{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.7281584739685059, "min": 0.6744995713233948, "max": 1.6092778444290161, "count": 66 }, "Pyramids.Policy.Entropy.sum": { "value": 687.381591796875, "min": 415.33734130859375, "max": 3295.801025390625, "count": 66 }, "Pyramids.Step.mean": { "value": 99992.0, "min": 896.0, "max": 99992.0, "count": 100 }, "Pyramids.Step.sum": { "value": 99992.0, "min": 896.0, "max": 99992.0, "count": 100 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": -0.03586368262767792, "min": -0.3220546543598175, "max": -0.015102476812899113, "count": 100 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": -0.32277312874794006, "min": -2.5558996200561523, "max": -0.10571733862161636, "count": 100 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.14093786478042603, "min": 0.14093786478042603, "max": 0.5928547978401184, "count": 100 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 1.2684407234191895, "min": 1.005059838294983, "max": 5.521230697631836, "count": 100 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 100 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 100 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06304602160611573, "min": 0.05414979751495754, "max": 0.08140035357925741, "count": 35 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.06304602160611573, "min": 0.05414979751495754, "max": 0.08140035357925741, "count": 35 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.0005666140401872861, "min": 0.00028501721738161996, "max": 0.03298690651232997, "count": 35 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.0005666140401872861, "min": 0.00028501721738161996, "max": 0.03298690651232997, "count": 35 }, "Pyramids.Policy.LearningRate.mean": { "value": 4.8570983810000114e-06, "min": 4.8570983810000114e-06, "max": 0.00028771200409599993, "count": 35 }, "Pyramids.Policy.LearningRate.sum": { "value": 4.8570983810000114e-06, "min": 4.8570983810000114e-06, "max": 0.00028771200409599993, "count": 35 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10161900000000003, "min": 0.10161900000000003, "max": 0.19590400000000005, "count": 35 }, "Pyramids.Policy.Epsilon.sum": { "value": 0.10161900000000003, "min": 0.10161900000000003, "max": 0.19590400000000005, "count": 35 }, "Pyramids.Policy.Beta.mean": { "value": 0.0001717381000000004, "min": 0.0001717381000000004, "max": 0.0095908096, "count": 35 }, "Pyramids.Policy.Beta.sum": { "value": 0.0001717381000000004, "min": 0.0001717381000000004, "max": 0.0095908096, "count": 35 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.10097824037075043, "min": 0.10097824037075043, "max": 0.8972789645195007, "count": 35 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.10097824037075043, "min": 0.10097824037075043, "max": 0.8972789645195007, "count": 35 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 330.0, "min": 200.0, "max": 999.0, "count": 17 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 330.0, "min": 200.0, "max": 15984.0, "count": 17 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.6699999868869781, "min": -1.0000000521540642, "max": 1.6699999868869781, "count": 21 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 1.6699999868869781, "min": -10.000000521540642, "max": 1.6699999868869781, "count": 21 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.6699999868869781, "min": -1.0000000521540642, "max": 1.6699999868869781, "count": 21 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 1.6699999868869781, "min": -10.000000521540642, "max": 1.6699999868869781, "count": 21 }, "Pyramids.Policy.RndReward.mean": { "value": 0.5077967494726181, "min": 0.5077967494726181, "max": 9.100134731829167, "count": 21 }, "Pyramids.Policy.RndReward.sum": { "value": 0.5077967494726181, "min": 0.5077967494726181, "max": 91.00134731829166, "count": 21 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1727626327", "python_version": "3.10.12 (main, Sep 11 2024, 15:47:36) [GCC 11.4.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn ./ml-agents/config/ppo/PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids Training --no-graphics", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.4.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1727626544" }, "total": 216.60991267100007, "count": 1, "self": 0.47671838800033584, "children": { "run_training.setup": { "total": 0.05115096800000174, "count": 1, "self": 0.05115096800000174 }, "TrainerController.start_learning": { "total": 216.08204331499974, "count": 1, "self": 0.12679844002241225, "children": { "TrainerController._reset_env": { "total": 1.9232988000003388, "count": 1, "self": 1.9232988000003388 }, "TrainerController.advance": { "total": 213.91848426897695, "count": 6327, "self": 0.13398623596003745, "children": { "env_step": { "total": 143.05944446200283, "count": 6327, "self": 127.22490817301286, "children": { "SubprocessEnvManager._take_step": { "total": 15.756051689991637, "count": 6327, "self": 0.4820266309861836, "children": { "TorchPolicy.evaluate": { "total": 15.274025059005453, "count": 6315, "self": 15.274025059005453 } } }, "workers": { "total": 0.0784845989983296, "count": 6327, "self": 0.0, "children": { "worker_root": { "total": 215.54143862199498, "count": 6327, "is_parallel": true, "self": 100.79717779498606, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0020771810000042024, "count": 1, "is_parallel": true, "self": 0.0007567270004074089, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013204539995967934, "count": 8, "is_parallel": true, "self": 0.0013204539995967934 } } }, "UnityEnvironment.step": { "total": 0.11057858899994244, "count": 1, "is_parallel": true, "self": 0.0006054720001884561, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00048615000014251564, "count": 1, "is_parallel": true, "self": 0.00048615000014251564 }, "communicator.exchange": { "total": 0.10787747999984276, "count": 1, "is_parallel": true, "self": 0.10787747999984276 }, "steps_from_proto": { "total": 0.0016094869997687056, "count": 1, "is_parallel": true, "self": 0.00038932600000407547, "children": { "_process_rank_one_or_two_observation": { "total": 0.00122016099976463, "count": 8, "is_parallel": true, "self": 0.00122016099976463 } } } } } } }, "UnityEnvironment.step": { "total": 114.74426082700893, "count": 6326, "is_parallel": true, "self": 3.374676842957342, "children": { "UnityEnvironment._generate_step_input": { "total": 2.4732373780138914, "count": 6326, "is_parallel": true, "self": 2.4732373780138914 }, "communicator.exchange": { "total": 98.5807858160083, "count": 6326, "is_parallel": true, "self": 98.5807858160083 }, "steps_from_proto": { "total": 10.315560790029394, "count": 6326, "is_parallel": true, "self": 2.076887960085969, "children": { "_process_rank_one_or_two_observation": { "total": 8.238672829943425, "count": 50608, "is_parallel": true, "self": 8.238672829943425 } } } } } } } } } } }, "trainer_advance": { "total": 70.72505357101409, "count": 6327, "self": 0.16935117399771116, "children": { "process_trajectory": { "total": 13.578296737017808, "count": 6327, "self": 13.578296737017808 }, "_update_policy": { "total": 56.97740565999857, "count": 35, "self": 32.00444705198561, "children": { "TorchPPOOptimizer.update": { "total": 24.97295860801296, "count": 2280, "self": 24.97295860801296 } } } } } } }, "trainer_threads": { "total": 9.169998520519584e-07, "count": 1, "self": 9.169998520519584e-07 }, "TrainerController._save_models": { "total": 0.11346088900018003, "count": 1, "self": 0.0015222460001496074, "children": { "RLTrainer._checkpoint": { "total": 0.11193864300003042, "count": 1, "self": 0.11193864300003042 } } } } } } }