{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.45951950550079346, "min": 0.45951950550079346, "max": 1.3073469400405884, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 13756.17578125, "min": 13756.17578125, "max": 39659.67578125, "count": 33 }, "Pyramids.Step.mean": { "value": 989997.0, "min": 29901.0, "max": 989997.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989997.0, "min": 29901.0, "max": 989997.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.5230852961540222, "min": -0.09277036786079407, "max": 0.6073257923126221, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 144.89462280273438, "min": -22.635969161987305, "max": 168.83657836914062, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.053420089185237885, "min": -0.0034140017814934254, "max": 0.41429218649864197, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 14.797364234924316, "min": -0.9490925073623657, "max": 98.18724822998047, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06367975641232215, "min": 0.06367975641232215, "max": 0.07449174448118952, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9551963461848323, "min": 0.5796412080492537, "max": 1.062237931531854, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.017143356681229193, "min": 0.0009248526530807243, "max": 0.017237112276447066, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.2571503502184379, "min": 0.01109823183696869, "max": 0.25855668414670596, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.441057519680003e-06, "min": 7.441057519680003e-06, "max": 0.0002948457392180875, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00011161586279520004, "min": 0.00011161586279520004, "max": 0.0036354268881911003, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10248032, "min": 0.10248032, "max": 0.19828191250000002, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.5372048, "min": 1.4779371999999997, "max": 2.6118088999999998, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00025778396800000007, "min": 0.00025778396800000007, "max": 0.00982836305875, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.003866759520000001, "min": 0.003866759520000001, "max": 0.12119970911, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.011454583145678043, "min": 0.011454583145678043, "max": 0.4336065649986267, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.17181874811649323, "min": 0.1609770506620407, "max": 3.4688525199890137, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 363.3375, "min": 320.55913978494624, "max": 990.6206896551724, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29067.0, "min": 16316.0, "max": 32596.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.5656197352541819, "min": -0.9258061110070257, "max": 1.6579247090604998, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 126.81519855558872, "min": -30.55160166323185, "max": 154.18699794262648, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.5656197352541819, "min": -0.9258061110070257, "max": 1.6579247090604998, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 126.81519855558872, "min": -30.55160166323185, "max": 154.18699794262648, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.043381846219554175, "min": 0.039163820208012755, "max": 8.770061861066257, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.513929543783888, "min": 3.513929543783888, "max": 149.09105163812637, "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": "1774349792", "python_version": "3.10.12 (main, Mar 3 2026, 11:56:32) [GCC 11.4.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn /content/ml-agents/config/ppo/PyramidsRND.yaml --env=/content/ml-agents/training-envs-executables/linux/Pyramids/Pyramids --run-id=PyramidsTraining --no-graphics", "mlagents_version": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.8.0+cu128", "numpy_version": "1.23.5", "end_time_seconds": "1774352008" }, "total": 2215.147890494, "count": 1, "self": 1.253988529000253, "children": { "run_training.setup": { "total": 0.02878663299998152, "count": 1, "self": 0.02878663299998152 }, "TrainerController.start_learning": { "total": 2213.8651153319997, "count": 1, "self": 1.3933979539451684, "children": { "TrainerController._reset_env": { "total": 3.2693291969999336, "count": 1, "self": 3.2693291969999336 }, "TrainerController.advance": { "total": 2209.0897225200547, "count": 63911, "self": 1.4411164489938528, "children": { "env_step": { "total": 1540.935677703997, "count": 63911, "self": 1386.0134546429852, "children": { "SubprocessEnvManager._take_step": { "total": 154.0728831670417, "count": 63911, "self": 4.708483322068673, "children": { "TorchPolicy.evaluate": { "total": 149.36439984497304, "count": 62555, "self": 149.36439984497304 } } }, "workers": { "total": 0.849339893970182, "count": 63911, "self": 0.0, "children": { "worker_root": { "total": 2207.748057136973, "count": 63911, "is_parallel": true, "self": 939.9113298389618, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005398995000064133, "count": 1, "is_parallel": true, "self": 0.0032955129998981647, "children": { "_process_rank_one_or_two_observation": { "total": 0.002103482000165968, "count": 8, "is_parallel": true, "self": 0.002103482000165968 } } }, "UnityEnvironment.step": { "total": 0.06000990199993339, "count": 1, "is_parallel": true, "self": 0.0006024409999554337, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005850630000168167, "count": 1, "is_parallel": true, "self": 0.0005850630000168167 }, "communicator.exchange": { "total": 0.057077855999978055, "count": 1, "is_parallel": true, "self": 0.057077855999978055 }, "steps_from_proto": { "total": 0.0017445419999830847, "count": 1, "is_parallel": true, "self": 0.0003749849997802812, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013695570002028035, "count": 8, "is_parallel": true, "self": 0.0013695570002028035 } } } } } } }, "UnityEnvironment.step": { "total": 1267.836727298011, "count": 63910, "is_parallel": true, "self": 34.39222513399977, "children": { "UnityEnvironment._generate_step_input": { "total": 23.47740528601139, "count": 63910, "is_parallel": true, "self": 23.47740528601139 }, "communicator.exchange": { "total": 1097.6219775779614, "count": 63910, "is_parallel": true, "self": 1097.6219775779614 }, "steps_from_proto": { "total": 112.34511930003839, "count": 63910, "is_parallel": true, "self": 23.70870833116237, "children": { "_process_rank_one_or_two_observation": { "total": 88.63641096887602, "count": 511280, "is_parallel": true, "self": 88.63641096887602 } } } } } } } } } } }, "trainer_advance": { "total": 666.7129283670639, "count": 63911, "self": 2.7841519210537626, "children": { "process_trajectory": { "total": 127.34662603900676, "count": 63911, "self": 127.12780509900642, "children": { "RLTrainer._checkpoint": { "total": 0.21882094000034158, "count": 2, "self": 0.21882094000034158 } } }, "_update_policy": { "total": 536.5821504070034, "count": 457, "self": 295.7930077620157, "children": { "TorchPPOOptimizer.update": { "total": 240.7891426449877, "count": 22776, "self": 240.7891426449877 } } } } } } }, "trainer_threads": { "total": 8.160000106727239e-07, "count": 1, "self": 8.160000106727239e-07 }, "TrainerController._save_models": { "total": 0.11266484499992657, "count": 1, "self": 0.001470989000154077, "children": { "RLTrainer._checkpoint": { "total": 0.1111938559997725, "count": 1, "self": 0.1111938559997725 } } } } } } }