{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.4671494662761688, "min": 0.4671494662761688, "max": 1.3924988508224487, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 14074.279296875, "min": 13929.384765625, "max": 42242.84375, "count": 33 }, "Pyramids.Step.mean": { "value": 989969.0, "min": 29952.0, "max": 989969.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989969.0, "min": 29952.0, "max": 989969.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.08507057279348373, "min": -0.10575323551893234, "max": 0.08507057279348373, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 21.097501754760742, "min": -25.486530303955078, "max": 21.097501754760742, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.05225399136543274, "min": 0.022579381242394447, "max": 0.7404017448425293, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 12.958990097045898, "min": 5.509368896484375, "max": 175.4752197265625, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.0664102877469434, "min": 0.06533160973142986, "max": 0.07269938079838788, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9297440284572076, "min": 0.4836040788146817, "max": 1.0177913311774303, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.008111140180300848, "min": 0.0001247202956558229, "max": 0.01851770633556759, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.11355596252421188, "min": 0.0016213638435256977, "max": 0.12962394434897312, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.503247498950002e-06, "min": 7.503247498950002e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010504546498530003, "min": 0.00010504546498530003, "max": 0.0035074136308621997, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10250105000000001, "min": 0.10250105000000001, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4350147000000002, "min": 1.3691136000000002, "max": 2.5691378, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00025985489500000007, "min": 0.00025985489500000007, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0036379685300000006, "min": 0.0036379685300000006, "max": 0.11693686622, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.022003738209605217, "min": 0.022003738209605217, "max": 0.7469258904457092, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.30805233120918274, "min": 0.30805233120918274, "max": 5.228481292724609, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 786.421052631579, "min": 756.8974358974359, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29884.0, "min": 15984.0, "max": 34149.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 0.23346662597778517, "min": -1.0000000521540642, "max": 0.26846662698647916, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 9.105198413133621, "min": -32.000001668930054, "max": 10.470198452472687, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 0.23346662597778517, "min": -1.0000000521540642, "max": 0.26846662698647916, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 9.105198413133621, "min": -32.000001668930054, "max": 10.470198452472687, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.17855534232251394, "min": 0.17855534232251394, "max": 15.415195751935244, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 6.963658350578044, "min": 6.3973067798651755, "max": 246.6431320309639, "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": "1773883626", "python_version": "3.10.13 (main, Sep 11 2023, 13:44:35) [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": "2.8.0+cu128", "numpy_version": "1.23.5", "end_time_seconds": "1773885791" }, "total": 2164.3104597379997, "count": 1, "self": 0.47904001399911067, "children": { "run_training.setup": { "total": 0.022021775000212074, "count": 1, "self": 0.022021775000212074 }, "TrainerController.start_learning": { "total": 2163.8093979490004, "count": 1, "self": 1.4262358291744022, "children": { "TrainerController._reset_env": { "total": 2.123861572000351, "count": 1, "self": 2.123861572000351 }, "TrainerController.advance": { "total": 2160.1749073568253, "count": 63273, "self": 1.4533864500081108, "children": { "env_step": { "total": 1496.95250360284, "count": 63273, "self": 1346.1210723171043, "children": { "SubprocessEnvManager._take_step": { "total": 150.03830692079373, "count": 63273, "self": 4.726816939822129, "children": { "TorchPolicy.evaluate": { "total": 145.3114899809716, "count": 62578, "self": 145.3114899809716 } } }, "workers": { "total": 0.793124364941832, "count": 63273, "self": 0.0, "children": { "worker_root": { "total": 2157.451709145914, "count": 63273, "is_parallel": true, "self": 927.189133171817, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0018153560004066094, "count": 1, "is_parallel": true, "self": 0.0006085159993745037, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012068400010321056, "count": 8, "is_parallel": true, "self": 0.0012068400010321056 } } }, "UnityEnvironment.step": { "total": 0.05177770299997064, "count": 1, "is_parallel": true, "self": 0.0005757780008934787, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004963840001437347, "count": 1, "is_parallel": true, "self": 0.0004963840001437347 }, "communicator.exchange": { "total": 0.04906073899928742, "count": 1, "is_parallel": true, "self": 0.04906073899928742 }, "steps_from_proto": { "total": 0.0016448019996460062, "count": 1, "is_parallel": true, "self": 0.0003346229987073457, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013101790009386605, "count": 8, "is_parallel": true, "self": 0.0013101790009386605 } } } } } } }, "UnityEnvironment.step": { "total": 1230.2625759740968, "count": 63272, "is_parallel": true, "self": 33.370208038157216, "children": { "UnityEnvironment._generate_step_input": { "total": 22.59027136504119, "count": 63272, "is_parallel": true, "self": 22.59027136504119 }, "communicator.exchange": { "total": 1066.9861452130917, "count": 63272, "is_parallel": true, "self": 1066.9861452130917 }, "steps_from_proto": { "total": 107.31595135780663, "count": 63272, "is_parallel": true, "self": 22.45222959353123, "children": { "_process_rank_one_or_two_observation": { "total": 84.8637217642754, "count": 506176, "is_parallel": true, "self": 84.8637217642754 } } } } } } } } } } }, "trainer_advance": { "total": 661.7690173039773, "count": 63273, "self": 2.560107305727797, "children": { "process_trajectory": { "total": 125.24601274624274, "count": 63273, "self": 125.05573973524315, "children": { "RLTrainer._checkpoint": { "total": 0.19027301099959004, "count": 2, "self": 0.19027301099959004 } } }, "_update_policy": { "total": 533.9628972520068, "count": 444, "self": 295.8931594539463, "children": { "TorchPPOOptimizer.update": { "total": 238.0697377980605, "count": 22788, "self": 238.0697377980605 } } } } } } }, "trainer_threads": { "total": 9.320010576630011e-07, "count": 1, "self": 9.320010576630011e-07 }, "TrainerController._save_models": { "total": 0.08439225899928715, "count": 1, "self": 0.0009278130000893725, "children": { "RLTrainer._checkpoint": { "total": 0.08346444599919778, "count": 1, "self": 0.08346444599919778 } } } } } } }