{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.6341098546981812, "min": 0.6110514998435974, "max": 1.4416582584381104, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 18901.546875, "min": 18302.21484375, "max": 43734.14453125, "count": 33 }, "Pyramids.Step.mean": { "value": 989930.0, "min": 29952.0, "max": 989930.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989930.0, "min": 29952.0, "max": 989930.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.03653291240334511, "min": -0.10923309624195099, "max": 0.11070718616247177, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 8.914031028747559, "min": -26.2159423828125, "max": 27.566089630126953, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.017870547249913216, "min": 0.006423051934689283, "max": 0.32659757137298584, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 4.360413551330566, "min": 1.56080162525177, "max": 77.40362548828125, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.0674890060846727, "min": 0.06571688138829618, "max": 0.07431280248942776, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9448460851854178, "min": 0.4843974076542634, "max": 1.0533845678243476, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.004471762363339492, "min": 9.208782003877487e-05, "max": 0.008486804630794924, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.06260467308675288, "min": 0.0012892294805428482, "max": 0.12730206946192385, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.245976156135712e-06, "min": 7.245976156135712e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010144366618589997, "min": 0.00010144366618589997, "max": 0.003609007896997399, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10241529285714288, "min": 0.10241529285714288, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4338141000000002, "min": 1.3886848, "max": 2.5689816, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002512877564285714, "min": 0.0002512877564285714, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0035180285899999997, "min": 0.0035180285899999997, "max": 0.12030995974, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.014610230922698975, "min": 0.014610230922698975, "max": 0.41627854108810425, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.20454323291778564, "min": 0.20454323291778564, "max": 2.913949728012085, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 868.3783783783783, "min": 682.3157894736842, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 32130.0, "min": 15984.0, "max": 34178.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": -0.22009734648305015, "min": -1.0000000521540642, "max": 0.5280368055560087, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": -8.143601819872856, "min": -31.995201662182808, "max": 20.06539861112833, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": -0.22009734648305015, "min": -1.0000000521540642, "max": 0.5280368055560087, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": -8.143601819872856, "min": -31.995201662182808, "max": 20.06539861112833, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.1296893820116246, "min": 0.11072873893212282, "max": 8.08805986493826, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 4.7985071344301105, "min": 4.207692079420667, "max": 129.40895783901215, "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": "1678872482", "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": "1.8.1+cu102", "numpy_version": "1.21.2", "end_time_seconds": "1678874705" }, "total": 2223.338906328, "count": 1, "self": 0.4835379340011059, "children": { "run_training.setup": { "total": 0.11461777999920741, "count": 1, "self": 0.11461777999920741 }, "TrainerController.start_learning": { "total": 2222.740750614, "count": 1, "self": 1.4417169141670456, "children": { "TrainerController._reset_env": { "total": 6.586836167999536, "count": 1, "self": 6.586836167999536 }, "TrainerController.advance": { "total": 2214.6240201798328, "count": 63172, "self": 1.5358823157639563, "children": { "env_step": { "total": 1549.167171374991, "count": 63172, "self": 1425.5287951739992, "children": { "SubprocessEnvManager._take_step": { "total": 122.74120824500005, "count": 63172, "self": 5.665761172978819, "children": { "TorchPolicy.evaluate": { "total": 117.07544707202123, "count": 62561, "self": 117.07544707202123 } } }, "workers": { "total": 0.8971679559917902, "count": 63172, "self": 0.0, "children": { "worker_root": { "total": 2217.456724589819, "count": 63172, "is_parallel": true, "self": 916.7137947647316, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0019778340001721517, "count": 1, "is_parallel": true, "self": 0.0006740130002071965, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013038209999649553, "count": 8, "is_parallel": true, "self": 0.0013038209999649553 } } }, "UnityEnvironment.step": { "total": 0.05102604099920427, "count": 1, "is_parallel": true, "self": 0.0005796479981654556, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004942209998262115, "count": 1, "is_parallel": true, "self": 0.0004942209998262115 }, "communicator.exchange": { "total": 0.048027380000348785, "count": 1, "is_parallel": true, "self": 0.048027380000348785 }, "steps_from_proto": { "total": 0.0019247920008638175, "count": 1, "is_parallel": true, "self": 0.00044321699897409417, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014815750018897234, "count": 8, "is_parallel": true, "self": 0.0014815750018897234 } } } } } } }, "UnityEnvironment.step": { "total": 1300.7429298250872, "count": 63171, "is_parallel": true, "self": 32.85322743206052, "children": { "UnityEnvironment._generate_step_input": { "total": 25.92962242289468, "count": 63171, "is_parallel": true, "self": 25.92962242289468 }, "communicator.exchange": { "total": 1139.2461806130596, "count": 63171, "is_parallel": true, "self": 1139.2461806130596 }, "steps_from_proto": { "total": 102.71389935707248, "count": 63171, "is_parallel": true, "self": 22.3335198918312, "children": { "_process_rank_one_or_two_observation": { "total": 80.38037946524128, "count": 505368, "is_parallel": true, "self": 80.38037946524128 } } } } } } } } } } }, "trainer_advance": { "total": 663.9209664890777, "count": 63172, "self": 2.644322095025018, "children": { "process_trajectory": { "total": 129.00793402805448, "count": 63172, "self": 128.81231839505563, "children": { "RLTrainer._checkpoint": { "total": 0.19561563299885165, "count": 2, "self": 0.19561563299885165 } } }, "_update_policy": { "total": 532.2687103659982, "count": 448, "self": 335.7965915458517, "children": { "TorchPPOOptimizer.update": { "total": 196.47211882014653, "count": 22785, "self": 196.47211882014653 } } } } } } }, "trainer_threads": { "total": 1.1889997040270828e-06, "count": 1, "self": 1.1889997040270828e-06 }, "TrainerController._save_models": { "total": 0.08817616300075315, "count": 1, "self": 0.0014188710001690197, "children": { "RLTrainer._checkpoint": { "total": 0.08675729200058413, "count": 1, "self": 0.08675729200058413 } } } } } } }