{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.5708813071250916, "min": 0.5655150413513184, "max": 1.4859533309936523, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 17099.037109375, "min": 16977.06640625, "max": 45077.87890625, "count": 33 }, "Pyramids.Step.mean": { "value": 989956.0, "min": 29952.0, "max": 989956.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989956.0, "min": 29952.0, "max": 989956.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": -0.06450152397155762, "min": -0.11216867715120316, "max": -0.03278736397624016, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": -15.609369277954102, "min": -26.920482635498047, "max": -7.770605087280273, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.01114608719944954, "min": 0.0067435503005981445, "max": 0.18880322575569153, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 2.6973531246185303, "min": 1.6386827230453491, "max": 45.312774658203125, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06820288197770362, "min": 0.06445500577475677, "max": 0.07252554854213991, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9548403476878508, "min": 0.4788092781673186, "max": 1.033808975441692, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.0019665540029339813, "min": 5.042557388877481e-05, "max": 0.0049891224837221955, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.027531756041075738, "min": 0.0005546813127765229, "max": 0.05715166313196581, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.4364975211999985e-06, "min": 7.4364975211999985e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010411096529679998, "min": 0.00010411096529679998, "max": 0.002900874233042, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.1024788, "min": 0.1024788, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4347032, "min": 1.327104, "max": 2.166958, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00025763211999999994, "min": 0.00025763211999999994, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.003606849679999999, "min": 0.003606849679999999, "max": 0.0967191042, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.010786646977066994, "min": 0.010786646977066994, "max": 0.2914198935031891, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.1510130614042282, "min": 0.1510130614042282, "max": 2.0399391651153564, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 969.0645161290323, "min": 858.4193548387096, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30041.0, "min": 15984.0, "max": 32456.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": -0.776090374156352, "min": -1.0000000521540642, "max": -0.3427355195726118, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": -24.058801598846912, "min": -32.000001668930054, "max": -10.624801106750965, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": -0.776090374156352, "min": -1.0000000521540642, "max": -0.3427355195726118, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": -24.058801598846912, "min": -32.000001668930054, "max": -10.624801106750965, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.10775177314456913, "min": 0.10153135738801211, "max": 5.862117176875472, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.340304967481643, "min": 3.1965397249441594, "max": 93.79387483000755, "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": "1682382792", "python_version": "3.9.16 (main, Dec 7 2022, 01:11:51) \n[GCC 9.4.0]", "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": "0.31.0.dev0", "mlagents_envs_version": "0.31.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.11.0+cu102", "numpy_version": "1.21.2", "end_time_seconds": "1682384833" }, "total": 2041.520196816, "count": 1, "self": 0.8555173459999423, "children": { "run_training.setup": { "total": 0.11233643200012011, "count": 1, "self": 0.11233643200012011 }, "TrainerController.start_learning": { "total": 2040.552343038, "count": 1, "self": 1.4334295900398502, "children": { "TrainerController._reset_env": { "total": 3.979769903000033, "count": 1, "self": 3.979769903000033 }, "TrainerController.advance": { "total": 2034.9785624699603, "count": 62979, "self": 1.5554788879740045, "children": { "env_step": { "total": 1408.948517668032, "count": 62979, "self": 1295.4697900840447, "children": { "SubprocessEnvManager._take_step": { "total": 112.59227783697634, "count": 62979, "self": 5.209899514972221, "children": { "TorchPolicy.evaluate": { "total": 107.38237832200412, "count": 62554, "self": 107.38237832200412 } } }, "workers": { "total": 0.8864497470110564, "count": 62979, "self": 0.0, "children": { "worker_root": { "total": 2035.039257309963, "count": 62979, "is_parallel": true, "self": 857.4642484309554, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.004779885000061768, "count": 1, "is_parallel": true, "self": 0.003313747999982297, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014661370000794705, "count": 8, "is_parallel": true, "self": 0.0014661370000794705 } } }, "UnityEnvironment.step": { "total": 0.04782473199998094, "count": 1, "is_parallel": true, "self": 0.0006112989999564888, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005176990000563819, "count": 1, "is_parallel": true, "self": 0.0005176990000563819 }, "communicator.exchange": { "total": 0.044868495999935476, "count": 1, "is_parallel": true, "self": 0.044868495999935476 }, "steps_from_proto": { "total": 0.0018272380000325938, "count": 1, "is_parallel": true, "self": 0.00040979000004881527, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014174479999837786, "count": 8, "is_parallel": true, "self": 0.0014174479999837786 } } } } } } }, "UnityEnvironment.step": { "total": 1177.5750088790076, "count": 62978, "is_parallel": true, "self": 34.22461183014843, "children": { "UnityEnvironment._generate_step_input": { "total": 25.94166392997522, "count": 62978, "is_parallel": true, "self": 25.94166392997522 }, "communicator.exchange": { "total": 1014.62582821093, "count": 62978, "is_parallel": true, "self": 1014.62582821093 }, "steps_from_proto": { "total": 102.78290490795393, "count": 62978, "is_parallel": true, "self": 21.943200839087922, "children": { "_process_rank_one_or_two_observation": { "total": 80.83970406886601, "count": 503824, "is_parallel": true, "self": 80.83970406886601 } } } } } } } } } } }, "trainer_advance": { "total": 624.4745659139542, "count": 62979, "self": 2.315489458949287, "children": { "process_trajectory": { "total": 109.74366404500597, "count": 62979, "self": 109.4614732710063, "children": { "RLTrainer._checkpoint": { "total": 0.2821907739996732, "count": 2, "self": 0.2821907739996732 } } }, "_update_policy": { "total": 512.4154124099989, "count": 410, "self": 329.06317192099027, "children": { "TorchPPOOptimizer.update": { "total": 183.35224048900864, "count": 22908, "self": 183.35224048900864 } } } } } } }, "trainer_threads": { "total": 1.4709999049955513e-06, "count": 1, "self": 1.4709999049955513e-06 }, "TrainerController._save_models": { "total": 0.1605796039998495, "count": 1, "self": 0.0021674390000043786, "children": { "RLTrainer._checkpoint": { "total": 0.15841216499984512, "count": 1, "self": 0.15841216499984512 } } } } } } }