "min": -29.74900161474943, "max": 223.9947980493307, "count": 50 }, "Pyramids.Policy.RndReward.mean": { "value": 0.02488347915498577, "min": 0.023911526658549356, "max": 11.845616444945335, "count": 50 }, "Pyramids.Policy.RndReward.sum": { "value": 2.7869496653584065, "min": 2.7869496653584065, "max": 189.52986311912537, "count": 50 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 50 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 50 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1731518937", "python_version": "3.10.12 (main, Sep 11 2024, 15:47:36) [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": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.5.0+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1731524214" }, "total": 5276.5313382879995, "count": 1, "self": 0.6404445269990902, "children": { "run_training.setup": { "total": 0.0851747910000995, "count": 1, "self": 0.0851747910000995 }, "TrainerController.start_learning": { "total": 5275.80571897, "count": 1, "self": 3.7140206357498755, "children": { "TrainerController._reset_env": { "total": 2.7510618830001476, "count": 1, "self": 2.7510618830001476 }, "TrainerController.advance": { "total": 5269.340263712249, "count": 97207, "self": 3.6612425241137316, "children": { "env_step": { "total": 3638.2077083330587, "count": 97207, "self": 3389.888309416723, "children": { "SubprocessEnvManager._take_step": { "total": 246.25262339826077, "count": 97207, "self": 10.138080488414744, "children": { "TorchPolicy.evaluate": { "total": 236.11454290984602, "count": 94009, "self": 236.11454290984602 } } }, "workers": { "total": 2.0667755180747918, "count": 97206, "self": 0.0, "children": { "worker_root": { "total": 5264.728408751971, "count": 97206, "is_parallel": true, "self": 2139.64836307901, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.002366988999710884, "count": 1, "is_parallel": true, "self": 0.0007567939974251203, "children": { "_process_rank_one_or_two_observation": { "total": 0.0016101950022857636, "count": 8, "is_parallel": true, "self": 0.0016101950022857636 } } }, "UnityEnvironment.step": { "total": 0.060700216999975964, "count": 1, "is_parallel": true, "self": 0.000774199000261433, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005190749998291722, "count": 1, "is_parallel": true, "self": 0.0005190749998291722 }, "communicator.exchange": { "total": 0.057338566999533214, "count": 1, "is_parallel": true, "self": 0.057338566999533214 }, "steps_from_proto": { "total": 0.0020683760003521456, "count": 1, "is_parallel": true, "self": 0.00043154400100320345, "children": { "_process_rank_one_or_two_observation": { "total": 0.0016368319993489422, "count": 8, "is_parallel": true, "self": 0.0016368319993489422 } } } } } } }, "UnityEnvironment.step": { "total": 3125.080045672961, "count": 97205, "is_parallel": true, "self": 72.98485001781864, "children": { "UnityEnvironment._generate_step_input": { "total": 45.5973766119987, "count": 97205, "is_parallel": true, "self": 45.5973766119987 }, "communicator.exchange": { "total": 2811.1031216530528, "count": 97205, "is_parallel": true, "self": 2811.1031216530528 }, "steps_from_proto": { "total": 195.3946973900911, "count": 97205, "is_parallel": true, "self": 42.181809910593984, "children": { "_process_rank_one_or_two_observation": { "total": 153.2128874794971, "count": 777640, "is_parallel": true, "self": 153.2128874794971 } } } } } } } } } } }, "trainer_advance": { "total": 1627.4713128550766, "count": 97206, "self": 7.007601120218169, "children": { "process_trajectory": { "total": 252.08617351287012, "count": 97206, "self": 251.7073947038698, "children": { "RLTrainer._checkpoint": { "total": 0.37877880900032324, "count": 3, "self": 0.37877880900032324 } } }, "_update_policy": { "total": 1368.3775382219883, "count": 691, "self": 555.2198198440856, "children": { "TorchPPOOptimizer.update": { "total": 813.1577183779027, "count": 34272, "self": 813.1577183779027 } } } } } } }, "trainer_threads": { "total": 1.3930002751294523e-06, "count": 1, "self": 1.3930002751294523e-06 }, "TrainerController._save_models": { "total": 0.00037134600097488146, "count": 1, "self": 3.178200131515041e-05, "children": { "RLTrainer._checkpoint": { "total": 0.00033956399965973105, "count": 1, "self": 0.00033956399965973105 } } } } } } }