{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.1425759345293045, "min": 0.12369681894779205, "max": 1.4445167779922485, "count": 100 }, "Pyramids.Policy.Entropy.sum": { "value": 4259.0283203125, "min": 3774.2373046875, "max": 43820.859375, "count": 100 }, "Pyramids.Step.mean": { "value": 2999930.0, "min": 29952.0, "max": 2999930.0, "count": 100 }, "Pyramids.Step.sum": { "value": 2999930.0, "min": 29952.0, "max": 2999930.0, "count": 100 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.6850188374519348, "min": -0.10068638622760773, "max": 0.7707670331001282, "count": 100 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 196.60040283203125, "min": -24.265419006347656, "max": 232.00086975097656, "count": 100 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.014707330614328384, "min": -0.013152971863746643, "max": 0.2346818447113037, "count": 100 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 4.221004009246826, "min": -3.801208734512329, "max": 56.32364273071289, "count": 100 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06774665155916453, "min": 0.06347314301329507, "max": 0.07313320786407632, "count": 100 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9484531218283033, "min": 0.5053947240672203, "max": 1.0969981179611448, "count": 100 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.01566835978536844, "min": 0.0003226696105697404, "max": 0.018183415580497037, "count": 100 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.21935703699515818, "min": 0.003872035326836885, "max": 0.25789668833022006, "count": 100 }, "Pyramids.Policy.LearningRate.mean": { "value": 1.4917566456380958e-06, "min": 1.4917566456380958e-06, "max": 0.00029838354339596195, "count": 100 }, "Pyramids.Policy.LearningRate.sum": { "value": 2.088459303893334e-05, "min": 2.088459303893334e-05, "max": 0.003800496633167833, "count": 100 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10049721904761906, "min": 0.10049721904761906, "max": 0.19946118095238097, "count": 100 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4069610666666668, "min": 1.3962282666666668, "max": 2.7374416333333333, "count": 100 }, "Pyramids.Policy.Beta.mean": { "value": 5.9672182857142894e-05, "min": 5.9672182857142894e-05, "max": 0.009946171977142856, "count": 100 }, "Pyramids.Policy.Beta.sum": { "value": 0.0008354105600000006, "min": 0.0008354105600000006, "max": 0.12669653345, "count": 100 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.003958154935389757, "min": 0.003958154935389757, "max": 0.34865251183509827, "count": 100 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.055414170026779175, "min": 0.055414170026779175, "max": 2.4405674934387207, "count": 100 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 270.42201834862385, "min": 235.06349206349208, "max": 999.0, "count": 100 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29476.0, "min": 15984.0, "max": 33282.0, "count": 100 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.7297818064689636, "min": -1.0000000521540642, "max": 1.7490603086494265, "count": 100 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 190.275998711586, "min": -31.99640166759491, "max": 220.38159888982773, "count": 100 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.7297818064689636, "min": -1.0000000521540642, "max": 1.7490603086494265, "count": 100 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 190.275998711586, "min": -31.99640166759491, "max": 220.38159888982773, "count": 100 }, "Pyramids.Policy.RndReward.mean": { "value": 0.011185747535835783, "min": 0.01055627999448916, "max": 7.119001051411033, "count": 100 }, "Pyramids.Policy.RndReward.sum": { "value": 1.230432228941936, "min": 1.2180342293577269, "max": 113.90401682257652, "count": 100 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 100 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 100 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1711263799", "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": "1711270732" }, "total": 6932.178401962, "count": 1, "self": 0.7554602770005658, "children": { "run_training.setup": { "total": 0.0510294780001459, "count": 1, "self": 0.0510294780001459 }, "TrainerController.start_learning": { "total": 6931.371912207, "count": 1, "self": 4.145228382023561, "children": { "TrainerController._reset_env": { "total": 2.1904738000000634, "count": 1, "self": 2.1904738000000634 }, "TrainerController.advance": { "total": 6924.946475131975, "count": 193655, "self": 4.371817471876966, "children": { "env_step": { "total": 5022.735735885754, "count": 193655, "self": 4635.836239497656, "children": { "SubprocessEnvManager._take_step": { "total": 384.37616857610374, "count": 193655, "self": 13.72823313992717, "children": { "TorchPolicy.evaluate": { "total": 370.64793543617657, "count": 187562, "self": 370.64793543617657 } } }, "workers": { "total": 2.523327811995159, "count": 193655, "self": 0.0, "children": { "worker_root": { "total": 6916.939984790151, "count": 193655, "is_parallel": true, "self": 2636.3323282040365, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0022432670000398502, "count": 1, "is_parallel": true, "self": 0.0006517780002468498, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015914889997930004, "count": 8, "is_parallel": true, "self": 0.0015914889997930004 } } }, "UnityEnvironment.step": { "total": 0.050308270999948945, "count": 1, "is_parallel": true, "self": 0.0006835199997112795, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00043692100007319823, "count": 1, "is_parallel": true, "self": 0.00043692100007319823 }, "communicator.exchange": { "total": 0.047452438000163966, "count": 1, "is_parallel": true, "self": 0.047452438000163966 }, "steps_from_proto": { "total": 0.0017353920000005019, "count": 1, "is_parallel": true, "self": 0.0003847049999876617, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013506870000128401, "count": 8, "is_parallel": true, "self": 0.0013506870000128401 } } } } } } }, "UnityEnvironment.step": { "total": 4280.607656586115, "count": 193654, "is_parallel": true, "self": 104.54350094137499, "children": { "UnityEnvironment._generate_step_input": { "total": 72.08082596068834, "count": 193654, "is_parallel": true, "self": 72.08082596068834 }, "communicator.exchange": { "total": 3800.485416257255, "count": 193654, "is_parallel": true, "self": 3800.485416257255 }, "steps_from_proto": { "total": 303.49791342679623, "count": 193654, "is_parallel": true, "self": 60.940379767842614, "children": { "_process_rank_one_or_two_observation": { "total": 242.55753365895362, "count": 1549232, "is_parallel": true, "self": 242.55753365895362 } } } } } } } } } } }, "trainer_advance": { "total": 1897.8389217743436, "count": 193655, "self": 8.30014565255442, "children": { "process_trajectory": { "total": 389.39133063177974, "count": 193655, "self": 388.8272138427799, "children": { "RLTrainer._checkpoint": { "total": 0.5641167889998542, "count": 6, "self": 0.5641167889998542 } } }, "_update_policy": { "total": 1500.1474454900094, "count": 1390, "self": 879.1641519109266, "children": { "TorchPPOOptimizer.update": { "total": 620.9832935790828, "count": 68400, "self": 620.9832935790828 } } } } } } }, "trainer_threads": { "total": 9.619998309062794e-07, "count": 1, "self": 9.619998309062794e-07 }, "TrainerController._save_models": { "total": 0.08973393100131943, "count": 1, "self": 0.0017437570004403824, "children": { "RLTrainer._checkpoint": { "total": 0.08799017400087905, "count": 1, "self": 0.08799017400087905 } } } } } } }