{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.4067824184894562, "min": 0.38718852400779724, "max": 1.4957274198532104, "count": 34 }, "Pyramids.Policy.Entropy.sum": { "value": 12157.9130859375, "min": 11590.8759765625, "max": 45374.38671875, "count": 34 }, "Pyramids.Step.mean": { "value": 1019903.0, "min": 29952.0, "max": 1019903.0, "count": 34 }, "Pyramids.Step.sum": { "value": 1019903.0, "min": 29952.0, "max": 1019903.0, "count": 34 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.41822972893714905, "min": -0.1310168206691742, "max": 0.4564484655857086, "count": 34 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 113.34025573730469, "min": -31.050987243652344, "max": 122.32818603515625, "count": 34 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.0038186325691640377, "min": -0.018477989360690117, "max": 0.39332205057144165, "count": 34 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 1.0348494052886963, "min": -4.859711170196533, "max": 93.21732330322266, "count": 34 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06455381287863324, "min": 0.06455381287863324, "max": 0.07297718234033147, "count": 34 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9037533803008653, "min": 0.505437096987313, "max": 1.05106996889306, "count": 34 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.013627099252993333, "min": 0.0005246370140711768, "max": 0.015729893115349114, "count": 34 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.19077938954190665, "min": 0.006532934723271984, "max": 0.2202185036148876, "count": 34 }, "Pyramids.Policy.LearningRate.mean": { "value": 4.358144765805326e-06, "min": 4.358144765805326e-06, "max": 0.0002952457158704761, "count": 34 }, "Pyramids.Policy.LearningRate.sum": { "value": 6.101402672127456e-05, "min": 6.101402672127456e-05, "max": 0.00352068904996647, "count": 34 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10145268207282912, "min": 0.10145268207282912, "max": 0.19841523809523814, "count": 34 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4203375490196077, "min": 1.388906666666667, "max": 2.5735629411764704, "count": 34 }, "Pyramids.Policy.Beta.mean": { "value": 0.00015512293907563035, "min": 0.00015512293907563035, "max": 0.009841682285714286, "count": 34 }, "Pyramids.Policy.Beta.sum": { "value": 0.002171721147058825, "min": 0.002171721147058825, "max": 0.1173789378235294, "count": 34 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.00842695590108633, "min": 0.00812582578510046, "max": 0.4004283547401428, "count": 34 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.11797738075256348, "min": 0.11376155912876129, "max": 2.8029985427856445, "count": 34 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 410.0821917808219, "min": 400.986301369863, "max": 999.0, "count": 34 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29936.0, "min": 15984.0, "max": 33206.0, "count": 34 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.4254903907645238, "min": -1.0000000521540642, "max": 1.4619944956000537, "count": 34 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 104.06079852581024, "min": -30.9994016289711, "max": 106.72559817880392, "count": 34 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.4254903907645238, "min": -1.0000000521540642, "max": 1.4619944956000537, "count": 34 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 104.06079852581024, "min": -30.9994016289711, "max": 106.72559817880392, "count": 34 }, "Pyramids.Policy.RndReward.mean": { "value": 0.03596552041174257, "min": 0.03436772238498247, "max": 8.141340014524758, "count": 34 }, "Pyramids.Policy.RndReward.sum": { "value": 2.6254829900572076, "min": 2.5088437341037206, "max": 130.26144023239613, "count": 34 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 34 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 34 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1741329250", "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]", "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": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.6.0+cu124", "numpy_version": "1.23.5", "end_time_seconds": "1741331494" }, "total": 2244.42545135, "count": 1, "self": 0.4788491240001349, "children": { "run_training.setup": { "total": 0.020122637999975268, "count": 1, "self": 0.020122637999975268 }, "TrainerController.start_learning": { "total": 2243.926479588, "count": 1, "self": 1.5226517059763864, "children": { "TrainerController._reset_env": { "total": 2.9923215439998785, "count": 1, "self": 2.9923215439998785 }, "TrainerController.advance": { "total": 2239.3218639660236, "count": 64875, "self": 1.6579230410907257, "children": { "env_step": { "total": 1535.6764424969924, "count": 64875, "self": 1371.4269022549315, "children": { "SubprocessEnvManager._take_step": { "total": 163.36262808906758, "count": 64875, "self": 4.829454173099975, "children": { "TorchPolicy.evaluate": { "total": 158.5331739159676, "count": 63796, "self": 158.5331739159676 } } }, "workers": { "total": 0.8869121529933182, "count": 64875, "self": 0.0, "children": { "worker_root": { "total": 2238.719162512064, "count": 64875, "is_parallel": true, "self": 985.7300886311702, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0028691550000985444, "count": 1, "is_parallel": true, "self": 0.0008231920003254345, "children": { "_process_rank_one_or_two_observation": { "total": 0.00204596299977311, "count": 8, "is_parallel": true, "self": 0.00204596299977311 } } }, "UnityEnvironment.step": { "total": 0.047550631999911275, "count": 1, "is_parallel": true, "self": 0.0005395609996412531, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004299770000670833, "count": 1, "is_parallel": true, "self": 0.0004299770000670833 }, "communicator.exchange": { "total": 0.04503076800006056, "count": 1, "is_parallel": true, "self": 0.04503076800006056 }, "steps_from_proto": { "total": 0.0015503260001423769, "count": 1, "is_parallel": true, "self": 0.0003221950000806828, "children": { "_process_rank_one_or_two_observation": { "total": 0.001228131000061694, "count": 8, "is_parallel": true, "self": 0.001228131000061694 } } } } } } }, "UnityEnvironment.step": { "total": 1252.9890738808938, "count": 64874, "is_parallel": true, "self": 32.82234711984347, "children": { "UnityEnvironment._generate_step_input": { "total": 22.82634516304529, "count": 64874, "is_parallel": true, "self": 22.82634516304529 }, "communicator.exchange": { "total": 1099.929582632955, "count": 64874, "is_parallel": true, "self": 1099.929582632955 }, "steps_from_proto": { "total": 97.41079896504993, "count": 64874, "is_parallel": true, "self": 20.08675521899636, "children": { "_process_rank_one_or_two_observation": { "total": 77.32404374605358, "count": 518992, "is_parallel": true, "self": 77.32404374605358 } } } } } } } } } } }, "trainer_advance": { "total": 701.9874984279406, "count": 64875, "self": 2.912825963958994, "children": { "process_trajectory": { "total": 130.40559497998288, "count": 64875, "self": 130.2077466149833, "children": { "RLTrainer._checkpoint": { "total": 0.19784836499957237, "count": 2, "self": 0.19784836499957237 } } }, "_update_policy": { "total": 568.6690774839988, "count": 459, "self": 312.5982403779583, "children": { "TorchPPOOptimizer.update": { "total": 256.07083710604047, "count": 23298, "self": 256.07083710604047 } } } } } } }, "trainer_threads": { "total": 9.300001693191007e-07, "count": 1, "self": 9.300001693191007e-07 }, "TrainerController._save_models": { "total": 0.08964144199990187, "count": 1, "self": 0.0012995550000596268, "children": { "RLTrainer._checkpoint": { "total": 0.08834188699984225, "count": 1, "self": 0.08834188699984225 } } } } } } }