{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.23576901853084564, "min": 0.23576901853084564, "max": 0.36750328540802, "count": 23 }, "Pyramids.Policy.Entropy.sum": { "value": 7057.9814453125, "min": 7057.9814453125, "max": 10233.427734375, "count": 23 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 329.21505376344084, "min": 302.7551020408163, "max": 478.65714285714284, "count": 23 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30617.0, "min": 13762.0, "max": 33506.0, "count": 23 }, "Pyramids.Step.mean": { "value": 1679903.0, "min": 1019959.0, "max": 1679903.0, "count": 23 }, "Pyramids.Step.sum": { "value": 1679903.0, "min": 1019959.0, "max": 1679903.0, "count": 23 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.6018615961074829, "min": 0.3889569044113159, "max": 0.6184836030006409, "count": 23 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 167.9193878173828, "min": 71.98414611816406, "max": 171.93844604492188, "count": 23 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -0.0008180650766007602, "min": -0.004084211774170399, "max": 0.028206808492541313, "count": 23 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -0.22824016213417053, "min": -1.1272424459457397, "max": 7.644045352935791, "count": 23 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.6277553023810083, "min": 1.321277118580682, "max": 1.6277553023810083, "count": 23 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 153.00899842381477, "min": 58.237999230623245, "max": 159.90779871493578, "count": 23 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.6277553023810083, "min": 1.321277118580682, "max": 1.6277553023810083, "count": 23 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 153.00899842381477, "min": 58.237999230623245, "max": 159.90779871493578, "count": 23 }, "Pyramids.Policy.RndReward.mean": { "value": 0.031048489362682574, "min": 0.03094655353232505, "max": 0.07338713616149367, "count": 23 }, "Pyramids.Policy.RndReward.sum": { "value": 2.918558000092162, "min": 2.089674953633221, "max": 5.137099531304557, "count": 23 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06773896340330664, "min": 0.06412356666405684, "max": 0.07152340681585925, "count": 23 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.948345487646293, "min": 0.6317606997326948, "max": 1.036901918860773, "count": 23 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.01557055618849561, "min": 0.011792417253423526, "max": 0.016712072956752744, "count": 23 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.21798778663893856, "min": 0.11095894096797565, "max": 0.2339690213945384, "count": 23 }, "Pyramids.Policy.LearningRate.mean": { "value": 5.022549397248215e-05, "min": 5.022549397248215e-05, "max": 0.00014842608385798892, "count": 23 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.0007031569156147501, "min": 0.0007031569156147501, "max": 0.00202674837441745, "count": 23 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.11674180357142859, "min": 0.11674180357142859, "max": 0.14947534444444446, "count": 23 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.6343852500000002, "min": 1.3452781000000003, "max": 2.1563334, "count": 23 }, "Pyramids.Policy.Beta.mean": { "value": 0.0016825061767857144, "min": 0.0016825061767857144, "max": 0.00495258691, "count": 23 }, "Pyramids.Policy.Beta.sum": { "value": 0.023555086475, "min": 0.023555086475, "max": 0.067630696745, "count": 23 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.009054279886186123, "min": 0.009054279886186123, "max": 0.014804517850279808, "count": 23 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.12675991654396057, "min": 0.12675991654396057, "max": 0.20726324617862701, "count": 23 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 23 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 23 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1721993125", "python_version": "3.10.12 (main, Mar 22 2024, 16:50:05) [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": "2.3.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1721994768" }, "total": 1642.6813722149996, "count": 1, "self": 0.4982997039987822, "children": { "run_training.setup": { "total": 0.059540038000250206, "count": 1, "self": 0.059540038000250206 }, "TrainerController.start_learning": { "total": 1642.1235324730005, "count": 1, "self": 0.8982533830780994, "children": { "TrainerController._reset_env": { "total": 2.051978708000206, "count": 1, "self": 2.051978708000206 }, "TrainerController.advance": { "total": 1638.7901514449227, "count": 44161, "self": 0.9263329430473277, "children": { "env_step": { "total": 1199.851026489871, "count": 44161, "self": 1109.8131978896654, "children": { "SubprocessEnvManager._take_step": { "total": 89.51381826909846, "count": 44161, "self": 3.1261631671336545, "children": { "TorchPolicy.evaluate": { "total": 86.38765510196481, "count": 42699, "self": 86.38765510196481 } } }, "workers": { "total": 0.5240103311070925, "count": 44160, "self": 0.0, "children": { "worker_root": { "total": 1638.5502897600577, "count": 44160, "is_parallel": true, "self": 610.4764003480341, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.002349054000205797, "count": 1, "is_parallel": true, "self": 0.0006989300004534016, "children": { "_process_rank_one_or_two_observation": { "total": 0.0016501239997523953, "count": 8, "is_parallel": true, "self": 0.0016501239997523953 } } }, "UnityEnvironment.step": { "total": 0.049945648000175424, "count": 1, "is_parallel": true, "self": 0.0006210650008142693, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004746249996969709, "count": 1, "is_parallel": true, "self": 0.0004746249996969709 }, "communicator.exchange": { "total": 0.04719839099971068, "count": 1, "is_parallel": true, "self": 0.04719839099971068 }, "steps_from_proto": { "total": 0.001651566999953502, "count": 1, "is_parallel": true, "self": 0.0003632790003393893, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012882879996141128, "count": 8, "is_parallel": true, "self": 0.0012882879996141128 } } } } } } }, "UnityEnvironment.step": { "total": 1028.0738894120236, "count": 44159, "is_parallel": true, "self": 22.615243170127542, "children": { "UnityEnvironment._generate_step_input": { "total": 16.16354234092296, "count": 44159, "is_parallel": true, "self": 16.16354234092296 }, "communicator.exchange": { "total": 922.6371116630103, "count": 44159, "is_parallel": true, "self": 922.6371116630103 }, "steps_from_proto": { "total": 66.65799223796284, "count": 44159, "is_parallel": true, "self": 13.613427392246194, "children": { "_process_rank_one_or_two_observation": { "total": 53.04456484571665, "count": 353272, "is_parallel": true, "self": 53.04456484571665 } } } } } } } } } } }, "trainer_advance": { "total": 438.0127920120044, "count": 44160, "self": 1.8215301810610072, "children": { "process_trajectory": { "total": 88.54691594793758, "count": 44160, "self": 88.35791005293822, "children": { "RLTrainer._checkpoint": { "total": 0.1890058949993545, "count": 1, "self": 0.1890058949993545 } } }, "_update_policy": { "total": 347.6443458830058, "count": 322, "self": 199.17829740993784, "children": { "TorchPPOOptimizer.update": { "total": 148.46604847306799, "count": 15504, "self": 148.46604847306799 } } } } } } }, "trainer_threads": { "total": 1.7639995348872617e-06, "count": 1, "self": 1.7639995348872617e-06 }, "TrainerController._save_models": { "total": 0.38314717299999757, "count": 1, "self": 0.014124008999715443, "children": { "RLTrainer._checkpoint": { "total": 0.3690231640002821, "count": 1, "self": 0.3690231640002821 } } } } } } }