| { |
| "name": "root", |
| "gauges": { |
| "Pyramids.Policy.Entropy.mean": { |
| "value": 0.1537657231092453, |
| "min": 0.14524783194065094, |
| "max": 1.4448449611663818, |
| "count": 100 |
| }, |
| "Pyramids.Policy.Entropy.sum": { |
| "value": 4600.67041015625, |
| "min": 4322.57568359375, |
| "max": 43830.81640625, |
| "count": 100 |
| }, |
| "Pyramids.Step.mean": { |
| "value": 2999985.0, |
| "min": 29952.0, |
| "max": 2999985.0, |
| "count": 100 |
| }, |
| "Pyramids.Step.sum": { |
| "value": 2999985.0, |
| "min": 29952.0, |
| "max": 2999985.0, |
| "count": 100 |
| }, |
| "Pyramids.Policy.ExtrinsicValueEstimate.mean": { |
| "value": 0.8360688090324402, |
| "min": -0.11075292527675629, |
| "max": 0.8537501692771912, |
| "count": 100 |
| }, |
| "Pyramids.Policy.ExtrinsicValueEstimate.sum": { |
| "value": 249.14849853515625, |
| "min": -26.58070182800293, |
| "max": 265.51629638671875, |
| "count": 100 |
| }, |
| "Pyramids.Policy.RndValueEstimate.mean": { |
| "value": 0.014502187259495258, |
| "min": -0.02345305122435093, |
| "max": 0.45518144965171814, |
| "count": 100 |
| }, |
| "Pyramids.Policy.RndValueEstimate.sum": { |
| "value": 4.321651935577393, |
| "min": -6.824838161468506, |
| "max": 109.24354553222656, |
| "count": 100 |
| }, |
| "Pyramids.Losses.PolicyLoss.mean": { |
| "value": 0.06710910912148567, |
| "min": 0.06470017557426001, |
| "max": 0.07449668927152782, |
| "count": 100 |
| }, |
| "Pyramids.Losses.PolicyLoss.sum": { |
| "value": 0.9395275277007993, |
| "min": 0.48271707378561346, |
| "max": 1.1131395857373718, |
| "count": 100 |
| }, |
| "Pyramids.Losses.ValueLoss.mean": { |
| "value": 0.014682536504724774, |
| "min": 0.00011524376498658496, |
| "max": 0.018288665539113846, |
| "count": 100 |
| }, |
| "Pyramids.Losses.ValueLoss.sum": { |
| "value": 0.20555551106614683, |
| "min": 0.0014981689448256045, |
| "max": 0.25604131754759385, |
| "count": 100 |
| }, |
| "Pyramids.Policy.LearningRate.mean": { |
| "value": 1.483449505549998e-06, |
| "min": 1.483449505549998e-06, |
| "max": 0.00029838354339596195, |
| "count": 100 |
| }, |
| "Pyramids.Policy.LearningRate.sum": { |
| "value": 2.0768293077699972e-05, |
| "min": 2.0768293077699972e-05, |
| "max": 0.0038433220188926996, |
| "count": 100 |
| }, |
| "Pyramids.Policy.Epsilon.mean": { |
| "value": 0.10049445000000001, |
| "min": 0.10049445000000001, |
| "max": 0.19946118095238097, |
| "count": 100 |
| }, |
| "Pyramids.Policy.Epsilon.sum": { |
| "value": 1.4069223000000002, |
| "min": 1.3897045333333333, |
| "max": 2.7524873000000003, |
| "count": 100 |
| }, |
| "Pyramids.Policy.Beta.mean": { |
| "value": 5.939555499999994e-05, |
| "min": 5.939555499999994e-05, |
| "max": 0.009946171977142856, |
| "count": 100 |
| }, |
| "Pyramids.Policy.Beta.sum": { |
| "value": 0.0008315377699999991, |
| "min": 0.0008315377699999991, |
| "max": 0.12812261927, |
| "count": 100 |
| }, |
| "Pyramids.Losses.RNDLoss.mean": { |
| "value": 0.011604508385062218, |
| "min": 0.011522161774337292, |
| "max": 0.7920774817466736, |
| "count": 100 |
| }, |
| "Pyramids.Losses.RNDLoss.sum": { |
| "value": 0.16246311366558075, |
| "min": 0.16131027042865753, |
| "max": 5.54454231262207, |
