{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.1361546367406845, "min": 0.12755775451660156, "max": 1.46051824092865, "count": 100 }, "Pyramids.Policy.Entropy.sum": { "value": 4069.3896484375, "min": 3838.97802734375, "max": 44306.28125, "count": 100 }, "Pyramids.Step.mean": { "value": 2999937.0, "min": 29952.0, "max": 2999937.0, "count": 100 }, "Pyramids.Step.sum": { "value": 2999937.0, "min": 29952.0, "max": 2999937.0, "count": 100 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.7945671677589417, "min": -0.17170310020446777, "max": 0.8766002058982849, "count": 100 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 241.5484161376953, "min": -40.693634033203125, "max": 268.39801025390625, "count": 100 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -0.008171307854354382, "min": -0.012753987684845924, "max": 0.3145892322063446, "count": 100 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -2.4840774536132812, "min": -3.8389501571655273, "max": 74.55764770507812, "count": 100 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06867012760498566, "min": 0.06521343575407039, "max": 0.07318826600071501, "count": 100 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9613817864697991, "min": 0.4775440939434472, "max": 1.0825946712090324, "count": 100 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.015932791787406746, "min": 0.0013238003899818513, "max": 0.017329587172679357, "count": 100 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.22305908502369443, "min": 0.015885604679782214, "max": 0.242614220417511, "count": 100 }, "Pyramids.Policy.LearningRate.mean": { "value": 1.5695994768333284e-06, "min": 1.5695994768333284e-06, "max": 0.00029838354339596195, "count": 100 }, "Pyramids.Policy.LearningRate.sum": { "value": 2.1974392675666597e-05, "min": 2.1974392675666597e-05, "max": 0.004072517442494233, "count": 100 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10052316666666665, "min": 0.10052316666666665, "max": 0.19946118095238097, "count": 100 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4073243333333332, "min": 1.3962282666666668, "max": 2.857505766666667, "count": 100 }, "Pyramids.Policy.Beta.mean": { "value": 6.226434999999985e-05, "min": 6.226434999999985e-05, "max": 0.009946171977142856, "count": 100 }, "Pyramids.Policy.Beta.sum": { "value": 0.0008717008999999978, "min": 0.0008717008999999978, "max": 0.13576482608999998, "count": 100 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.008122281171381474, "min": 0.007557399570941925, "max": 0.4077818989753723, "count": 100 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.11371193081140518, "min": 0.10580359399318695, "max": 2.854473352432251, "count": 100 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 229.43283582089552, "min": 204.25714285714287, "max": 999.0, "count": 100 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30744.0, "min": 15984.0, "max": 33011.0, "count": 100 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.724627053211058, "min": -1.0000000521540642, "max": 1.7883642757577556, "count": 100 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 229.3753980770707, "min": -30.580001659691334, "max": 251.35619761794806, "count": 100 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.724627053211058, "min": -1.0000000521540642, "max": 1.7883642757577556, "count": 100 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 229.3753980770707, "min": -30.580001659691334, "max": 251.35619761794806, "count": 100 }, "Pyramids.Policy.RndReward.mean": { "value": 0.019083163959540503, "min": 0.017236884946136604, "max": 7.341188870370388, "count": 100 }, "Pyramids.Policy.RndReward.sum": { "value": 2.538060806618887, "min": 2.3529925889979495, "max": 117.45902192592621, "count": 100 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 100 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 100 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1694527801", "python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [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": "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": "1694535242" }, "total": 7440.891022198, "count": 1, "self": 0.7833144680007535, "children": { "run_training.setup": { "total": 0.04917014400007247, "count": 1, "self": 0.04917014400007247 }, "TrainerController.start_learning": { "total": 7440.058537586, "count": 1, "self": 4.0052658119739135, "children": { "TrainerController._reset_env": { "total": 4.019375286000013, "count": 1, "self": 4.019375286000013 }, "TrainerController.advance": { "total": 7431.862733687027, "count": 195338, "self": 4.3087558690695005, "children": { "env_step": { "total": 5474.177049442924, "count": 195338, "self": 5141.60610358462, "children": { "SubprocessEnvManager._take_step": { "total": 330.10786218423414, "count": 195338, "self": 14.651638160289167, "children": { "TorchPolicy.evaluate": { "total": 315.45622402394497, "count": 187558, "self": 315.45622402394497 } } }, "workers": { "total": 2.463083674070049, "count": 195338, "self": 0.0, "children": { "worker_root": { "total": 7424.598986643024, "count": 195338, "is_parallel": true, "self": 2635.346304624082, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.001902434999919933, "count": 1, "is_parallel": true, "self": 0.0006425539993415441, "children": { "_process_rank_one_or_two_observation": { "total": 0.001259881000578389, "count": 8, "is_parallel": true, "self": 0.001259881000578389 } } }, "UnityEnvironment.step": { "total": 0.07255168999995476, "count": 1, "is_parallel": true, "self": 0.0005602329997600464, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005499270000655088, "count": 1, "is_parallel": true, "self": 0.0005499270000655088 }, "communicator.exchange": { "total": 0.06850658500002282, "count": 1, "is_parallel": true, "self": 0.06850658500002282 }, "steps_from_proto": { "total": 0.0029349450001063815, "count": 1, "is_parallel": true, "self": 0.0003859000005377311, "children": { "_process_rank_one_or_two_observation": { "total": 0.0025490449995686504, "count": 8, "is_parallel": true, "self": 0.0025490449995686504 } } } } } } }, "UnityEnvironment.step": { "total": 4789.252682018941, "count": 195337, "is_parallel": true, "self": 103.3238895241966, "children": { "UnityEnvironment._generate_step_input": { "total": 73.30962652311905, "count": 195337, "is_parallel": true, "self": 73.30962652311905 }, "communicator.exchange": { "total": 4276.801311144426, "count": 195337, "is_parallel": true, "self": 4276.801311144426 }, "steps_from_proto": { "total": 335.81785482719965, "count": 195337, "is_parallel": true, "self": 66.5160536697033, "children": { "_process_rank_one_or_two_observation": { "total": 269.30180115749636, "count": 1562696, "is_parallel": true, "self": 269.30180115749636 } } } } } } } } } } }, "trainer_advance": { "total": 1953.376928375033, "count": 195338, "self": 8.176945569754253, "children": { "process_trajectory": { "total": 356.2814652652612, "count": 195338, "self": 355.55455622726026, "children": { "RLTrainer._checkpoint": { "total": 0.7269090380009402, "count": 6, "self": 0.7269090380009402 } } }, "_update_policy": { "total": 1588.9185175400175, "count": 1400, "self": 1028.525685467058, "children": { "TorchPPOOptimizer.update": { "total": 560.3928320729594, "count": 68358, "self": 560.3928320729594 } } } } } } }, "trainer_threads": { "total": 1.631999111850746e-06, "count": 1, "self": 1.631999111850746e-06 }, "TrainerController._save_models": { "total": 0.17116116900069756, "count": 1, "self": 0.0020317489997978555, "children": { "RLTrainer._checkpoint": { "total": 0.1691294200008997, "count": 1, "self": 0.1691294200008997 } } } } } } }