{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 1.0646613836288452, "min": 1.0646613836288452, "max": 1.4711694717407227, "count": 3 }, "Pyramids.Policy.Entropy.sum": { "value": 31888.736328125, "min": 31888.736328125, "max": 44629.3984375, "count": 3 }, "Pyramids.Step.mean": { "value": 89951.0, "min": 29952.0, "max": 89951.0, "count": 3 }, "Pyramids.Step.sum": { "value": 89951.0, "min": 29952.0, "max": 89951.0, "count": 3 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": -0.07193683087825775, "min": -0.07193683087825775, "max": 0.10903245210647583, "count": 3 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": -17.26483917236328, "min": -17.26483917236328, "max": 25.84069061279297, "count": 3 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.10358892381191254, "min": 0.10358892381191254, "max": 0.1658889353275299, "count": 3 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 24.86134147644043, "min": 24.86134147644043, "max": 40.14512252807617, "count": 3 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06408439005856496, "min": 0.06408439005856496, "max": 0.07208999549105613, "count": 3 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.7049282906442146, "min": 0.5046299684373929, "max": 0.7085097216114451, "count": 3 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.00028752326244752593, "min": 0.00028752326244752593, "max": 0.004838845401727831, "count": 3 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.0031627558869227854, "min": 0.0031627558869227854, "max": 0.033871917812094816, "count": 3 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.9683073439e-05, "min": 7.9683073439e-05, "max": 0.0002515063018788571, "count": 3 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.000876513807829, "min": 0.000876513807829, "max": 0.0017605441131519997, "count": 3 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.12656099999999998, "min": 0.12656099999999998, "max": 0.1838354285714286, "count": 3 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.3921709999999998, "min": 1.2868480000000002, "max": 1.5465579999999999, "count": 3 }, "Pyramids.Policy.Beta.mean": { "value": 0.0026634439, "min": 0.0026634439, "max": 0.008385159314285713, "count": 3 }, "Pyramids.Policy.Beta.sum": { "value": 0.029297882900000002, "min": 0.029297882900000002, "max": 0.058696115199999996, "count": 3 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.0787273719906807, "min": 0.0787273719906807, "max": 0.3258635997772217, "count": 3 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.8660010695457458, "min": 0.8660010695457458, "max": 2.2810451984405518, "count": 3 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 999.0, "min": 972.3823529411765, "max": 999.0, "count": 3 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30969.0, "min": 15984.0, "max": 33061.0, "count": 3 }, "Pyramids.Environment.CumulativeReward.mean": { "value": -0.9999355356539449, "min": -1.0000000521540642, "max": -0.8556412269963938, "count": 3 }, "Pyramids.Environment.CumulativeReward.sum": { "value": -30.998001605272293, "min": -30.998001605272293, "max": -16.000000834465027, "count": 3 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": -0.9999355356539449, "min": -1.0000000521540642, "max": -0.8556412269963938, "count": 3 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": -30.998001605272293, "min": -30.998001605272293, "max": -16.000000834465027, "count": 3 }, "Pyramids.Policy.RndReward.mean": { "value": 0.8813057140477242, "min": 0.8813057140477242, "max": 7.295567667111754, "count": 3 }, "Pyramids.Policy.RndReward.sum": { "value": 27.32047713547945, "min": 27.32047713547945, "max": 116.72908267378807, "count": 3 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 3 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 3 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1748079713", "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": "2.7.0+cu126", "numpy_version": "1.23.5", "end_time_seconds": "1748079911" }, "total": 198.08658607799998, "count": 1, "self": 0.48427313599995614, "children": { "run_training.setup": { "total": 0.019944675000033385, "count": 1, "self": 0.019944675000033385 }, "TrainerController.start_learning": { "total": 197.582368267, "count": 1, "self": 0.11894500701441757, "children": { "TrainerController._reset_env": { "total": 2.2487035710000782, "count": 1, "self": 2.2487035710000782 }, "TrainerController.advance": { "total": 195.09844964198533, "count": 6291, "self": 0.14207545598810611, "children": { "env_step": { "total": 128.84404812500156, "count": 6291, "self": 113.20385726201266, "children": { "SubprocessEnvManager._take_step": { "total": 15.567520525991995, "count": 6291, "self": 0.4681209089853837, "children": { "TorchPolicy.evaluate": { "total": 15.099399617006611, "count": 6283, "self": 15.099399617006611 } } }, "workers": { "total": 0.07267033699690728, "count": 6291, "self": 0.0, "children": { "worker_root": { "total": 197.02493919201083, "count": 6291, "is_parallel": true, "self": 94.80708520302665, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.002038632999983747, "count": 1, "is_parallel": true, "self": 0.0006578889999673265, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013807440000164206, "count": 8, "is_parallel": true, "self": 0.0013807440000164206 } } }, "UnityEnvironment.step": { "total": 0.08060050200015212, "count": 1, "is_parallel": true, "self": 0.0005080880002878985, "children": { "UnityEnvironment._generate_step_input": { "total": 0.000532840000005308, "count": 1, "is_parallel": true, "self": 0.000532840000005308 }, "communicator.exchange": { "total": 0.07796224300000176, "count": 1, "is_parallel": true, "self": 0.07796224300000176 }, "steps_from_proto": { "total": 0.0015973309998571494, "count": 1, "is_parallel": true, "self": 0.0003499869999359362, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012473439999212133, "count": 8, "is_parallel": true, "self": 0.0012473439999212133 } } } } } } }, "UnityEnvironment.step": { "total": 102.21785398898419, "count": 6290, "is_parallel": true, "self": 3.1636413130001984, "children": { "UnityEnvironment._generate_step_input": { "total": 2.4241675740006485, "count": 6290, "is_parallel": true, "self": 2.4241675740006485 }, "communicator.exchange": { "total": 86.88600490699537, "count": 6290, "is_parallel": true, "self": 86.88600490699537 }, "steps_from_proto": { "total": 9.744040194987974, "count": 6290, "is_parallel": true, "self": 1.912765758995647, "children": { "_process_rank_one_or_two_observation": { "total": 7.831274435992327, "count": 50320, "is_parallel": true, "self": 7.831274435992327 } } } } } } } } } } }, "trainer_advance": { "total": 66.11232606099566, "count": 6291, "self": 0.15701774100671173, "children": { "process_trajectory": { "total": 12.387249768988568, "count": 6291, "self": 12.387249768988568 }, "_update_policy": { "total": 53.56805855100038, "count": 32, "self": 29.683329667000635, "children": { "TorchPPOOptimizer.update": { "total": 23.884728883999742, "count": 2274, "self": 23.884728883999742 } } } } } } }, "trainer_threads": { "total": 9.830000635702163e-07, "count": 1, "self": 9.830000635702163e-07 }, "TrainerController._save_models": { "total": 0.11626906400010739, "count": 1, "self": 0.0013207780002630898, "children": { "RLTrainer._checkpoint": { "total": 0.1149482859998443, "count": 1, "self": 0.1149482859998443 } } } } } } }