{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.46871811151504517, "min": 0.46871811151504517, "max": 1.4347219467163086, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 14091.541015625, "min": 14091.541015625, "max": 43523.7265625, "count": 33 }, "Pyramids.Step.mean": { "value": 989902.0, "min": 29910.0, "max": 989902.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989902.0, "min": 29910.0, "max": 989902.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.41535234451293945, "min": -0.12590618431568146, "max": 0.41535234451293945, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 110.89907836914062, "min": -30.217483520507812, "max": 110.89907836914062, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -0.00023446280101779848, "min": -0.059020914137363434, "max": 0.203892782330513, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -0.06260156631469727, "min": -15.109354019165039, "max": 49.138160705566406, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.07050569612918133, "min": 0.06477310515656401, "max": 0.07619860619156672, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9870797458085385, "min": 0.600380818041384, "max": 1.0669108343883598, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.015642743894810945, "min": 0.00023774593981955463, "max": 0.015642743894810945, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.21899841452735322, "min": 0.002615205338015101, "max": 0.21899841452735322, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.403283246557142e-06, "min": 7.403283246557142e-06, "max": 0.00029528835157055, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.0001036459654518, "min": 0.0001036459654518, "max": 0.003223104125632, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10246772857142858, "min": 0.10246772857142858, "max": 0.19842945, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4345482, "min": 1.4345482, "max": 2.4425243000000005, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002565260842857143, "min": 0.0002565260842857143, "max": 0.009843102055, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.00359136518, "min": 0.00359136518, "max": 0.10744936319999998, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.00963502936065197, "min": 0.00963502936065197, "max": 0.34898096323013306, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.13489040732383728, "min": 0.13489040732383728, "max": 2.7918477058410645, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 408.34722222222223, "min": 408.34722222222223, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29401.0, "min": 16709.0, "max": 32349.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.4527110898246367, "min": -0.9999742455059483, "max": 1.4527110898246367, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 104.59519846737385, "min": -31.998401656746864, "max": 104.59519846737385, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.4527110898246367, "min": -0.9999742455059483, "max": 1.4527110898246367, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 104.59519846737385, "min": -31.998401656746864, "max": 104.59519846737385, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.040899573755773924, "min": 0.040899573755773924, "max": 6.261625605470994, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 2.9447693104157224, "min": 2.9447693104157224, "max": 106.4476352930069, "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": "1739994216", "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": "1739996344" }, "total": 2127.233976557, "count": 1, "self": 0.8204664959998809, "children": { "run_training.setup": { "total": 0.02116938900007881, "count": 1, "self": 0.02116938900007881 }, "TrainerController.start_learning": { "total": 2126.392340672, "count": 1, "self": 1.2762381159786855, "children": { "TrainerController._reset_env": { "total": 2.729924062000009, "count": 1, "self": 2.729924062000009 }, "TrainerController.advance": { "total": 2122.252585556022, "count": 63602, "self": 1.3035594428183686, "children": { "env_step": { "total": 1433.6145528131192, "count": 63602, "self": 1283.9428846619885, "children": { "SubprocessEnvManager._take_step": { "total": 148.9488474340751, "count": 63602, "self": 4.615752209114817, "children": { "TorchPolicy.evaluate": { "total": 144.3330952249603, "count": 62575, "self": 144.3330952249603 } } }, "workers": { "total": 0.7228207170555834, "count": 63602, "self": 0.0, "children": { "worker_root": { "total": 2121.6632734419863, "count": 63602, "is_parallel": true, "self": 945.3097322231006, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.001988934000110021, "count": 1, "is_parallel": true, "self": 0.0006815709998591046, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013073630002509162, "count": 8, "is_parallel": true, "self": 0.0013073630002509162 } } }, "UnityEnvironment.step": { "total": 0.0921219540000493, "count": 1, "is_parallel": true, "self": 0.0005481130001498968, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00045441699967341265, "count": 1, "is_parallel": true, "self": 0.00045441699967341265 }, "communicator.exchange": { "total": 0.08925518700016255, "count": 1, "is_parallel": true, "self": 0.08925518700016255 }, "steps_from_proto": { "total": 0.00186423700006344, "count": 1, "is_parallel": true, "self": 0.0004173259994786349, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014469110005848052, "count": 8, "is_parallel": true, "self": 0.0014469110005848052 } } } } } } }, "UnityEnvironment.step": { "total": 1176.3535412188858, "count": 63601, "is_parallel": true, "self": 31.592030050806443, "children": { "UnityEnvironment._generate_step_input": { "total": 22.815404827963448, "count": 63601, "is_parallel": true, "self": 22.815404827963448 }, "communicator.exchange": { "total": 1027.6999074809878, "count": 63601, "is_parallel": true, "self": 1027.6999074809878 }, "steps_from_proto": { "total": 94.24619885912807, "count": 63601, "is_parallel": true, "self": 18.42477378976946, "children": { "_process_rank_one_or_two_observation": { "total": 75.82142506935861, "count": 508808, "is_parallel": true, "self": 75.82142506935861 } } } } } } } } } } }, "trainer_advance": { "total": 687.3344733000845, "count": 63602, "self": 2.3620640490817095, "children": { "process_trajectory": { "total": 127.72672320000402, "count": 63602, "self": 127.48533132000375, "children": { "RLTrainer._checkpoint": { "total": 0.2413918800002648, "count": 2, "self": 0.2413918800002648 } } }, "_update_policy": { "total": 557.2456860509988, "count": 445, "self": 305.39139048403376, "children": { "TorchPPOOptimizer.update": { "total": 251.854295566965, "count": 22845, "self": 251.854295566965 } } } } } } }, "trainer_threads": { "total": 8.469996828353032e-07, "count": 1, "self": 8.469996828353032e-07 }, "TrainerController._save_models": { "total": 0.13359209099962754, "count": 1, "self": 0.0016830699996717158, "children": { "RLTrainer._checkpoint": { "total": 0.13190902099995583, "count": 1, "self": 0.13190902099995583 } } } } } } }