{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.5174436569213867, "min": 0.5174436569213867, "max": 1.4287441968917847, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 15871.03125, "min": 15589.71875, "max": 43342.3828125, "count": 33 }, "Pyramids.Step.mean": { "value": 989951.0, "min": 29952.0, "max": 989951.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989951.0, "min": 29952.0, "max": 989951.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.4723411798477173, "min": -0.09946552664041519, "max": 0.4723411798477173, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 128.9491424560547, "min": -23.97119140625, "max": 128.9491424560547, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.003802003338932991, "min": -0.0008896716753952205, "max": 0.4280623495578766, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 1.0379469394683838, "min": -0.22063857316970825, "max": 101.45077514648438, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.07150962337341514, "min": 0.06571518829772885, "max": 0.07347433631209879, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 1.001134727227812, "min": 0.4856993964583554, "max": 1.0310917089216174, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.01634774996567839, "min": 0.00016203205397028093, "max": 0.01634774996567839, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.22886849951949745, "min": 0.002106416701613652, "max": 0.22886849951949745, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.458761799492854e-06, "min": 7.458761799492854e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010442266519289996, "min": 0.00010442266519289996, "max": 0.003508410230529999, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10248622142857143, "min": 0.10248622142857143, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4348071, "min": 1.3691136000000002, "max": 2.56947, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002583735207142857, "min": 0.0002583735207142857, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0036172292899999997, "min": 0.0036172292899999997, "max": 0.11697005300000002, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.010901412926614285, "min": 0.010901412926614285, "max": 0.6035937666893005, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.15261977910995483, "min": 0.15261977910995483, "max": 4.225156307220459, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 411.36842105263156, "min": 393.8125, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 31264.0, "min": 15984.0, "max": 32942.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.4833368148262565, "min": -1.0000000521540642, "max": 1.5311549723148346, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 112.73359792679548, "min": -32.000001668930054, "max": 122.49239778518677, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.4833368148262565, "min": -1.0000000521540642, "max": 1.5311549723148346, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 112.73359792679548, "min": -32.000001668930054, "max": 122.49239778518677, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.04728845096197849, "min": 0.04728845096197849, "max": 12.186938704922795, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.5939222731103655, "min": 3.5343312439508736, "max": 194.99101927876472, "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": "1780239651", "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": "2.8.0+cu128", "numpy_version": "1.23.5", "end_time_seconds": "1780242009" }, "total": 2357.259327102, "count": 1, "self": 0.4851120259995696, "children": { "run_training.setup": { "total": 0.025087288999998236, "count": 1, "self": 0.025087288999998236 }, "TrainerController.start_learning": { "total": 2356.7491277870004, "count": 1, "self": 1.3639070540129978, "children": { "TrainerController._reset_env": { "total": 3.3557298289999835, "count": 1, "self": 3.3557298289999835 }, "TrainerController.advance": { "total": 2351.9470048799876, "count": 63589, "self": 1.445588437034985, "children": { "env_step": { "total": 1678.1740596610093, "count": 63589, "self": 1519.22220237601, "children": { "SubprocessEnvManager._take_step": { "total": 158.1292226060517, "count": 63589, "self": 4.845116449984289, "children": { "TorchPolicy.evaluate": { "total": 153.28410615606742, "count": 62573, "self": 153.28410615606742 } } }, "workers": { "total": 0.8226346789474519, "count": 63589, "self": 0.0, "children": { "worker_root": { "total": 2350.900398110049, "count": 63589, "is_parallel": true, "self": 950.9267244600965, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.004900631000055, "count": 1, "is_parallel": true, "self": 0.003695878000371522, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012047529996834783, "count": 8, "is_parallel": true, "self": 0.0012047529996834783 } } }, "UnityEnvironment.step": { "total": 0.10388240299994322, "count": 1, "is_parallel": true, "self": 0.0005570349999288737, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004323949999616161, "count": 1, "is_parallel": true, "self": 0.0004323949999616161 }, "communicator.exchange": { "total": 0.09931678800001009, "count": 1, "is_parallel": true, "self": 0.09931678800001009 }, "steps_from_proto": { "total": 0.003576185000042642, "count": 1, "is_parallel": true, "self": 0.0023653709999962302, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012108140000464118, "count": 8, "is_parallel": true, "self": 0.0012108140000464118 } } } } } } }, "UnityEnvironment.step": { "total": 1399.9736736499526, "count": 63588, "is_parallel": true, "self": 34.88917812197769, "children": { "UnityEnvironment._generate_step_input": { "total": 23.98125416702385, "count": 63588, "is_parallel": true, "self": 23.98125416702385 }, "communicator.exchange": { "total": 1230.7298736230048, "count": 63588, "is_parallel": true, "self": 1230.7298736230048 }, "steps_from_proto": { "total": 110.37336773794652, "count": 63588, "is_parallel": true, "self": 22.944427027006896, "children": { "_process_rank_one_or_two_observation": { "total": 87.42894071093963, "count": 508704, "is_parallel": true, "self": 87.42894071093963 } } } } } } } } } } }, "trainer_advance": { "total": 672.3273567819432, "count": 63589, "self": 2.654835209916314, "children": { "process_trajectory": { "total": 126.8063125340268, "count": 63589, "self": 126.48707196902706, "children": { "RLTrainer._checkpoint": { "total": 0.3192405649997454, "count": 2, "self": 0.3192405649997454 } } }, "_update_policy": { "total": 542.8662090380001, "count": 447, "self": 297.3013747939847, "children": { "TorchPPOOptimizer.update": { "total": 245.5648342440154, "count": 22854, "self": 245.5648342440154 } } } } } } }, "trainer_threads": { "total": 9.269997462979518e-07, "count": 1, "self": 9.269997462979518e-07 }, "TrainerController._save_models": { "total": 0.08248509700024442, "count": 1, "self": 0.0012375830001474242, "children": { "RLTrainer._checkpoint": { "total": 0.081247514000097, "count": 1, "self": 0.081247514000097 } } } } } } }