{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.5242890119552612, "min": 0.5198160409927368, "max": 1.5085222721099854, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 15812.556640625, "min": 15602.798828125, "max": 45762.53125, "count": 33 }, "Pyramids.Step.mean": { "value": 989952.0, "min": 29952.0, "max": 989952.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989952.0, "min": 29952.0, "max": 989952.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.414237380027771, "min": -0.09166667610406876, "max": 0.5567175149917603, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 111.01561737060547, "min": -22.000001907348633, "max": 155.32418823242188, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.002206940669566393, "min": -0.008212718181312084, "max": 0.36719396710395813, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 0.591460108757019, "min": -2.159944772720337, "max": 87.02497100830078, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.07065573055435727, "min": 0.06359740228591752, "max": 0.07496003907061946, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9891802277610017, "min": 0.5023638336673706, "max": 1.0646917481279554, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.01340566594375386, "min": 0.0010241960521957378, "max": 0.015459363466878803, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.18767932321255404, "min": 0.012290352626348854, "max": 0.21643108853630325, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.603104608521431e-06, "min": 7.603104608521431e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010644346451930003, "min": 0.00010644346451930003, "max": 0.0037582933472355994, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10253433571428573, "min": 0.10253433571428573, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4354807000000003, "min": 1.3886848, "max": 2.6527644000000006, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002631801378571429, "min": 0.0002631801378571429, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0036845219300000007, "min": 0.0036845219300000007, "max": 0.12529116356, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.009434044361114502, "min": 0.009257475845515728, "max": 0.3544917702674866, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.13207662105560303, "min": 0.12960466742515564, "max": 2.481442451477051, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 389.9577464788732, "min": 334.55172413793105, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 27687.0, "min": 15984.0, "max": 34571.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.4348555342811677, "min": -1.0000000521540642, "max": 1.5504666532593212, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 103.30959846824408, "min": -28.433401599526405, "max": 134.89059883356094, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.4348555342811677, "min": -1.0000000521540642, "max": 1.5504666532593212, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 103.30959846824408, "min": -28.433401599526405, "max": 134.89059883356094, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.03827408184118516, "min": 0.0359413270055996, "max": 7.103593226522207, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 2.755733892565331, "min": 2.755733892565331, "max": 113.65749162435532, "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": "1709502282", "python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [GCC 11.4.0]", "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": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.1.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1709504632" }, "total": 2350.170255792, "count": 1, "self": 0.6931259999992108, "children": { "run_training.setup": { "total": 0.05467059600050561, "count": 1, "self": 0.05467059600050561 }, "TrainerController.start_learning": { "total": 2349.422459196, "count": 1, "self": 1.5782962950297588, "children": { "TrainerController._reset_env": { "total": 2.2112902369999574, "count": 1, "self": 2.2112902369999574 }, "TrainerController.advance": { "total": 2345.494155590971, "count": 63774, "self": 1.6340729130024556, "children": { "env_step": { "total": 1698.1845696958835, "count": 63774, "self": 1554.5454342908997, "children": { "SubprocessEnvManager._take_step": { "total": 142.6651070959133, "count": 63774, "self": 5.183118036145061, "children": { "TorchPolicy.evaluate": { "total": 137.48198905976824, "count": 62546, "self": 137.48198905976824 } } }, "workers": { "total": 0.9740283090704906, "count": 63774, "self": 0.0, "children": { "worker_root": { "total": 2343.4589487439507, "count": 63774, "is_parallel": true, "self": 919.7179341088777, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.001937319999342435, "count": 1, "is_parallel": true, "self": 0.0005849919998581754, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013523279994842596, "count": 8, "is_parallel": true, "self": 0.0013523279994842596 } } }, "UnityEnvironment.step": { "total": 0.05412215100022877, "count": 1, "is_parallel": true, "self": 0.0007157609998102998, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005623359993478516, "count": 1, "is_parallel": true, "self": 0.0005623359993478516 }, "communicator.exchange": { "total": 0.05073796600026981, "count": 1, "is_parallel": true, "self": 0.05073796600026981 }, "steps_from_proto": { "total": 0.00210608800080081, "count": 1, "is_parallel": true, "self": 0.0005625260000670096, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015435620007338002, "count": 8, "is_parallel": true, "self": 0.0015435620007338002 } } } } } } }, "UnityEnvironment.step": { "total": 1423.741014635073, "count": 63773, "is_parallel": true, "self": 37.81483607990867, "children": { "UnityEnvironment._generate_step_input": { "total": 27.913193535046958, "count": 63773, "is_parallel": true, "self": 27.913193535046958 }, "communicator.exchange": { "total": 1245.2838433260513, "count": 63773, "is_parallel": true, "self": 1245.2838433260513 }, "steps_from_proto": { "total": 112.72914169406613, "count": 63773, "is_parallel": true, "self": 22.985449912347576, "children": { "_process_rank_one_or_two_observation": { "total": 89.74369178171855, "count": 510184, "is_parallel": true, "self": 89.74369178171855 } } } } } } } } } } }, "trainer_advance": { "total": 645.6755129820849, "count": 63774, "self": 3.204582051092075, "children": { "process_trajectory": { "total": 134.60687019900433, "count": 63774, "self": 134.24096917700444, "children": { "RLTrainer._checkpoint": { "total": 0.36590102199988905, "count": 2, "self": 0.36590102199988905 } } }, "_update_policy": { "total": 507.8640607319885, "count": 456, "self": 300.7271611360802, "children": { "TorchPPOOptimizer.update": { "total": 207.1368995959083, "count": 22785, "self": 207.1368995959083 } } } } } } }, "trainer_threads": { "total": 1.2040000001434237e-06, "count": 1, "self": 1.2040000001434237e-06 }, "TrainerController._save_models": { "total": 0.13871586899949762, "count": 1, "self": 0.0020124489992667804, "children": { "RLTrainer._checkpoint": { "total": 0.13670342000023084, "count": 1, "self": 0.13670342000023084 } } } } } } }