{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.31270015239715576, "min": 0.30548951029777527, "max": 1.4538123607635498, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 9345.982421875, "min": 9223.3388671875, "max": 44102.8515625, "count": 33 }, "Pyramids.Step.mean": { "value": 989970.0, "min": 29952.0, "max": 989970.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989970.0, "min": 29952.0, "max": 989970.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.6198023557662964, "min": -0.19680991768836975, "max": 0.689395010471344, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 174.16445922851562, "min": -46.643951416015625, "max": 199.924560546875, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.01293552853167057, "min": -0.07038510590791702, "max": 0.4936814308166504, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 3.634883403778076, "min": -19.426288604736328, "max": 117.00250244140625, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06816188402438708, "min": 0.06499504836600474, "max": 0.07296393412425893, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9542663763414191, "min": 0.4915747260440665, "max": 1.0604991801471138, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.016702294844883905, "min": 0.0012352381520168074, "max": 0.016782219322417545, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.23383212782837468, "min": 0.017293334128235305, "max": 0.23495107051384562, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.658218875864287e-06, "min": 7.658218875864287e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.0001072150642621, "min": 0.0001072150642621, "max": 0.0036351016882994994, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10255270714285714, "min": 0.10255270714285714, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4357379, "min": 1.3886848, "max": 2.6117004999999995, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002650154435714286, "min": 0.0002650154435714286, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0037102162100000006, "min": 0.0037102162100000006, "max": 0.12118887995, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.013964233919978142, "min": 0.013964233919978142, "max": 0.5074424743652344, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.1954992711544037, "min": 0.1954992711544037, "max": 3.5520973205566406, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 317.0515463917526, "min": 275.30357142857144, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30754.0, "min": 15984.0, "max": 32494.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.6612999791589875, "min": -1.0000000521540642, "max": 1.6994595954624505, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 159.4847979992628, "min": -28.525001667439938, "max": 187.79839820414782, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.6612999791589875, "min": -1.0000000521540642, "max": 1.6994595954624505, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 159.4847979992628, "min": -28.525001667439938, "max": 187.79839820414782, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.046305508821205876, "min": 0.04105433041367759, "max": 9.282417479902506, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 4.445328846835764, "min": 4.346629672683775, "max": 148.5186796784401, "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": "1700723602", "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": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.1.0+cu118", "numpy_version": "1.23.5", "end_time_seconds": "1700726020" }, "total": 2418.034489912, "count": 1, "self": 0.4826668350001455, "children": { "run_training.setup": { "total": 0.04799439999999322, "count": 1, "self": 0.04799439999999322 }, "TrainerController.start_learning": { "total": 2417.503828677, "count": 1, "self": 1.4148575709959914, "children": { "TrainerController._reset_env": { "total": 10.156785888000059, "count": 1, "self": 10.156785888000059 }, "TrainerController.advance": { "total": 2405.8178336630044, "count": 64189, "self": 1.5899948401147412, "children": { "env_step": { "total": 1750.320984073932, "count": 64189, "self": 1613.8250577899767, "children": { "SubprocessEnvManager._take_step": { "total": 135.63195338194566, "count": 64189, "self": 4.618722296935971, "children": { "TorchPolicy.evaluate": { "total": 131.0132310850097, "count": 62563, "self": 131.0132310850097 } } }, "workers": { "total": 0.8639729020097775, "count": 64189, "self": 0.0, "children": { "worker_root": { "total": 2412.3903574969795, "count": 64189, "is_parallel": true, "self": 923.9061085479925, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005890033000014228, "count": 1, "is_parallel": true, "self": 0.00393391700004031, "children": { "_process_rank_one_or_two_observation": { "total": 0.0019561159999739175, "count": 8, "is_parallel": true, "self": 0.0019561159999739175 } } }, "UnityEnvironment.step": { "total": 0.05053104400008124, "count": 1, "is_parallel": true, "self": 0.0005828700001302423, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005125049999605835, "count": 1, "is_parallel": true, "self": 0.0005125049999605835 }, "communicator.exchange": { "total": 0.04779796599996189, "count": 1, "is_parallel": true, "self": 0.04779796599996189 }, "steps_from_proto": { "total": 0.001637703000028523, "count": 1, "is_parallel": true, "self": 0.00032380499999362655, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013138980000348965, "count": 8, "is_parallel": true, "self": 0.0013138980000348965 } } } } } } }, "UnityEnvironment.step": { "total": 1488.484248948987, "count": 64188, "is_parallel": true, "self": 35.278313447950495, "children": { "UnityEnvironment._generate_step_input": { "total": 25.626429683976653, "count": 64188, "is_parallel": true, "self": 25.626429683976653 }, "communicator.exchange": { "total": 1324.8182193980097, "count": 64188, "is_parallel": true, "self": 1324.8182193980097 }, "steps_from_proto": { "total": 102.76128641904995, "count": 64188, "is_parallel": true, "self": 20.788418670912847, "children": { "_process_rank_one_or_two_observation": { "total": 81.9728677481371, "count": 513504, "is_parallel": true, "self": 81.9728677481371 } } } } } } } } } } }, "trainer_advance": { "total": 653.9068547489577, "count": 64189, "self": 2.6378238599301085, "children": { "process_trajectory": { "total": 135.69664717102728, "count": 64189, "self": 135.39188028302738, "children": { "RLTrainer._checkpoint": { "total": 0.3047668879999037, "count": 2, "self": 0.3047668879999037 } } }, "_update_policy": { "total": 515.5723837180003, "count": 456, "self": 307.60239457299747, "children": { "TorchPPOOptimizer.update": { "total": 207.96998914500284, "count": 22797, "self": 207.96998914500284 } } } } } } }, "trainer_threads": { "total": 1.508999957877677e-06, "count": 1, "self": 1.508999957877677e-06 }, "TrainerController._save_models": { "total": 0.11435004599979948, "count": 1, "self": 0.0018757279999590537, "children": { "RLTrainer._checkpoint": { "total": 0.11247431799984042, "count": 1, "self": 0.11247431799984042 } } } } } } }