{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.2766302824020386, "min": 0.26760774850845337, "max": 1.5275776386260986, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 8254.6474609375, "min": 8165.248046875, "max": 46340.59375, "count": 33 }, "Pyramids.Step.mean": { "value": 989875.0, "min": 29888.0, "max": 989875.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989875.0, "min": 29888.0, "max": 989875.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.7422255873680115, "min": -0.09871438890695572, "max": 0.761667788028717, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 213.76097106933594, "min": -23.395309448242188, "max": 230.78533935546875, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.011955663561820984, "min": -0.008837718516588211, "max": 0.19378523528575897, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 3.4432311058044434, "min": -2.3066444396972656, "max": 46.702239990234375, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06758669480037059, "min": 0.0661322490658742, "max": 0.07477720977229958, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9462137272051883, "min": 0.5531869676610455, "max": 1.0580347109935246, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.015051518361263842, "min": 0.0007227946176846836, "max": 0.01685806785549392, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.2107212570576938, "min": 0.008673535412216203, "max": 0.23851755922078155, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.69730457712143e-06, "min": 7.69730457712143e-06, "max": 0.00029521320159560003, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010776226407970003, "min": 0.00010776226407970003, "max": 0.0035084222305259995, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.1025657357142857, "min": 0.1025657357142857, "max": 0.19840440000000004, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4359202999999998, "min": 1.4359202999999998, "max": 2.5694740000000005, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00026631699785714295, "min": 0.00026631699785714295, "max": 0.00984059956, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0037284379700000016, "min": 0.0037284379700000016, "max": 0.11697045260000002, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.008026245050132275, "min": 0.008026245050132275, "max": 0.3146364390850067, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.11236743628978729, "min": 0.11236743628978729, "max": 2.5170915126800537, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 254.981981981982, "min": 235.72222222222223, "max": 992.4375, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 28303.0, "min": 16815.0, "max": 33668.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.7269927778759517, "min": -0.9308313024230301, "max": 1.7642777675674075, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 191.69619834423065, "min": -29.786601677536964, "max": 222.29899871349335, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.7269927778759517, "min": -0.9308313024230301, "max": 1.7642777675674075, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 191.69619834423065, "min": -29.786601677536964, "max": 222.29899871349335, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.02132826999680932, "min": 0.0204191976035728, "max": 6.573728427290916, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 2.3674379696458345, "min": 2.3674379696458345, "max": 111.75338326394558, "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": "1687478475", "python_version": "3.10.12 (main, Jun 7 2023, 12:45:35) [GCC 9.4.0]", "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": "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": "1687480919" }, "total": 2444.300342024, "count": 1, "self": 0.47918474300058733, "children": { "run_training.setup": { "total": 0.042064614000082656, "count": 1, "self": 0.042064614000082656 }, "TrainerController.start_learning": { "total": 2443.7790926669995, "count": 1, "self": 1.5083776370379383, "children": { "TrainerController._reset_env": { "total": 4.068206929000098, "count": 1, "self": 4.068206929000098 }, "TrainerController.advance": { "total": 2438.0949945889615, "count": 64484, "self": 1.4613222468406093, "children": { "env_step": { "total": 1783.325123373119, "count": 64484, "self": 1664.8109349592023, "children": { "SubprocessEnvManager._take_step": { "total": 117.66057037494215, "count": 64484, "self": 5.129615910935399, "children": { "TorchPolicy.evaluate": { "total": 112.53095446400675, "count": 62583, "self": 112.53095446400675 } } }, "workers": { "total": 0.8536180389744459, "count": 64484, "self": 0.0, "children": { "worker_root": { "total": 2438.2682789369396, "count": 64484, "is_parallel": true, "self": 894.3621622219334, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0019327929999235494, "count": 1, "is_parallel": true, "self": 0.0005304420003540145, "children": { "_process_rank_one_or_two_observation": { "total": 0.001402350999569535, "count": 8, "is_parallel": true, "self": 0.001402350999569535 } } }, "UnityEnvironment.step": { "total": 0.054318982000040705, "count": 1, "is_parallel": true, "self": 0.0008316040000408975, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005919989998801611, "count": 1, "is_parallel": true, "self": 0.0005919989998801611 }, "communicator.exchange": { "total": 0.05023831700009396, "count": 1, "is_parallel": true, "self": 0.05023831700009396 }, "steps_from_proto": { "total": 0.0026570620000256895, "count": 1, "is_parallel": true, "self": 0.00045794099992235715, "children": { "_process_rank_one_or_two_observation": { "total": 0.0021991210001033323, "count": 8, "is_parallel": true, "self": 0.0021991210001033323 } } } } } } }, "UnityEnvironment.step": { "total": 1543.9061167150062, "count": 64483, "is_parallel": true, "self": 35.51183677706649, "children": { "UnityEnvironment._generate_step_input": { "total": 24.98985187994117, "count": 64483, "is_parallel": true, "self": 24.98985187994117 }, "communicator.exchange": { "total": 1372.3318560559785, "count": 64483, "is_parallel": true, "self": 1372.3318560559785 }, "steps_from_proto": { "total": 111.07257200202002, "count": 64483, "is_parallel": true, "self": 22.521818831923383, "children": { "_process_rank_one_or_two_observation": { "total": 88.55075317009664, "count": 515864, "is_parallel": true, "self": 88.55075317009664 } } } } } } } } } } }, "trainer_advance": { "total": 653.3085489690022, "count": 64484, "self": 2.811789912981112, "children": { "process_trajectory": { "total": 118.82583346602769, "count": 64484, "self": 118.61772979702755, "children": { "RLTrainer._checkpoint": { "total": 0.20810366900013832, "count": 2, "self": 0.20810366900013832 } } }, "_update_policy": { "total": 531.6709255899934, "count": 457, "self": 338.7419542559628, "children": { "TorchPPOOptimizer.update": { "total": 192.92897133403062, "count": 22821, "self": 192.92897133403062 } } } } } } }, "trainer_threads": { "total": 1.1519996405695565e-06, "count": 1, "self": 1.1519996405695565e-06 }, "TrainerController._save_models": { "total": 0.10751236000032804, "count": 1, "self": 0.002266110999698867, "children": { "RLTrainer._checkpoint": { "total": 0.10524624900062918, "count": 1, "self": 0.10524624900062918 } } } } } } }