| { | |
| "name": "root", | |
| "gauges": { | |
| "Pyramids.Policy.Entropy.mean": { | |
| "value": 0.5639423727989197, | |
| "min": 0.5639423727989197, | |
| "max": 1.45734703540802, | |
| "count": 33 | |
| }, | |
| "Pyramids.Policy.Entropy.sum": { | |
| "value": 16746.83203125, | |
| "min": 16746.83203125, | |
| "max": 44210.078125, | |
| "count": 33 | |
| }, | |
| "Pyramids.Step.mean": { | |
| "value": 989910.0, | |
| "min": 29952.0, | |
| "max": 989910.0, | |
| "count": 33 | |
| }, | |
| "Pyramids.Step.sum": { | |
| "value": 989910.0, | |
| "min": 29952.0, | |
| "max": 989910.0, | |
| "count": 33 | |
| }, | |
| "Pyramids.Policy.ExtrinsicValueEstimate.mean": { | |
| "value": 0.31699663400650024, | |
| "min": -0.09870252758264542, | |
| "max": 0.31699663400650024, | |
| "count": 33 | |
| }, | |
| "Pyramids.Policy.ExtrinsicValueEstimate.sum": { | |
| "value": 81.46813201904297, | |
| "min": -23.68860626220703, | |
| "max": 83.57212829589844, | |
| "count": 33 | |
| }, | |
| "Pyramids.Policy.RndValueEstimate.mean": { | |
| "value": 0.024626612663269043, | |
| "min": 0.006441299803555012, | |
| "max": 0.3491041958332062, | |
| "count": 33 | |
| }, | |
| "Pyramids.Policy.RndValueEstimate.sum": { | |
| "value": 6.329039573669434, | |
| "min": 1.6618553400039673, | |
| "max": 82.7376937866211, | |
| "count": 33 | |
| }, | |
| "Pyramids.Losses.PolicyLoss.mean": { | |
| "value": 0.06752784810001579, | |
| "min": 0.06363302046848283, | |
| "max": 0.07478717686654902, | |
| "count": 33 | |
| }, | |
| "Pyramids.Losses.PolicyLoss.sum": { | |
| "value": 1.0129177215002367, | |
| "min": 0.5015946025013436, | |
| "max": 1.081839949306895, | |
| "count": 33 | |
| }, | |
| "Pyramids.Losses.ValueLoss.mean": { | |
| "value": 0.012679850450299186, | |
| "min": 0.00015198339330376248, | |
| "max": 0.013792555278043782, | |
| "count": 33 | |
| }, | |
| "Pyramids.Losses.ValueLoss.sum": { | |
| "value": 0.1901977567544878, | |
| "min": 0.0022797508995564372, | |
| "max": 0.19309577389261295, | |
| "count": 33 | |
| }, | |
| "Pyramids.Policy.LearningRate.mean": { | |
| "value": 7.494097502000001e-06, | |
| "min": 7.494097502000001e-06, | |
| "max": 0.00029515063018788575, | |
| "count": 33 | |
| }, | |
| "Pyramids.Policy.LearningRate.sum": { | |
| "value": 0.00011241146253000002, | |
| "min": 0.00011241146253000002, | |
| "max": 0.0035074967308344994, | |
| "count": 33 | |
| }, | |
| "Pyramids.Policy.Epsilon.mean": { | |
| "value": 0.102498, | |
| "min": 0.102498, | |
| "max": 0.19838354285714285, | |
| "count": 33 | |
| }, | |
| "Pyramids.Policy.Epsilon.sum": { | |
| "value": 1.5374700000000001, | |
| "min": 1.3886848, | |
| "max": 2.5725091, | |
| "count": 33 | |
| }, | |
| "Pyramids.Policy.Beta.mean": { | |
| "value": 0.0002595502, | |
| "min": 0.0002595502, | |
| "max": 0.00983851593142857, | |
| "count": 33 | |
| }, | |
| "Pyramids.Policy.Beta.sum": { | |
| "value": 0.003893253, | |
| "min": 0.003893253, | |
| "max": 0.11693963345, | |
| "count": 33 | |
| }, | |
| "Pyramids.Losses.RNDLoss.mean": { | |
| "value": 0.011282947845757008, | |
| "min": 0.011282947845757008, | |
| "max": 0.6098914742469788, | |
| "count": 33 | |
| }, | |
| "Pyramids.Losses.RNDLoss.sum": { | |
| "value": 0.1692442148923874, | |
| "min": 0.16650858521461487, | |
| "max": 4.269240379333496, | |
| "count": 33 | |
| }, | |
| "Pyramids.Environment.EpisodeLength.mean": { | |
| "value": 517.6603773584906, | |
| "min": 493.8, | |
| "max": 999.0, | |
| "count": 33 | |
| }, | |
| "Pyramids.Environment.EpisodeLength.sum": { | |
| "value": 27436.0, | |
| "min": 15984.0, | |
| "max": 32857.0, | |
| "count": 33 | |
| }, | |
| "Pyramids.Environment.CumulativeReward.mean": { | |
| "value": 1.1048867573153298, | |
| "min": -1.0000000521540642, | |
| "max": 1.2352856806080257, | |
| "count": 33 | |
| }, | |
| "Pyramids.Environment.CumulativeReward.sum": { | |
| "value": 58.55899813771248, | |
| "min": -29.985601499676704, | |
| "max": 77.89719799906015, | |
| "count": 33 | |
| }, | |
| "Pyramids.Policy.ExtrinsicReward.mean": { | |
| "value": 1.1048867573153298, | |
| "min": -1.0000000521540642, | |
| "max": 1.2352856806080257, | |
| "count": 33 | |
| }, | |
| "Pyramids.Policy.ExtrinsicReward.sum": { | |
| "value": 58.55899813771248, | |
| "min": -29.985601499676704, | |
| "max": 77.89719799906015, | |
| "count": 33 | |
| }, | |
| "Pyramids.Policy.RndReward.mean": { | |
| "value": 0.060398781492005824, | |
| "min": 0.060398781492005824, | |
