{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.19447007775306702, "min": 0.18383972346782684, "max": 0.2861004173755646, "count": 34 }, "Pyramids.Policy.Entropy.sum": { "value": 5871.4404296875, "min": 3007.487548828125, "max": 8052.08837890625, "count": 34 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 229.1851851851852, "min": 217.7846153846154, "max": 295.7943925233645, "count": 34 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30940.0, "min": 7971.0, "max": 32682.0, "count": 34 }, "Pyramids.Step.mean": { "value": 2999945.0, "min": 2009891.0, "max": 2999945.0, "count": 34 }, "Pyramids.Step.sum": { "value": 2999945.0, "min": 2009891.0, "max": 2999945.0, "count": 34 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.7751678824424744, "min": 0.66791170835495, "max": 0.8467879295349121, "count": 34 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 233.32553100585938, "min": 69.88168334960938, "max": 255.72994995117188, "count": 34 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -0.008486342616379261, "min": -0.015169317834079266, "max": 0.009918980300426483, "count": 34 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -2.554389238357544, "min": -4.444610118865967, "max": 2.886423349380493, "count": 34 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.741180732735881, "min": 1.6214789329260064, "max": 1.77858331385586, "count": 34 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 235.05939891934395, "min": 64.02899929881096, "max": 241.55399768054485, "count": 34 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.741180732735881, "min": 1.6214789329260064, "max": 1.77858331385586, "count": 34 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 235.05939891934395, "min": 64.02899929881096, "max": 241.55399768054485, "count": 34 }, "Pyramids.Policy.RndReward.mean": { "value": 0.01038157304531153, "min": 0.00992044427262009, "max": 0.015632113703759387, "count": 34 }, "Pyramids.Policy.RndReward.sum": { "value": 1.4015123611170566, "min": 0.427553438290488, "max": 1.735164621117292, "count": 34 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06890407945562056, "min": 0.06562225044208822, "max": 0.07359485832606807, "count": 34 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 1.0335611918343084, "min": 0.2943794333042723, "max": 1.0683906553210416, "count": 34 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.013979296925176375, "min": 0.010338170142058924, "max": 0.015761167142340975, "count": 34 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.20968945387764562, "min": 0.05070107399432363, "max": 0.23291246707473573, "count": 34 }, "Pyramids.Policy.LearningRate.mean": { "value": 1.4917128361288924e-06, "min": 1.4917128361288924e-06, "max": 9.946254184584165e-05, "count": 34 }, "Pyramids.Policy.LearningRate.sum": { "value": 2.2375692541933385e-05, "min": 2.2375692541933385e-05, "max": 0.0014177664274115332, "count": 34 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10049720444444447, "min": 0.10049720444444447, "max": 0.13315415833333333, "count": 34 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.507458066666667, "min": 0.5326166333333333, "max": 1.9725884666666664, "count": 34 }, "Pyramids.Policy.Beta.mean": { "value": 5.967072400000013e-05, "min": 5.967072400000013e-05, "max": 0.0033221004175, "count": 34 }, "Pyramids.Policy.Beta.sum": { "value": 0.000895060860000002, "min": 0.000895060860000002, "max": 0.04736158782, "count": 34 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.0043326267041265965, "min": 0.003924329299479723, "max": 0.005151048302650452, "count": 34 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.06498940289020538, "min": 0.020344968885183334, "max": 0.07672524452209473, "count": 34 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 34 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 34 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1704542500", "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 --resume", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.1.2+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1704545083" }, "total": 2583.259252974998, "count": 1, "self": 0.4928741639978398, "children": { "run_training.setup": { "total": 0.07088430399926438, "count": 1, "self": 0.07088430399926438 }, "TrainerController.start_learning": { "total": 2582.695494507001, "count": 1, "self": 1.558044161671205, "children": { "TrainerController._reset_env": { "total": 2.6628672189999634, "count": 1, "self": 2.6628672189999634 }, "TrainerController.advance": { "total": 2578.366044042332, "count": 65717, "self": 1.6596024030895933, "children": { "env_step": { "total": 1934.4351272762378, "count": 65717, "self": 1798.0640002781493, "children": { "SubprocessEnvManager._take_step": { "total": 135.42625987509928, "count": 65717, "self": 4.999619346084728, "children": { "TorchPolicy.evaluate": { "total": 130.42664052901455, "count": 62559, "self": 130.42664052901455 } } }, "workers": { "total": 0.944867122989308, "count": 65717, "self": 0.0, "children": { "worker_root": { "total": 2577.1343034877464, "count": 65717, "is_parallel": true, "self": 907.8647695509935, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0021623559987347107, "count": 1, "is_parallel": true, "self": 0.0005556680007430259, "children": { "_process_rank_one_or_two_observation": { "total": 0.0016066879979916848, "count": 8, "is_parallel": true, "self": 0.0016066879979916848 } } }, "UnityEnvironment.step": { "total": 0.054620971000986174, "count": 1, "is_parallel": true, "self": 0.0005905210018681828, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005216879999352386, "count": 1, "is_parallel": true, "self": 0.0005216879999352386 }, "communicator.exchange": { "total": 0.05182303299989144, "count": 1, "is_parallel": true, "self": 0.05182303299989144 }, "steps_from_proto": { "total": 0.0016857289992913138, "count": 1, "is_parallel": true, "self": 0.00035755799945036415, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013281709998409497, "count": 8, "is_parallel": true, "self": 0.0013281709998409497 } } } } } } }, "UnityEnvironment.step": { "total": 1669.2695339367529, "count": 65716, "is_parallel": true, "self": 35.74490044466438, "children": { "UnityEnvironment._generate_step_input": { "total": 26.236024077867114, "count": 65716, "is_parallel": true, "self": 26.236024077867114 }, "communicator.exchange": { "total": 1501.0775967582758, "count": 65716, "is_parallel": true, "self": 1501.0775967582758 }, "steps_from_proto": { "total": 106.21101265594552, "count": 65716, "is_parallel": true, "self": 22.09386625551997, "children": { "_process_rank_one_or_two_observation": { "total": 84.11714640042555, "count": 525728, "is_parallel": true, "self": 84.11714640042555 } } } } } } } } } } }, "trainer_advance": { "total": 642.2713143630044, "count": 65717, "self": 3.1598845891039673, "children": { "process_trajectory": { "total": 138.54325879792668, "count": 65717, "self": 138.33453556292625, "children": { "RLTrainer._checkpoint": { "total": 0.20872323500043422, "count": 2, "self": 0.20872323500043422 } } }, "_update_policy": { "total": 500.56817097597377, "count": 473, "self": 296.00760533089124, "children": { "TorchPPOOptimizer.update": { "total": 204.56056564508253, "count": 22791, "self": 204.56056564508253 } } } } } } }, "trainer_threads": { "total": 9.379982657264918e-07, "count": 1, "self": 9.379982657264918e-07 }, "TrainerController._save_models": { "total": 0.1085381459997734, "count": 1, "self": 0.002584736001153942, "children": { "RLTrainer._checkpoint": { "total": 0.10595340999861946, "count": 1, "self": 0.10595340999861946 } } } } } } }