{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.18891167640686035, "min": 0.17684133350849152, "max": 1.5110535621643066, "count": 66 }, "Pyramids.Policy.Entropy.sum": { "value": 5640.14697265625, "min": 5282.6044921875, "max": 45839.3203125, "count": 66 }, "Pyramids.Step.mean": { "value": 1979940.0, "min": 29952.0, "max": 1979940.0, "count": 66 }, "Pyramids.Step.sum": { "value": 1979940.0, "min": 29952.0, "max": 1979940.0, "count": 66 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.6915242075920105, "min": -0.1068970113992691, "max": 0.7658700942993164, "count": 66 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 199.15896606445312, "min": -25.655282974243164, "max": 230.5269012451172, "count": 66 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.030494902282953262, "min": -0.00272195041179657, "max": 0.48265042901039124, "count": 66 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 8.78253173828125, "min": -0.7485363483428955, "max": 114.38815307617188, "count": 66 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06731753824925463, "min": 0.06473618129495576, "max": 0.07435470879207803, "count": 66 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 1.0097630737388195, "min": 0.5204829615445462, "max": 1.0532710177746292, "count": 66 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.014686005505953089, "min": 0.00019062917491517435, "max": 0.01607855709018714, "count": 66 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.22029008258929633, "min": 0.0024781792738972665, "max": 0.23825280266464685, "count": 66 }, "Pyramids.Policy.LearningRate.mean": { "value": 5.228848257083338e-06, "min": 5.228848257083338e-06, "max": 0.0002975753150939428, "count": 66 }, "Pyramids.Policy.LearningRate.sum": { "value": 7.843272385625007e-05, "min": 7.843272385625007e-05, "max": 0.0035394336701888504, "count": 66 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10087145833333334, "min": 0.10087145833333334, "max": 0.1495958857142857, "count": 66 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.513071875, "min": 1.0471712, "max": 2.0868438750000005, "count": 66 }, "Pyramids.Policy.Beta.mean": { "value": 0.00018411737500000013, "min": 0.00018411737500000013, "max": 0.009919257965714285, "count": 66 }, "Pyramids.Policy.Beta.sum": { "value": 0.002761760625000002, "min": 0.002761760625000002, "max": 0.118003133885, "count": 66 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.009143485687673092, "min": 0.008826537057757378, "max": 0.5682476162910461, "count": 66 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.1371522843837738, "min": 0.12357151508331299, "max": 3.9777333736419678, "count": 66 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 270.1454545454545, "min": 242.22131147540983, "max": 999.0, "count": 66 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29716.0, "min": 15984.0, "max": 34074.0, "count": 66 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.6752945339137857, "min": -1.0000000521540642, "max": 1.7401817978783087, "count": 66 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 184.28239873051643, "min": -31.99920167028904, "max": 210.44839851558208, "count": 66 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.6752945339137857, "min": -1.0000000521540642, "max": 1.7401817978783087, "count": 66 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 184.28239873051643, "min": -31.99920167028904, "max": 210.44839851558208, "count": 66 }, "Pyramids.Policy.RndReward.mean": { "value": 0.026084950056710195, "min": 0.024309700210669062, "max": 12.210489066317677, "count": 66 }, "Pyramids.Policy.RndReward.sum": { "value": 2.8693445062381215, "min": 2.5831952454827842, "max": 195.36782506108284, "count": 66 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 66 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 66 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1703794145", "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 --force", "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": "1703798893" }, "total": 4747.931961107, "count": 1, "self": 0.4863195040006758, "children": { "run_training.setup": { "total": 0.04818614699979662, "count": 1, "self": 0.04818614699979662 }, "TrainerController.start_learning": { "total": 4747.397455455999, "count": 1, "self": 2.9452523527525045, "children": { "TrainerController._reset_env": { "total": 1.9935149369994178, "count": 1, "self": 1.9935149369994178 }, "TrainerController.advance": { "total": 4742.374269712247, "count": 129295, "self": 3.0485140909013353, "children": { "env_step": { "total": 3460.7321008522304, "count": 129295, "self": 3189.4103073206006, "children": { "SubprocessEnvManager._take_step": { "total": 269.4725381423277, "count": 129295, "self": 10.058822524116295, "children": { "TorchPolicy.evaluate": { "total": 259.4137156182114, "count": 125059, "self": 259.4137156182114 } } }, "workers": { "total": 1.8492553893020158, "count": 129295, "self": 0.0, "children": { "worker_root": { "total": 4736.733146702908, "count": 129295, "is_parallel": true, "self": 1799.8357480438062, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0018275729999004398, "count": 1, "is_parallel": true, "self": 0.0005797880003228784, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012477849995775614, "count": 8, "is_parallel": true, "self": 0.0012477849995775614 } } }, "UnityEnvironment.step": { "total": 0.05308938000052876, "count": 1, "is_parallel": true, "self": 0.0006222820011316799, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004984879997209646, "count": 1, "is_parallel": true, "self": 0.0004984879997209646 }, "communicator.exchange": { "total": 0.050138102999881085, "count": 1, "is_parallel": true, "self": 0.050138102999881085 }, "steps_from_proto": { "total": 0.001830506999795034, "count": 1, "is_parallel": true, "self": 0.0003873210016536177, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014431859981414163, "count": 8, "is_parallel": true, "self": 0.0014431859981414163 } } } } } } }, "UnityEnvironment.step": { "total": 2936.897398659102, "count": 129294, "is_parallel": true, "self": 71.43184985760945, "children": { "UnityEnvironment._generate_step_input": { "total": 52.23215479549435, "count": 129294, "is_parallel": true, "self": 52.23215479549435 }, "communicator.exchange": { "total": 2604.7269187898646, "count": 129294, "is_parallel": true, "self": 2604.7269187898646 }, "steps_from_proto": { "total": 208.50647521613337, "count": 129294, "is_parallel": true, "self": 42.95708791493871, "children": { "_process_rank_one_or_two_observation": { "total": 165.54938730119466, "count": 1034352, "is_parallel": true, "self": 165.54938730119466 } } } } } } } } } } }, "trainer_advance": { "total": 1278.5936547691153, "count": 129295, "self": 5.734748111053705, "children": { "process_trajectory": { "total": 268.78127965707336, "count": 129295, "self": 268.28226629907385, "children": { "RLTrainer._checkpoint": { "total": 0.49901335799950175, "count": 4, "self": 0.49901335799950175 } } }, "_update_policy": { "total": 1004.0776270009883, "count": 919, "self": 594.7395972520089, "children": { "TorchPPOOptimizer.update": { "total": 409.33802974897935, "count": 45579, "self": 409.33802974897935 } } } } } } }, "trainer_threads": { "total": 1.3499993656296283e-06, "count": 1, "self": 1.3499993656296283e-06 }, "TrainerController._save_models": { "total": 0.08441710400074953, "count": 1, "self": 0.002206681001553079, "children": { "RLTrainer._checkpoint": { "total": 0.08221042299919645, "count": 1, "self": 0.08221042299919645 } } } } } } }