{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.38227856159210205, "min": 0.37805527448654175, "max": 1.4718120098114014, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 11352.14453125, "min": 11312.125, "max": 44648.890625, "count": 33 }, "Pyramids.Step.mean": { "value": 989917.0, "min": 29952.0, "max": 989917.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989917.0, "min": 29952.0, "max": 989917.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.4941466152667999, "min": -0.11051377654075623, "max": 0.6004889607429504, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 133.41958618164062, "min": -26.633819580078125, "max": 166.93592834472656, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -0.007095681503415108, "min": -0.017237400636076927, "max": 0.4513334035873413, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -1.9158339500427246, "min": -4.395537376403809, "max": 106.96601867675781, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.07047067760418359, "min": 0.06527664507545221, "max": 0.07304319939265484, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 1.0570601640627537, "min": 0.4878646544439734, "max": 1.069396370416393, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.015740372930893833, "min": 0.0004207468224655531, "max": 0.017161966378764538, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.23610559396340752, "min": 0.004628215047121084, "max": 0.24026752930270354, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.511597496166664e-06, "min": 7.511597496166664e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00011267396244249996, "min": 0.00011267396244249996, "max": 0.0033832805722399002, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10250383333333332, "min": 0.10250383333333332, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.5375575, "min": 1.3691136000000002, "max": 2.5277601, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00026013295, "min": 0.00026013295, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0039019942499999996, "min": 0.0039019942499999996, "max": 0.11280323399000002, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.006322004366666079, "min": 0.006322004366666079, "max": 0.3464207649230957, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.09483006596565247, "min": 0.09059952199459076, "max": 2.42494535446167, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 359.32894736842104, "min": 334.0705882352941, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 27309.0, "min": 15984.0, "max": 32445.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.5617052436267074, "min": -1.0000000521540642, "max": 1.6166809261554764, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 118.68959851562977, "min": -32.000001668930054, "max": 146.95139849185944, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.5617052436267074, "min": -1.0000000521540642, "max": 1.6166809261554764, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 118.68959851562977, "min": -32.000001668930054, "max": 146.95139849185944, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.023627302823163183, "min": 0.023627302823163183, "max": 7.672519818879664, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 1.795675014560402, "min": 1.795675014560402, "max": 122.76031710207462, "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": "1749098559", "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": "2.7.1+cu126", "numpy_version": "1.23.5", "end_time_seconds": "1749101071" }, "total": 2511.9621966439995, "count": 1, "self": 0.4767756559999725, "children": { "run_training.setup": { "total": 0.02199216099984369, "count": 1, "self": 0.02199216099984369 }, "TrainerController.start_learning": { "total": 2511.463428827, "count": 1, "self": 1.609908126044047, "children": { "TrainerController._reset_env": { "total": 2.4360228909999933, "count": 1, "self": 2.4360228909999933 }, "TrainerController.advance": { "total": 2507.3218476329553, "count": 63801, "self": 1.6667371868893497, "children": { "env_step": { "total": 1768.0515789170101, "count": 63801, "self": 1590.2960046579256, "children": { "SubprocessEnvManager._take_step": { "total": 176.82207010607954, "count": 63801, "self": 5.394103585125549, "children": { "TorchPolicy.evaluate": { "total": 171.427966520954, "count": 62559, "self": 171.427966520954 } } }, "workers": { "total": 0.9335041530050603, "count": 63801, "self": 0.0, "children": { "worker_root": { "total": 2505.519235399918, "count": 63801, "is_parallel": true, "self": 1046.194658390008, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0022433430001456145, "count": 1, "is_parallel": true, "self": 0.0007448250003108114, "children": { "_process_rank_one_or_two_observation": { "total": 0.001498517999834803, "count": 8, "is_parallel": true, "self": 0.001498517999834803 } } }, "UnityEnvironment.step": { "total": 0.05467721500008338, "count": 1, "is_parallel": true, "self": 0.0006206119999205839, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005244320000201697, "count": 1, "is_parallel": true, "self": 0.0005244320000201697 }, "communicator.exchange": { "total": 0.05174444599992967, "count": 1, "is_parallel": true, "self": 0.05174444599992967 }, "steps_from_proto": { "total": 0.0017877250002129585, "count": 1, "is_parallel": true, "self": 0.00038896800060683745, "children": { "_process_rank_one_or_two_observation": { "total": 0.001398756999606121, "count": 8, "is_parallel": true, "self": 0.001398756999606121 } } } } } } }, "UnityEnvironment.step": { "total": 1459.3245770099102, "count": 63800, "is_parallel": true, "self": 35.191958244886564, "children": { "UnityEnvironment._generate_step_input": { "total": 26.216574111017735, "count": 63800, "is_parallel": true, "self": 26.216574111017735 }, "communicator.exchange": { "total": 1285.9510801500242, "count": 63800, "is_parallel": true, "self": 1285.9510801500242 }, "steps_from_proto": { "total": 111.96496450398172, "count": 63800, "is_parallel": true, "self": 23.669500662166456, "children": { "_process_rank_one_or_two_observation": { "total": 88.29546384181526, "count": 510400, "is_parallel": true, "self": 88.29546384181526 } } } } } } } } } } }, "trainer_advance": { "total": 737.6035315290555, "count": 63801, "self": 2.9337186920461136, "children": { "process_trajectory": { "total": 146.31576319900137, "count": 63801, "self": 146.10025464600108, "children": { "RLTrainer._checkpoint": { "total": 0.2155085530002907, "count": 2, "self": 0.2155085530002907 } } }, "_update_policy": { "total": 588.3540496380081, "count": 444, "self": 327.8787609779897, "children": { "TorchPPOOptimizer.update": { "total": 260.47528866001835, "count": 22806, "self": 260.47528866001835 } } } } } } }, "trainer_threads": { "total": 1.2930004231748171e-06, "count": 1, "self": 1.2930004231748171e-06 }, "TrainerController._save_models": { "total": 0.0956488840001839, "count": 1, "self": 0.001202853999529907, "children": { "RLTrainer._checkpoint": { "total": 0.09444603000065399, "count": 1, "self": 0.09444603000065399 } } } } } } }