| { |
| "name": "root", |
| "gauges": { |
| "Pyramids.Policy.Entropy.mean": { |
| "value": 0.47395145893096924, |
| "min": 0.43914881348609924, |
| "max": 1.5772427320480347, |
| "count": 30 |
| }, |
| "Pyramids.Policy.Entropy.sum": { |
| "value": 23788.572265625, |
| "min": 22133.099609375, |
| "max": 82168.0390625, |
| "count": 30 |
| }, |
| "Pyramids.Step.mean": { |
| "value": 1499894.0, |
| "min": 49792.0, |
| "max": 1499894.0, |
| "count": 30 |
| }, |
| "Pyramids.Step.sum": { |
| "value": 1499894.0, |
| "min": 49792.0, |
| "max": 1499894.0, |
| "count": 30 |
| }, |
| "Pyramids.Policy.ExtrinsicValueEstimate.mean": { |
| "value": 0.7238889336585999, |
| "min": -0.08758947253227234, |
| "max": 0.7238889336585999, |
| "count": 30 |
| }, |
| "Pyramids.Policy.ExtrinsicValueEstimate.sum": { |
| "value": 201.24111938476562, |
| "min": -17.605484008789062, |
| "max": 209.07135009765625, |
| "count": 30 |
| }, |
| "Pyramids.Policy.RndValueEstimate.mean": { |
| "value": 0.039022047072649, |
| "min": 0.039022047072649, |
| "max": 1.0661793947219849, |
| "count": 30 |
| }, |
| "Pyramids.Policy.RndValueEstimate.sum": { |
| "value": 10.848129272460938, |
| "min": 10.848129272460938, |
| "max": 213.2358856201172, |
| "count": 30 |
| }, |
| "Pyramids.Losses.PolicyLoss.mean": { |
| "value": 0.05059290239053856, |
| "min": 0.04804883606993826, |
| "max": 0.05429279381665317, |
| "count": 30 |
| }, |
| "Pyramids.Losses.PolicyLoss.sum": { |
| "value": 0.30355741434323136, |
| "min": 0.20743013373082606, |
| "max": 0.32058311826040153, |
| "count": 30 |
| }, |
| "Pyramids.Losses.ValueLoss.mean": { |
| "value": 0.013280400857790179, |
| "min": 0.00047992524293536206, |
| "max": 0.04562955859006067, |
| "count": 30 |
| }, |
| "Pyramids.Losses.ValueLoss.sum": { |
| "value": 0.07968240514674108, |
| "min": 0.0019197009717414483, |
| "max": 0.18251823436024267, |
| "count": 30 |
| }, |
| "Pyramids.Policy.LearningRate.mean": { |
| "value": 0.00010172208247231668, |
| "min": 0.00010172208247231668, |
| "max": 0.0001979904010048, |
| "count": 30 |
| }, |
| "Pyramids.Policy.LearningRate.sum": { |
| "value": 0.0006103324948339001, |
| "min": 0.0006103324948339001, |
| "max": 0.0011089415121959332, |
| "count": 30 |
| }, |
| "Pyramids.Policy.Epsilon.mean": { |
| "value": 0.12543050833333336, |
| "min": 0.12543050833333336, |
| "max": 0.14949759999999998, |
| "count": 30 |
| }, |
| "Pyramids.Policy.Epsilon.sum": { |
| "value": 0.7525830500000001, |
| "min": 0.5915904, |
| "max": 0.8772353666666668, |
| "count": 30 |
| }, |
| "Pyramids.Policy.Beta.mean": { |
| "value": 0.0025479647316666667, |
| "min": 0.0025479647316666667, |
| "max": 0.00494986048, |
| "count": 30 |
| }, |
| "Pyramids.Policy.Beta.sum": { |
| "value": 0.015287788390000001, |
| "min": 0.015287788390000001, |
| "max": 0.027728089593333335, |
| "count": 30 |
| }, |
| "Pyramids.Losses.RNDLoss.mean": { |
| "value": 0.022282997146248817, |
| "min": 0.022282997146248817, |
| "max": 0.692805290222168, |
| "count": 30 |
| }, |
| "Pyramids.Losses.RNDLoss.sum": { |
| "value": 0.1336979866027832, |
| "min": 0.1336979866027832, |
| "max": 2.771221160888672, |
| "count": 30 |
| }, |
