{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.47353658080101013, "min": 0.47353658080101013, "max": 1.4519610404968262, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 14213.673828125, "min": 14128.1923828125, "max": 44046.69140625, "count": 33 }, "Pyramids.Step.mean": { "value": 989919.0, "min": 29897.0, "max": 989919.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989919.0, "min": 29897.0, "max": 989919.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.40372467041015625, "min": -0.10758207738399506, "max": 0.4199679493904114, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 108.19821166992188, "min": -25.92728042602539, "max": 112.13143920898438, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -1.747574806213379, "min": -1.747574806213379, "max": 0.4807884693145752, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -468.35003662109375, "min": -468.35003662109375, "max": 113.94686889648438, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06987175734466494, "min": 0.06622611479840244, "max": 0.07398406066797583, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9782046028253092, "min": 0.5033006010745683, "max": 1.0681712726974522, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.42207790994938427, "min": 0.0003429664413930363, "max": 0.42207790994938427, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 5.90909073929138, "min": 0.004801530179502508, "max": 5.90909073929138, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.554483196157139e-06, "min": 7.554483196157139e-06, "max": 0.0002952352730168143, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010576276474619994, "min": 0.00010576276474619994, "max": 0.003331755689414799, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10251812857142859, "min": 0.10251812857142859, "max": 0.19841175714285714, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4352538000000001, "min": 1.3888823, "max": 2.5277117000000002, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00026156104428571415, "min": 0.00026156104428571415, "max": 0.009841334538571429, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0036618546199999984, "min": 0.0036618546199999984, "max": 0.11106746148, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.01011080015450716, "min": 0.01011080015450716, "max": 0.42718544602394104, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.1415511965751648, "min": 0.1415511965751648, "max": 2.99029803276062, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 427.57142857142856, "min": 427.57142857142856, "max": 996.3125, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29930.0, "min": 16696.0, "max": 33599.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.4009599696312631, "min": -0.9347313002217561, "max": 1.4009599696312631, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 98.06719787418842, "min": -29.911401607096195, "max": 98.84119851142168, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.4009599696312631, "min": -0.9347313002217561, "max": 1.4009599696312631, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 98.06719787418842, "min": -29.911401607096195, "max": 98.84119851142168, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.045105562023153266, "min": 0.045105562023153266, "max": 9.413788940100108, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.1573893416207284, "min": 3.1573893416207284, "max": 160.03441198170185, "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": "1683999957", "python_version": "3.10.11 (main, Apr 5 2023, 14:15:10) [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": "1684002078" }, "total": 2120.334343196, "count": 1, "self": 0.4751523140007521, "children": { "run_training.setup": { "total": 0.037476475999937975, "count": 1, "self": 0.037476475999937975 }, "TrainerController.start_learning": { "total": 2119.8217144059995, "count": 1, "self": 1.6343922130122337, "children": { "TrainerController._reset_env": { "total": 3.784178335999968, "count": 1, "self": 3.784178335999968 }, "TrainerController.advance": { "total": 2114.312077743987, "count": 63492, "self": 1.5902375030468647, "children": { "env_step": { "total": 1466.6501948949804, "count": 63492, "self": 1347.3609882509036, "children": { "SubprocessEnvManager._take_step": { "total": 118.35331251702928, "count": 63492, "self": 5.05964539703109, "children": { "TorchPolicy.evaluate": { "total": 113.29366711999819, "count": 62557, "self": 113.29366711999819 } } }, "workers": { "total": 0.9358941270475043, "count": 63492, "self": 0.0, "children": { "worker_root": { "total": 2114.343356566943, "count": 63492, "is_parallel": true, "self": 886.661819986944, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0017414379999536322, "count": 1, "is_parallel": true, "self": 0.0005408349998106132, "children": { "_process_rank_one_or_two_observation": { "total": 0.001200603000143019, "count": 8, "is_parallel": true, "self": 0.001200603000143019 } } }, "UnityEnvironment.step": { "total": 0.047490417000062735, "count": 1, "is_parallel": true, "self": 0.0005182050008443184, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004964109998581989, "count": 1, "is_parallel": true, "self": 0.0004964109998581989 }, "communicator.exchange": { "total": 0.04442400199968688, "count": 1, "is_parallel": true, "self": 0.04442400199968688 }, "steps_from_proto": { "total": 0.0020517989996733377, "count": 1, "is_parallel": true, "self": 0.0004039679988636635, "children": { "_process_rank_one_or_two_observation": { "total": 0.0016478310008096742, "count": 8, "is_parallel": true, "self": 0.0016478310008096742 } } } } } } }, "UnityEnvironment.step": { "total": 1227.681536579999, "count": 63491, "is_parallel": true, "self": 32.39106075385553, "children": { "UnityEnvironment._generate_step_input": { "total": 23.084779710036855, "count": 63491, "is_parallel": true, "self": 23.084779710036855 }, "communicator.exchange": { "total": 1072.492355054047, "count": 63491, "is_parallel": true, "self": 1072.492355054047 }, "steps_from_proto": { "total": 99.7133410620595, "count": 63491, "is_parallel": true, "self": 20.964373608922415, "children": { "_process_rank_one_or_two_observation": { "total": 78.74896745313708, "count": 507928, "is_parallel": true, "self": 78.74896745313708 } } } } } } } } } } }, "trainer_advance": { "total": 646.07164534596, "count": 63492, "self": 2.9929602330116722, "children": { "process_trajectory": { "total": 108.67970381494433, "count": 63492, "self": 108.47196045994406, "children": { "RLTrainer._checkpoint": { "total": 0.2077433550002752, "count": 2, "self": 0.2077433550002752 } } }, "_update_policy": { "total": 534.398981298004, "count": 449, "self": 343.03543414700516, "children": { "TorchPPOOptimizer.update": { "total": 191.36354715099878, "count": 22791, "self": 191.36354715099878 } } } } } } }, "trainer_threads": { "total": 9.149998732027598e-07, "count": 1, "self": 9.149998732027598e-07 }, "TrainerController._save_models": { "total": 0.09106519800025126, "count": 1, "self": 0.0013718460004383815, "children": { "RLTrainer._checkpoint": { "total": 0.08969335199981288, "count": 1, "self": 0.08969335199981288 } } } } } } }