{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.4721953868865967, "min": 0.4721953868865967, "max": 1.493204116821289, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 14097.865234375, "min": 14097.865234375, "max": 45297.83984375, "count": 33 }, "Pyramids.Step.mean": { "value": 989981.0, "min": 29952.0, "max": 989981.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989981.0, "min": 29952.0, "max": 989981.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.36898553371429443, "min": -0.08865886181592941, "max": 0.3906594216823578, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 97.04319763183594, "min": -21.366785049438477, "max": 103.52474975585938, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -0.032084815204143524, "min": -0.032084815204143524, "max": 0.2022375762462616, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -8.43830680847168, "min": -8.43830680847168, "max": 48.537017822265625, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06696300321934921, "min": 0.06482201028952621, "max": 0.07428567994080083, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9374820450708891, "min": 0.4864473035659417, "max": 1.0797611826515185, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.01300539549646644, "min": 0.0006810838695920599, "max": 0.013819628464781478, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.18207553695053016, "min": 0.006607853886844064, "max": 0.1934747985069407, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.69565457767143e-06, "min": 7.69565457767143e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010773916408740002, "min": 0.00010773916408740002, "max": 0.0033807812730729998, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10256518571428572, "min": 0.10256518571428572, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4359126, "min": 1.3691136000000002, "max": 2.526927, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00026626205285714294, "min": 0.00026626205285714294, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.003727668740000001, "min": 0.003727668740000001, "max": 0.11272000729999998, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.013073139823973179, "min": 0.013073139823973179, "max": 0.39544448256492615, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.18302395939826965, "min": 0.18302395939826965, "max": 2.76811146736145, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 451.72131147540983, "min": 430.55555555555554, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 27555.0, "min": 15984.0, "max": 32558.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.3131866462528705, "min": -1.0000000521540642, "max": 1.402733309297926, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 78.79119877517223, "min": -32.000001668930054, "max": 100.99679826945066, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.3131866462528705, "min": -1.0000000521540642, "max": 1.402733309297926, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 78.79119877517223, "min": -32.000001668930054, "max": 100.99679826945066, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.06140258851761852, "min": 0.0577265878859584, "max": 7.813111422583461, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.6841553110571112, "min": 3.6841553110571112, "max": 125.00978276133537, "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": "1739168610", "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": "2.6.0+cu124", "numpy_version": "1.23.5", "end_time_seconds": "1739170876" }, "total": 2266.500905179, "count": 1, "self": 0.4967932709996603, "children": { "run_training.setup": { "total": 0.022443112000019028, "count": 1, "self": 0.022443112000019028 }, "TrainerController.start_learning": { "total": 2265.981668796, "count": 1, "self": 1.4262639259641219, "children": { "TrainerController._reset_env": { "total": 3.218919051999819, "count": 1, "self": 3.218919051999819 }, "TrainerController.advance": { "total": 2261.247164184036, "count": 63596, "self": 1.4708147980322792, "children": { "env_step": { "total": 1574.7532440460425, "count": 63596, "self": 1415.0824145039085, "children": { "SubprocessEnvManager._take_step": { "total": 158.82616301405892, "count": 63596, "self": 4.839324174033209, "children": { "TorchPolicy.evaluate": { "total": 153.9868388400257, "count": 62582, "self": 153.9868388400257 } } }, "workers": { "total": 0.8446665280750949, "count": 63596, "self": 0.0, "children": { "worker_root": { "total": 2260.6057218870005, "count": 63596, "is_parallel": true, "self": 964.6158320479954, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.006391806999999972, "count": 1, "is_parallel": true, "self": 0.0049930800000765885, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013987269999233831, "count": 8, "is_parallel": true, "self": 0.0013987269999233831 } } }, "UnityEnvironment.step": { "total": 0.10376846100007242, "count": 1, "is_parallel": true, "self": 0.000515161999828706, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004891589999260759, "count": 1, "is_parallel": true, "self": 0.0004891589999260759 }, "communicator.exchange": { "total": 0.10094323700013774, "count": 1, "is_parallel": true, "self": 0.10094323700013774 }, "steps_from_proto": { "total": 0.0018209030001798965, "count": 1, "is_parallel": true, "self": 0.0004953610000484332, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013255420001314633, "count": 8, "is_parallel": true, "self": 0.0013255420001314633 } } } } } } }, "UnityEnvironment.step": { "total": 1295.9898898390052, "count": 63595, "is_parallel": true, "self": 32.198771507023594, "children": { "UnityEnvironment._generate_step_input": { "total": 22.98706648104144, "count": 63595, "is_parallel": true, "self": 22.98706648104144 }, "communicator.exchange": { "total": 1143.5183168340373, "count": 63595, "is_parallel": true, "self": 1143.5183168340373 }, "steps_from_proto": { "total": 97.28573501690289, "count": 63595, "is_parallel": true, "self": 19.767963773849033, "children": { "_process_rank_one_or_two_observation": { "total": 77.51777124305386, "count": 508760, "is_parallel": true, "self": 77.51777124305386 } } } } } } } } } } }, "trainer_advance": { "total": 685.0231053399614, "count": 63596, "self": 2.7978552029435377, "children": { "process_trajectory": { "total": 129.12705710201726, "count": 63596, "self": 128.87863575301708, "children": { "RLTrainer._checkpoint": { "total": 0.2484213490001821, "count": 2, "self": 0.2484213490001821 } } }, "_update_policy": { "total": 553.0981930350006, "count": 445, "self": 305.53042718799793, "children": { "TorchPPOOptimizer.update": { "total": 247.56776584700265, "count": 22833, "self": 247.56776584700265 } } } } } } }, "trainer_threads": { "total": 9.99999883788405e-07, "count": 1, "self": 9.99999883788405e-07 }, "TrainerController._save_models": { "total": 0.08932063400015977, "count": 1, "self": 0.0014554820004377689, "children": { "RLTrainer._checkpoint": { "total": 0.087865151999722, "count": 1, "self": 0.087865151999722 } } } } } } }