| "Pyramids.Environment.EpisodeLength.mean": { |
| "value": 278.3, |
| "min": 253.3451776649746, |
| "max": 999.0, |
| "count": 30 |
| }, |
| "Pyramids.Environment.EpisodeLength.sum": { |
| "value": 50094.0, |
| "min": 47121.0, |
| "max": 53748.0, |
| "count": 30 |
| }, |
| "Pyramids.Environment.CumulativeReward.mean": { |
| "value": 1.6661210844914118, |
| "min": -1.0000000596046448, |
| "max": 1.7369999766650825, |
| "count": 30 |
| }, |
| "Pyramids.Environment.CumulativeReward.sum": { |
| "value": 299.90179520845413, |
| "min": -48.00000286102295, |
| "max": 343.92599537968636, |
| "count": 30 |
| }, |
| "Pyramids.Policy.ExtrinsicReward.mean": { |
| "value": 1.6661210844914118, |
| "min": -1.0000000596046448, |
| "max": 1.7369999766650825, |
| "count": 30 |
| }, |
| "Pyramids.Policy.ExtrinsicReward.sum": { |
| "value": 299.90179520845413, |
| "min": -48.00000286102295, |
| "max": 343.92599537968636, |
| "count": 30 |
| }, |
| "Pyramids.Policy.RndReward.mean": { |
| "value": 0.1269037943727906, |
| "min": 0.12021264313270968, |
| "max": 25.533917946120102, |
| "count": 30 |
| }, |
| "Pyramids.Policy.RndReward.sum": { |
| "value": 22.842682987102307, |
| "min": 22.842682987102307, |
| "max": 1225.628061413765, |
| "count": 30 |
| }, |
| "Pyramids.IsTraining.mean": { |
| "value": 1.0, |
| "min": 1.0, |
| "max": 1.0, |
| "count": 30 |
| }, |
| "Pyramids.IsTraining.sum": { |
| "value": 1.0, |
| "min": 1.0, |
| "max": 1.0, |
| "count": 30 |
| } |
| }, |
| "metadata": { |
| "timer_format_version": "0.1.0", |
| "start_time_seconds": "1739010197", |
| "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=Pyramids1 --no-graphics", |
| "mlagents_version": "1.2.0.dev0", |
| "mlagents_envs_version": "1.2.0.dev0", |
| "communication_protocol_version": "1.5.0", |
| "pytorch_version": "2.6.0+cu124", |
| "numpy_version": "1.23.5", |
| "end_time_seconds": "1739014540" |
| }, |
| "total": 4343.211638579, |
| "count": 1, |
| "self": 0.49571552599900315, |
| "children": { |
| "run_training.setup": { |
| "total": 0.02509687600002053, |
| "count": 1, |
| "self": 0.02509687600002053 |
| }, |
| "TrainerController.start_learning": { |
| "total": 4342.690826177, |
| "count": 1, |
| "self": 3.0422231159973308, |
| "children": { |
| "TrainerController._reset_env": { |
| "total": 3.5475151840000194, |
| "count": 1, |
| "self": 3.5475151840000194 |
| }, |
| "TrainerController.advance": { |
| "total": 4336.100126945003, |
| "count": 97085, |
| "self": 3.116563392974058, |
| "children": { |
| "env_step": { |
| "total": 3123.495565339006, |
| "count": 97085, |
| "self": 2759.640346882132, |
| "children": { |
| "SubprocessEnvManager._take_step": { |
| "total": 362.02454823896977, |
| "count": 97085, |
| "self": 8.998269734995972, |
| "children": { |
| "TorchPolicy.evaluate": { |
| "total": 353.0262785039738, |
| "count": 94211, |
| "self": 353.0262785039738 |
| } |
| } |
| }, |
| "workers": { |
| "total": 1.8306702179044123, |
| "count": 97084, |
| "self": 0.0, |
| "children": { |
| "worker_root": { |
| "total": 4332.975875222022, |
| "count": 97084, |
| "is_parallel": true, |
| "self": 1798.5675234819855, |
| "children": { |
| "run_training.setup": { |
