{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.6863691806793213, "min": 0.44609153270721436, "max": 1.4806675910949707, "count": 17 }, "Pyramids.Policy.Entropy.sum": { "value": 20547.1484375, "min": 13361.333984375, "max": 44917.53125, "count": 17 }, "Pyramids.Step.mean": { "value": 509876.0, "min": 29952.0, "max": 509876.0, "count": 17 }, "Pyramids.Step.sum": { "value": 509876.0, "min": 29952.0, "max": 509876.0, "count": 17 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.009797319769859314, "min": -0.19777660071849823, "max": 0.009797319769859314, "count": 17 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 2.380748748779297, "min": -46.87305450439453, "max": 2.380748748779297, "count": 17 }, "Pyramids.Policy.CuriosityValueEstimate.mean": { "value": 0.21247480809688568, "min": 0.19428382813930511, "max": 0.5327726006507874, "count": 17 }, "Pyramids.Policy.CuriosityValueEstimate.sum": { "value": 51.631378173828125, "min": 46.82240295410156, "max": 127.86541748046875, "count": 17 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06848906986413757, "min": 0.06624733092914306, "max": 0.07487210814514403, "count": 17 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9588469780979259, "min": 0.5068979500869862, "max": 1.0015575371479488, "count": 17 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.0032691564487353037, "min": 0.00043060905117009945, "max": 0.004821826685333981, "count": 17 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.04576819028229425, "min": 0.006028526716381392, "max": 0.04576819028229425, "count": 17 }, "Pyramids.Policy.LearningRate.mean": { "value": 0.00028517635565550217, "min": 0.00028517635565550217, "max": 0.0002995150630187886, "count": 17 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00399246897917703, "min": 0.0020907340830886396, "max": 0.0041432837589054205, "count": 17 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.19505878357142856, "min": 0.19505878357142856, "max": 0.1998383542857143, "count": 17 }, "Pyramids.Policy.Epsilon.sum": { "value": 2.7308229699999997, "min": 1.39691136, "max": 2.7810945800000004, "count": 17 }, "Pyramids.Policy.Beta.mean": { "value": 0.009506372478785715, "min": 0.009506372478785715, "max": 0.009983851593142858, "count": 17 }, "Pyramids.Policy.Beta.sum": { "value": 0.133089214703, "min": 0.069691444864, "max": 0.13811134854200002, "count": 17 }, "Pyramids.Losses.CuriosityForwardLoss.mean": { "value": 0.11134806499980825, "min": 0.09391165046746575, "max": 0.5048409593735068, "count": 17 }, "Pyramids.Losses.CuriosityForwardLoss.sum": { "value": 1.5588729099973155, "min": 1.3147631065445204, "max": 3.5338867156145475, "count": 17 }, "Pyramids.Losses.CuriosityInverseLoss.mean": { "value": 0.19675615540163002, "min": 0.17083643994289233, "max": 0.7954147527841561, "count": 17 }, "Pyramids.Losses.CuriosityInverseLoss.sum": { "value": 2.7545861756228205, "min": 2.3917101592004926, "max": 5.567903269489093, "count": 17 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 848.0588235294117, "min": 848.0588235294117, "max": 999.0, "count": 17 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 28834.0, "min": 15984.0, "max": 32355.0, "count": 17 }, "Pyramids.Environment.CumulativeReward.mean": { "value": -0.20144710404907956, "min": -1.0000000521540642, "max": -0.20144710404907956, "count": 17 }, "Pyramids.Environment.CumulativeReward.sum": { "value": -6.849201537668705, "min": -32.000001668930054, "max": -6.849201537668705, "count": 17 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": -0.20144710404907956, "min": -1.0000000521540642, "max": -0.20144710404907956, "count": 17 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": -6.849201537668705, "min": -32.000001668930054, "max": -6.849201537668705, "count": 17 }, "Pyramids.Policy.CuriosityReward.mean": { "value": 1.875498782048988, "min": 1.875498782048988, "max": 7.314000530168414, "count": 17 }, "Pyramids.Policy.CuriosityReward.sum": { "value": 63.76695858966559, "min": 58.44506286457181, "max": 188.0731085538864, "count": 17 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 17 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 17 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1701815619", "python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [GCC 11.4.