{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.38862118124961853, "min": 0.38862118124961853, "max": 1.4465970993041992, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 11633.763671875, "min": 11633.763671875, "max": 43883.96875, "count": 33 }, "Pyramids.Step.mean": { "value": 989886.0, "min": 29952.0, "max": 989886.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989886.0, "min": 29952.0, "max": 989886.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.30959466099739075, "min": -0.21692360937595367, "max": 0.44682183861732483, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 79.25623321533203, "min": -51.41089630126953, "max": 121.08871459960938, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.01304395217448473, "min": -0.0018741587409749627, "max": 0.34507521986961365, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 3.339251756668091, "min": -0.47603631019592285, "max": 81.78282928466797, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.0688061665076973, "min": 0.06522794297400826, "max": 0.07313658783936666, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9632863311077623, "min": 0.5048961591938291, "max": 1.0970488175905, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.012106658049469362, "min": 0.0007865643286531144, "max": 0.014395716319119322, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.16949321269257106, "min": 0.011011900601143602, "max": 0.20744626410790565, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.514926066485713e-06, "min": 7.514926066485713e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010520896493079999, "min": 0.00010520896493079999, "max": 0.003507916730694499, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10250494285714287, "min": 0.10250494285714287, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4350692000000003, "min": 1.3886848, "max": 2.569305500000001, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00026024379142857145, "min": 0.00026024379142857145, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0036434130800000004, "min": 0.0036434130800000004, "max": 0.11695361944999999, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.013181684538722038, "min": 0.013181684538722038, "max": 0.4494350850582123, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.18454357981681824, "min": 0.18454357981681824, "max": 3.146045684814453, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 525.0188679245283, "min": 402.19736842105266, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 27826.0, "min": 15984.0, "max": 33072.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.2209629381972331, "min": -1.0000000521540642, "max": 1.466178928943057, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 65.93199866265059, "min": -30.463001564145088, "max": 111.42959859967232, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.2209629381972331, "min": -1.0000000521540642, "max": 1.466178928943057, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 65.93199866265059, "min": -30.463001564145088, "max": 111.42959859967232, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.07145692137958205, "min": 0.06200181305298189, "max": 9.28210587054491, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.858673754497431, "min": 3.858673754497431, "max": 148.51369392871857, "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": "1681061175", "python_version": "3.9.16 (main, Dec 7 2022, 01:11:51) \n[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": "1681063273" }, "total": 2097.6822299240002, "count": 1, "self": 0.42880710700001146, "children": { "run_training.setup": { "total": 0.19626191199995446, "count": 1, "self": 0.19626191199995446 }, "TrainerController.start_learning": { "total": 2097.0571609050003, "count": 1, "self": 1.358372757961206, "children": { "TrainerController._reset_env": { "total": 4.072367790999806, "count": 1, "self": 4.072367790999806 }, "TrainerController.advance": { "total": 2091.532092939039, "count": 63554, "self": 1.4778631590379518, "children": { "env_step": { "total": 1488.784404202987, "count": 63554, "self": 1381.381308199924, "children": { "SubprocessEnvManager._take_step": { "total": 106.57095076205928, "count": 63554, "self": 4.681714134052754, "children": { "TorchPolicy.evaluate": { "total": 101.88923662800653, "count": 62572, "self": 101.88923662800653 } } }, "workers": { "total": 0.8321452410036727, "count": 63554, "self": 0.0, "children": { "worker_root": { "total": 2092.2194050819057, "count": 63554, "is_parallel": true, "self": 821.1908891169389, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0026603610001529887, "count": 1, "is_parallel": true, "self": 0.0007882909999352705, "children": { "_process_rank_one_or_two_observation": { "total": 0.0018720700002177182, "count": 8, "is_parallel": true, "self": 0.0018720700002177182 } } }, "UnityEnvironment.step": { "total": 0.06766189199993278, "count": 1, "is_parallel": true, "self": 0.0006835880001290207, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004995489998691482, "count": 1, "is_parallel": true, "self": 0.0004995489998691482 }, "communicator.exchange": { "total": 0.06484215199998289, "count": 1, "is_parallel": true, "self": 0.06484215199998289 }, "steps_from_proto": { "total": 0.0016366029999517195, "count": 1, "is_parallel": true, "self": 0.0003883179999775166, "children": { "_process_rank_one_or_two_observation": { "total": 0.001248284999974203, "count": 8, "is_parallel": true, "self": 0.001248284999974203 } } } } } } }, "UnityEnvironment.step": { "total": 1271.0285159649668, "count": 63553, "is_parallel": true, "self": 31.807159163026654, "children": { "UnityEnvironment._generate_step_input": { "total": 23.545963928943593, "count": 63553, "is_parallel": true, "self": 23.545963928943593 }, "communicator.exchange": { "total": 1120.4090823629485, "count": 63553, "is_parallel": true, "self": 1120.4090823629485 }, "steps_from_proto": { "total": 95.26631051004802, "count": 63553, "is_parallel": true, "self": 20.78443409707006, "children": { "_process_rank_one_or_two_observation": { "total": 74.48187641297795, "count": 508424, "is_parallel": true, "self": 74.48187641297795 } } } } } } } } } } }, "trainer_advance": { "total": 601.269825577014, "count": 63554, "self": 2.5093746420486696, "children": { "process_trajectory": { "total": 106.17467340896792, "count": 63554, "self": 105.90430925196779, "children": { "RLTrainer._checkpoint": { "total": 0.27036415700013094, "count": 2, "self": 0.27036415700013094 } } }, "_update_policy": { "total": 492.5857775259974, "count": 448, "self": 315.75429313498466, "children": { "TorchPPOOptimizer.update": { "total": 176.83148439101274, "count": 22848, "self": 176.83148439101274 } } } } } } }, "trainer_threads": { "total": 9.479999789618887e-07, "count": 1, "self": 9.479999789618887e-07 }, "TrainerController._save_models": { "total": 0.09432646899995234, "count": 1, "self": 0.0018513989998609759, "children": { "RLTrainer._checkpoint": { "total": 0.09247507000009136, "count": 1, "self": 0.09247507000009136 } } } } } } }