| "total": 0.0, |
| "count": 0, |
| "is_parallel": true, |
| "self": 0.0, |
| "children": { |
| "steps_from_proto": { |
| "total": 0.00626531799997565, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.004769854999835843, |
| "children": { |
| "_process_rank_one_or_two_observation": { |
| "total": 0.0014954630001398073, |
| "count": 8, |
| "is_parallel": true, |
| "self": 0.0014954630001398073 |
| } |
| } |
| }, |
| "UnityEnvironment.step": { |
| "total": 0.05627556700000014, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.000609010000005128, |
| "children": { |
| "UnityEnvironment._generate_step_input": { |
| "total": 0.000536020999959419, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.000536020999959419 |
| }, |
| "communicator.exchange": { |
| "total": 0.05290789800000084, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.05290789800000084 |
| }, |
| "steps_from_proto": { |
| "total": 0.002222638000034749, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.0005434350001110033, |
| "children": { |
| "_process_rank_one_or_two_observation": { |
| "total": 0.0016792029999237457, |
| "count": 8, |
| "is_parallel": true, |
| "self": 0.0016792029999237457 |
| } |
| } |
| } |
| } |
| } |
| } |
| }, |
| "UnityEnvironment.step": { |
| "total": 2534.408351740037, |
| "count": 97083, |
| "is_parallel": true, |
| "self": 57.82328162607564, |
| "children": { |
| "UnityEnvironment._generate_step_input": { |
| "total": 40.073639955927035, |
| "count": 97083, |
| "is_parallel": true, |
| "self": 40.073639955927035 |
| }, |
| "communicator.exchange": { |
| "total": 2263.384976569948, |
| "count": 97083, |
| "is_parallel": true, |
| "self": 2263.384976569948 |
| }, |
| "steps_from_proto": { |
| "total": 173.12645358808652, |
| "count": 97083, |
| "is_parallel": true, |
| "self": 37.581869337396995, |
| "children": { |
| "_process_rank_one_or_two_observation": { |
| "total": 135.54458425068952, |
| "count": 776664, |
| "is_parallel": true, |
| "self": 135.54458425068952 |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
| }, |
| "trainer_advance": { |
| "total": 1209.4879982130228, |
| "count": 97084, |
| "self": 6.136099132024356, |
| "children": { |
| "process_trajectory": { |
| "total": 235.83143179800277, |
| "count": 97084, |
| "self": 234.3824229140023, |
| "children": { |
| "RLTrainer._checkpoint": { |
| "total": 1.4490088840004773, |
| "count": 3, |
| "self": 1.4490088840004773 |
| } |
| } |
| }, |
| "_update_policy": { |
| "total": 967.5204672829958, |
| "count": 174, |
| "self": 587.5277926609949, |
| "children": { |
| "TorchPPOOptimizer.update": { |
| "total": 379.99267462200095, |
| "count": 23180, |
| "self": 379.99267462200095 |
| } |
| } |
| } |
| } |
| } |
| } |
| }, |
| "trainer_threads": { |
| "total": 1.6439998944406398e-06, |
| "count": 1, |
| "self": 1.6439998944406398e-06 |
| }, |
| "TrainerController._save_models": { |
| "total": 0.0009592880005584448, |
| "count": 1, |
| "self": 4.0442000681650825e-05, |
| "children": { |
| "RLTrainer._checkpoint": { |
| "total": 0.0009188459998767939, |
| "count": 1, |
| "self": 0.0009188459998767939 |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
