{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.7296828627586365, "min": 0.6193974018096924, "max": 1.4590489864349365, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 21855.4609375, "min": 18552.19140625, "max": 44261.7109375, "count": 33 }, "Pyramids.Step.mean": { "value": 989988.0, "min": 29952.0, "max": 989988.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989988.0, "min": 29952.0, "max": 989988.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.2756415605545044, "min": -0.10698758065700531, "max": 0.2756415605545044, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 71.66680908203125, "min": -25.356056213378906, "max": 71.66680908203125, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.5413818359375, "min": -0.020329132676124573, "max": 0.6159877777099609, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 140.75927734375, "min": -5.143270492553711, "max": 157.07688903808594, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.0695317835433794, "min": 0.06544274452200462, "max": 0.0728235122905541, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9734449696073116, "min": 0.502379660177996, "max": 1.011163737014274, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.03826436714999833, "min": 0.00013902719090190855, "max": 0.089207041512039, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.5357011400999766, "min": 0.0018073534817248111, "max": 1.248898581168546, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.644547451849998e-06, "min": 7.644547451849998e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010702366432589998, "min": 0.00010702366432589998, "max": 0.0032601749132751, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10254815000000002, "min": 0.10254815000000002, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4356741000000002, "min": 1.3886848, "max": 2.4017630000000003, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.000264560185, "min": 0.000264560185, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.00370384259, "min": 0.00370384259, "max": 0.10869381751, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.010061299428343773, "min": 0.010061299428343773, "max": 0.37853989005088806, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.14085818827152252, "min": 0.14085818827152252, "max": 2.6497793197631836, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 513.7636363636364, "min": 513.7636363636364, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 28257.0, "min": 15984.0, "max": 32550.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.1952581592581488, "min": -1.0000000521540642, "max": 1.1952581592581488, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 65.73919875919819, "min": -30.99620160460472, "max": 65.73919875919819, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.1952581592581488, "min": -1.0000000521540642, "max": 1.1952581592581488, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 65.73919875919819, "min": -30.99620160460472, "max": 65.73919875919819, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.0542708756359802, "min": 0.0542708756359802, "max": 7.359631835483015, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 2.9848981599789113, "min": 2.9848981599789113, "max": 117.75410936772823, "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": "1680166582", "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": "1680168584" }, "total": 2001.395192401, "count": 1, "self": 0.47524751900027695, "children": { "run_training.setup": { "total": 0.1146443619998081, "count": 1, "self": 0.1146443619998081 }, "TrainerController.start_learning": { "total": 2000.80530052, "count": 1, "self": 1.3757094799855167, "children": { "TrainerController._reset_env": { "total": 7.332073390000005, "count": 1, "self": 7.332073390000005 }, "TrainerController.advance": { "total": 1992.0061069540145, "count": 63355, "self": 1.4232795089676529, "children": { "env_step": { "total": 1348.9312914870213, "count": 63355, "self": 1238.1125437611113, "children": { "SubprocessEnvManager._take_step": { "total": 109.98765652496922, "count": 63355, "self": 4.744134901994812, "children": { "TorchPolicy.evaluate": { "total": 105.24352162297441, "count": 62575, "self": 105.24352162297441 } } }, "workers": { "total": 0.8310912009408185, "count": 63355, "self": 0.0, "children": { "worker_root": { "total": 1996.2505001488926, "count": 63355, "is_parallel": true, "self": 873.8105875758215, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0017549110000345536, "count": 1, "is_parallel": true, "self": 0.0005842159996518603, "children": { "_process_rank_one_or_two_observation": { "total": 0.0011706950003826933, "count": 8, "is_parallel": true, "self": 0.0011706950003826933 } } }, "UnityEnvironment.step": { "total": 0.04390658399984204, "count": 1, "is_parallel": true, "self": 0.000513723000040045, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005156709999027953, "count": 1, "is_parallel": true, "self": 0.0005156709999027953 }, "communicator.exchange": { "total": 0.04121877299985499, "count": 1, "is_parallel": true, "self": 0.04121877299985499 }, "steps_from_proto": { "total": 0.00165841700004421, "count": 1, "is_parallel": true, "self": 0.0003459750003003137, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013124419997438963, "count": 8, "is_parallel": true, "self": 0.0013124419997438963 } } } } } } }, "UnityEnvironment.step": { "total": 1122.439912573071, "count": 63354, "is_parallel": true, "self": 31.587443143185965, "children": { "UnityEnvironment._generate_step_input": { "total": 23.742414693914498, "count": 63354, "is_parallel": true, "self": 23.742414693914498 }, "communicator.exchange": { "total": 974.281145346979, "count": 63354, "is_parallel": true, "self": 974.281145346979 }, "steps_from_proto": { "total": 92.82890938899163, "count": 63354, "is_parallel": true, "self": 19.665833068762367, "children": { "_process_rank_one_or_two_observation": { "total": 73.16307632022927, "count": 506832, "is_parallel": true, "self": 73.16307632022927 } } } } } } } } } } }, "trainer_advance": { "total": 641.6515359580255, "count": 63355, "self": 2.533428097114893, "children": { "process_trajectory": { "total": 117.9240082699107, "count": 63355, "self": 117.72659769191068, "children": { "RLTrainer._checkpoint": { "total": 0.19741057800001727, "count": 2, "self": 0.19741057800001727 } } }, "_update_policy": { "total": 521.1940995909999, "count": 445, "self": 333.13917218700135, "children": { "TorchPPOOptimizer.update": { "total": 188.0549274039986, "count": 22791, "self": 188.0549274039986 } } } } } } }, "trainer_threads": { "total": 9.410000529896934e-07, "count": 1, "self": 9.410000529896934e-07 }, "TrainerController._save_models": { "total": 0.0914097549998587, "count": 1, "self": 0.0014795549996051705, "children": { "RLTrainer._checkpoint": { "total": 0.08993020000025354, "count": 1, "self": 0.08993020000025354 } } } } } } }