{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.2515352964401245, "min": 0.23638254404067993, "max": 1.4864236116409302, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 7453.494140625, "min": 7095.25830078125, "max": 45092.1484375, "count": 33 }, "Pyramids.Step.mean": { "value": 989935.0, "min": 29906.0, "max": 989935.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989935.0, "min": 29906.0, "max": 989935.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.48538723587989807, "min": -0.05440981313586235, "max": 0.6464516520500183, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 132.02532958984375, "min": -13.167174339294434, "max": 179.06710815429688, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -0.016310488805174828, "min": -0.03839949890971184, "max": 0.29167523980140686, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -4.436452865600586, "min": -10.636661529541016, "max": 70.29373168945312, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06846062976943339, "min": 0.06445511012507343, "max": 0.07292386991035779, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9584488167720675, "min": 0.6509149939911325, "max": 1.0550700070743915, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.016405140896114983, "min": 0.0020843880967359786, "max": 0.017822253440843063, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.22967197254560975, "min": 0.022928269064095765, "max": 0.26733380161264597, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.252876153835711e-06, "min": 7.252876153835711e-06, "max": 0.0002947544684151778, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010154026615369996, "min": 0.00010154026615369996, "max": 0.0037600834466389003, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10241759285714287, "min": 0.10241759285714287, "max": 0.19825148888888888, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4338463000000001, "min": 1.4338463000000001, "max": 2.6533611000000006, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002515175264285714, "min": 0.0002515175264285714, "max": 0.009825323739999997, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.00352124537, "min": 0.00352124537, "max": 0.12535077389000002, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.010455257259309292, "min": 0.009578200988471508, "max": 0.4772288501262665, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.14637359976768494, "min": 0.13409481942653656, "max": 4.295059680938721, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 344.8095238095238, "min": 334.6489361702128, "max": 978.6969696969697, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 28964.0, "min": 17216.0, "max": 32297.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.4884499782430274, "min": -0.8583576295411948, "max": 1.610332512083542, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 125.0297981724143, "min": -28.32580177485943, "max": 140.8365981504321, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.4884499782430274, "min": -0.8583576295411948, "max": 1.610332512083542, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 125.0297981724143, "min": -28.32580177485943, "max": 140.8365981504321, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.038034500984871385, "min": 0.03667926551334576, "max": 11.008352100849152, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.194898082729196, "min": 3.1168092234875076, "max": 198.15033781528473, "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": "1684236280", "python_version": "3.10.11 (main, Apr 5 2023, 14:15:10) [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=PyramidsTraining --no-graphics --force", "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": "1684238484" }, "total": 2204.8290435570007, "count": 1, "self": 0.4239928030001465, "children": { "run_training.setup": { "total": 0.037453362000633206, "count": 1, "self": 0.037453362000633206 }, "TrainerController.start_learning": { "total": 2204.367597392, "count": 1, "self": 1.386108570943179, "children": { "TrainerController._reset_env": { "total": 3.731340885999998, "count": 1, "self": 3.731340885999998 }, "TrainerController.advance": { "total": 2199.143014197057, "count": 64112, "self": 1.3374823591821041, "children": { "env_step": { "total": 1576.3593771220148, "count": 64112, "self": 1470.1973464801085, "children": { "SubprocessEnvManager._take_step": { "total": 105.37740431794191, "count": 64112, "self": 4.565854802940521, "children": { "TorchPolicy.evaluate": { "total": 100.81154951500139, "count": 62563, "self": 100.81154951500139 } } }, "workers": { "total": 0.7846263239644031, "count": 64112, "self": 0.0, "children": { "worker_root": { "total": 2199.358437832884, "count": 64112, "is_parallel": true, "self": 839.0354529738343, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0016940080004133051, "count": 1, "is_parallel": true, "self": 0.0005337900010999874, "children": { "_process_rank_one_or_two_observation": { "total": 0.0011602179993133177, "count": 8, "is_parallel": true, "self": 0.0011602179993133177 } } }, "UnityEnvironment.step": { "total": 0.04598249099944951, "count": 1, "is_parallel": true, "self": 0.0005420949992185342, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004750199996124138, "count": 1, "is_parallel": true, "self": 0.0004750199996124138 }, "communicator.exchange": { "total": 0.043201238000619924, "count": 1, "is_parallel": true, "self": 0.043201238000619924 }, "steps_from_proto": { "total": 0.0017641379999986384, "count": 1, "is_parallel": true, "self": 0.00036317199919722043, "children": { "_process_rank_one_or_two_observation": { "total": 0.001400966000801418, "count": 8, "is_parallel": true, "self": 0.001400966000801418 } } } } } } }, "UnityEnvironment.step": { "total": 1360.32298485905, "count": 64111, "is_parallel": true, "self": 31.294577941136595, "children": { "UnityEnvironment._generate_step_input": { "total": 22.023485829934543, "count": 64111, "is_parallel": true, "self": 22.023485829934543 }, "communicator.exchange": { "total": 1211.5744832040818, "count": 64111, "is_parallel": true, "self": 1211.5744832040818 }, "steps_from_proto": { "total": 95.43043788389696, "count": 64111, "is_parallel": true, "self": 19.38109179307594, "children": { "_process_rank_one_or_two_observation": { "total": 76.04934609082102, "count": 512888, "is_parallel": true, "self": 76.04934609082102 } } } } } } } } } } }, "trainer_advance": { "total": 621.4461547158598, "count": 64112, "self": 2.5644027749813176, "children": { "process_trajectory": { "total": 104.40456743387222, "count": 64112, "self": 104.15424303787313, "children": { "RLTrainer._checkpoint": { "total": 0.25032439599908685, "count": 2, "self": 0.25032439599908685 } } }, "_update_policy": { "total": 514.4771845070063, "count": 462, "self": 330.5881506359865, "children": { "TorchPPOOptimizer.update": { "total": 183.88903387101982, "count": 22755, "self": 183.88903387101982 } } } } } } }, "trainer_threads": { "total": 1.0399999155197293e-06, "count": 1, "self": 1.0399999155197293e-06 }, "TrainerController._save_models": { "total": 0.1071326979999867, "count": 1, "self": 0.001383179000185919, "children": { "RLTrainer._checkpoint": { "total": 0.10574951899980078, "count": 1, "self": 0.10574951899980078 } } } } } } }