| "count": 100 |
| }, |
| "Pyramids.Environment.EpisodeLength.mean": { |
| "value": 232.86153846153846, |
| "min": 198.16551724137932, |
| "max": 999.0, |
| "count": 100 |
| }, |
| "Pyramids.Environment.EpisodeLength.sum": { |
| "value": 30272.0, |
| "min": 15984.0, |
| "max": 32615.0, |
| "count": 100 |
| }, |
| "Pyramids.Environment.CumulativeReward.mean": { |
| "value": 1.7363553720598037, |
| "min": -1.0000000521540642, |
| "max": 1.801801357163142, |
| "count": 100 |
| }, |
| "Pyramids.Environment.CumulativeReward.sum": { |
| "value": 225.7261983677745, |
| "min": -32.000001668930054, |
| "max": 263.0629981458187, |
| "count": 100 |
| }, |
| "Pyramids.Policy.ExtrinsicReward.mean": { |
| "value": 1.7363553720598037, |
| "min": -1.0000000521540642, |
| "max": 1.801801357163142, |
| "count": 100 |
| }, |
| "Pyramids.Policy.ExtrinsicReward.sum": { |
| "value": 225.7261983677745, |
| "min": -32.000001668930054, |
| "max": 263.0629981458187, |
| "count": 100 |
| }, |
| "Pyramids.Policy.RndReward.mean": { |
| "value": 0.0279809628008829, |
| "min": 0.024561315306615043, |
| "max": 15.869521593675017, |
| "count": 100 |
| }, |
| "Pyramids.Policy.RndReward.sum": { |
| "value": 3.637525164114777, |
| "min": 3.5859520347657963, |
| "max": 253.91234549880028, |
| "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": "1793141013", |
| "python_version": "3.10.12 | packaged by conda-forge | (main, Jun 23 2023, 22:40:32) [GCC 12.3.0]", |
| "command_line_arguments": "/content/miniforge3/envs/unity-mlagents/bin/mlagents-learn ./config/ppo/PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=PyramidsTraining --no-graphics", |
| "mlagents_version": "1.2.0.dev0", |
| "mlagents_envs_version": "1.2.0.dev0", |
| "communication_protocol_version": "1.5.0", |
| "pytorch_version": "2.8.0+cu128", |
| "numpy_version": "1.23.5", |
| "end_time_seconds": "1793147725" |
| }, |
| "total": 6712.091307188999, |
| "count": 1, |
| "self": 0.47765121499924135, |
| "children": { |
| "run_training.setup": { |
| "total": 0.019709428000169282, |
| "count": 1, |
| "self": 0.019709428000169282 |
| }, |
| "TrainerController.start_learning": { |
| "total": 6711.593946546, |
| "count": 1, |
| "self": 3.9534448631702617, |
| "children": { |
| "TrainerController._reset_env": { |
| "total": 2.227990213999874, |
| "count": 1, |
| "self": 2.227990213999874 |
| }, |
| "TrainerController.advance": { |
| "total": 6705.33663984183, |
| "count": 194627, |
| "self": 4.19119513982514, |
| "children": { |
| "env_step": { |
| "total": 4868.012393009918, |
| "count": 194627, |
| "self": 4419.795942406809, |
| "children": { |
| "SubprocessEnvManager._take_step": { |
| "total": 445.7979657330443, |
| "count": 194627, |
| "self": 13.881561180000062, |
| "children": { |
| "TorchPolicy.evaluate": { |
| "total": 431.91640455304423, |
| "count": 187562, |
| "self": 431.91640455304423 |
| } |
| } |
| }, |
| "workers": { |
| "total": 2.418484870064276, |
| "count": 194627, |
| "self": 0.0, |
| "children": { |
| "worker_root": { |
| "total": 6701.959465543935, |
| "count": 194627, |
| "is_parallel": true, |
| "self": 2605.245865575198, |
| "children": { |
| "run_training.setup": { |