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn /content/ml-agents/config/ppo/Pyramids.yaml --env=/content/ml-agents/training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids1 --no-graphics", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.1.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1701816825" }, "total": 1205.241238173, "count": 1, "self": 0.9061653860003389, "children": { "run_training.setup": { "total": 0.05296262499996374, "count": 1, "self": 0.05296262499996374 }, "TrainerController.start_learning": { "total": 1204.2821101619998, "count": 1, "self": 0.8164048590165294, "children": { "TrainerController._reset_env": { "total": 3.072668053000143, "count": 1, "self": 3.072668053000143 }, "TrainerController.advance": { "total": 1200.3906866219836, "count": 32980, "self": 0.8021393219728452, "children": { "env_step": { "total": 783.6034465769694, "count": 32980, "self": 709.3270879479364, "children": { "SubprocessEnvManager._take_step": { "total": 73.77301805902198, "count": 32980, "self": 2.5918797740423543, "children": { "TorchPolicy.evaluate": { "total": 71.18113828497962, "count": 32743, "self": 71.18113828497962 } } }, "workers": { "total": 0.5033405700110052, "count": 32980, "self": 0.0, "children": { "worker_root": { "total": 1201.237725207955, "count": 32980, "is_parallel": true, "self": 558.9407126040014, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0021203999999670486, "count": 1, "is_parallel": true, "self": 0.0006876950005789695, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014327049993880792, "count": 8, "is_parallel": true, "self": 0.0014327049993880792 } } }, "UnityEnvironment.step": { "total": 0.04730950600014694, "count": 1, "is_parallel": true, "self": 0.0005626590000247234, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005579839998972602, "count": 1, "is_parallel": true, "self": 0.0005579839998972602 }, "communicator.exchange": { "total": 0.04455709500007288, "count": 1, "is_parallel": true, "self": 0.04455709500007288 }, "steps_from_proto": { "total": 0.0016317680001520785, "count": 1, "is_parallel": true, "self": 0.00036454800010687904, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012672200000451994, "count": 8, "is_parallel": true, "self": 0.0012672200000451994 } } } } } } }, "UnityEnvironment.step": { "total": 642.2970126039536, "count": 32979, "is_parallel": true, "self": 18.19606279298796, "children": { "UnityEnvironment._generate_step_input": { "total": 12.882446825000443, "count": 32979, "is_parallel": true, "self": 12.882446825000443 }, "communicator.exchange": { "total": 559.6122942609609, "count": 32979, "is_parallel": true, "self": 559.6122942609609 }, "steps_from_proto": { "total": 51.60620872500431, "count": 32979, "is_parallel": true, "self": 10.252579940982287, "children": { "_process_rank_one_or_two_observation": { "total": 41.35362878402202, "count": 263832, "is_parallel": true, "self": 41.35362878402202 } } } } } } } } } } }, "trainer_advance": { "total": 415.98510072304134, "count": 32980, "self": 1.3859687960612064, "children": { "process_trajectory": { "total": 67.05651527098007, "count": 32980, "self": 66.92206676197975, "children": { "RLTrainer._checkpoint": { "total": 0.1344485090003218, "count": 1, "self": 0.1344485090003218 } } }, "_update_policy": { "total": 347.54261665600006, "count": 225, "self": 234.5499943960308, "children": { "TorchPPOOptimizer.update": { "total": 112.99262225996927, "count": 11956, "self": 112.99262225996927 } } } } } } }, "trainer_threads": { "total": 1.3819999367115088e-06, "count": 1, "self": 1.3819999367115088e-06 }, "TrainerController._save_models": { "total": 0.002349245999539562, "count": 1, "self": 3.03979995806003e-05, "children": { "RLTrainer._checkpoint": { "total": 0.0023188479999589617, "count": 1, "self": 0.0023188479999589617 } } } } } } }