| "total": 0.0, |
| "count": 0, |
| "is_parallel": true, |
| "self": 0.0, |
| "children": { |
| "steps_from_proto": { |
| "total": 0.0017575480005689315, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.0005800060007459251, |
| "children": { |
| "_process_rank_one_or_two_observation": { |
| "total": 0.0011775419998230063, |
| "count": 8, |
| "is_parallel": true, |
| "self": 0.0011775419998230063 |
| } |
| } |
| }, |
| "UnityEnvironment.step": { |
| "total": 0.05920261999926879, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.0006186049995449139, |
| "children": { |
| "UnityEnvironment._generate_step_input": { |
| "total": 0.00046814399956929265, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.00046814399956929265 |
| }, |
| "communicator.exchange": { |
| "total": 0.05600203099947976, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.05600203099947976 |
| }, |
| "steps_from_proto": { |
| "total": 0.002113840000674827, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.00045718300134467427, |
| "children": { |
| "_process_rank_one_or_two_observation": { |
| "total": 0.0016566569993301528, |
| "count": 8, |
| "is_parallel": true, |
| "self": 0.0016566569993301528 |
| } |
| } |
| } |
| } |
| } |
| } |
| }, |
| "UnityEnvironment.step": { |
| "total": 4096.713599968737, |
| "count": 194626, |
| "is_parallel": true, |
| "self": 99.15302521938702, |
| "children": { |
| "UnityEnvironment._generate_step_input": { |
| "total": 69.18251319850424, |
| "count": 194626, |
| "is_parallel": true, |
| "self": 69.18251319850424 |
| }, |
| "communicator.exchange": { |
| "total": 3620.2359180068925, |
| "count": 194626, |
| "is_parallel": true, |
| "self": 3620.2359180068925 |
| }, |
| "steps_from_proto": { |
| "total": 308.14214354395335, |
| "count": 194626, |
| "is_parallel": true, |
| "self": 62.76559379481205, |
| "children": { |
| "_process_rank_one_or_two_observation": { |
| "total": 245.3765497491413, |
| "count": 1557008, |
| "is_parallel": true, |
| "self": 245.3765497491413 |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
| }, |
| "trainer_advance": { |
| "total": 1833.133051692087, |
| "count": 194627, |
| "self": 7.9694327016941315, |
| "children": { |
| "process_trajectory": { |
| "total": 336.6912313614366, |
| "count": 194627, |
| "self": 336.1759609964356, |
| "children": { |
| "RLTrainer._checkpoint": { |
| "total": 0.5152703650010153, |
| "count": 6, |
| "self": 0.5152703650010153 |
| } |
| } |
| }, |
| "_update_policy": { |
| "total": 1488.4723876289563, |
| "count": 1389, |
| "self": 784.083315033793, |
| "children": { |
| "TorchPPOOptimizer.update": { |
| "total": 704.3890725951633, |
| "count": 68352, |
| "self": 704.3890725951633 |
| } |
| } |
| } |
| } |
| } |
| } |
| }, |
| "trainer_threads": { |
| "total": 1.1039992386940867e-06, |
| "count": 1, |
| "self": 1.1039992386940867e-06 |
| }, |
| "TrainerController._save_models": { |
| "total": 0.0758705230000487, |
| "count": 1, |
| "self": 0.0010442189995956142, |
| "children": { |
| "RLTrainer._checkpoint": { |
| "total": 0.07482630400045309, |
| "count": 1, |
| "self": 0.07482630400045309 |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