| "max": 12.657764924690127, | |
| "count": 33 | |
| }, | |
| "Pyramids.Policy.RndReward.sum": { | |
| "value": 3.2011354190763086, | |
| "min": 3.127021064865403, | |
| "max": 202.52423879504204, | |
| "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": "1679288678", | |
| "python_version": "3.9.16 (main, Dec 7 2022, 01:11:51) \n[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=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": "1679290815" | |
| }, | |
| "total": 2137.0022376610004, | |
| "count": 1, | |
| "self": 0.7998460130006606, | |
| "children": { | |
| "run_training.setup": { | |
| "total": 0.15707216500004506, | |
| "count": 1, | |
| "self": 0.15707216500004506 | |
| }, | |
| "TrainerController.start_learning": { | |
| "total": 2136.0453194829997, | |
| "count": 1, | |
| "self": 1.2405654340477668, | |
| "children": { | |
| "TrainerController._reset_env": { | |
| "total": 6.586854276000395, | |
| "count": 1, | |
| "self": 6.586854276000395 | |
| }, | |
| "TrainerController.advance": { | |
| "total": 2128.076003685951, | |
| "count": 63474, | |
| "self": 1.3941674599632279, | |
| "children": { | |
| "env_step": { | |
| "total": 1515.2679582120131, | |
| "count": 63474, | |
| "self": 1408.6831696339855, | |
| "children": { | |
| "SubprocessEnvManager._take_step": { | |
| "total": 105.79384527908405, | |
| "count": 63474, | |
| "self": 4.652547167064768, | |
| "children": { | |
| "TorchPolicy.evaluate": { | |
| "total": 101.14129811201929, | |
| "count": 62560, | |
| "self": 101.14129811201929 | |
| } | |
| } | |
| }, | |
| "workers": { | |
| "total": 0.7909432989436027, | |
| "count": 63474, | |
| "self": 0.0, | |
| "children": { | |
| "worker_root": { | |
| "total": 2131.086762746878, | |
| "count": 63474, | |
| "is_parallel": true, | |
| "self": 836.9810587259058, | |
| "children": { | |
| "run_training.setup": { | |
| "total": 0.0, | |
| "count": 0, | |
| "is_parallel": true, | |
| "self": 0.0, | |
| "children": { | |
| "steps_from_proto": { | |
| "total": 0.002652702999967005, | |
| "count": 1, | |
| "is_parallel": true, | |
| "self": 0.0008033360004446877, | |
| "children": { | |
| "_process_rank_one_or_two_observation": { | |
| "total": 0.0018493669995223172, | |
| "count": 8, | |
| "is_parallel": true, | |
| "self": 0.0018493669995223172 | |
| } | |
| } | |
| }, | |
| "UnityEnvironment.step": { | |
| "total": 0.05023601700031577, | |
| "count": 1, | |
| "is_parallel": true, | |
| "self": 0.0005923800008531543, | |
| "children": { | |
| "UnityEnvironment._generate_step_input": { | |
| "total": 0.0005526019999706477, | |
| "count": 1, | |
| "is_parallel": true, | |
| "self": 0.0005526019999706477 | |
| }, | |
| "communicator.exchange": { | |
| "total": 0.046979691999695206, | |
| "count": 1, | |
| "is_parallel": true, | |
| "self": 0.046979691999695206 | |
| }, | |
| "steps_from_proto": { | |
| "total": 0.0021113429997967614, | |
| "count": 1, | |
| "is_parallel": true, | |
| "self": 0.0004425179999998363, | |
| "children": { | |
| "_process_rank_one_or_two_observation": { | |
| "total": 0.0016688249997969251, | |
| "count": 8, | |
| "is_parallel": true, | |
| "self": 0.0016688249997969251 | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| }, | |
| "UnityEnvironment.step": { | |
| "total": 1294.105704020972, | |
| "count": 63473, | |
| "is_parallel": true, | |
| "self": 30.742952320891163, | |
| "children": { | |
| "UnityEnvironment._generate_step_input": { | |
| "total": 23.332154306019675, | |
| "count": 63473, | |
| "is_parallel": true, | |
| "self": 23.332154306019675 | |
| }, | |
| "communicator.exchange": { | |
| "total": 1147.882381528032, | |
| "count": 63473, | |
| "is_parallel": true, | |
| "self": 1147.882381528032 | |
| }, | |
| "steps_from_proto": { | |
| "total": 92.1482158660292, | |
| "count": 63473, | |
| "is_parallel": true, | |
| "self": 19.763065727040157, | |
| "children": { | |
| "_process_rank_one_or_two_observation": { | |
| "total": 72.38515013898905, | |
| "count": 507784, | |
| "is_parallel": true, | |
| "self": 72.38515013898905 | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| }, | |
| "trainer_advance": { | |
| "total": 611.4138780139747, | |
| "count": 63474, | |
| "self": 2.381304512913175, | |
| "children": { | |
| "process_trajectory": { | |
| "total": 115.45620594405864, | |
| "count": 63474, | |
| "self": 115.19946812805892, | |
| "children": { | |
| "RLTrainer._checkpoint": { | |
| "total": 0.25673781599971335, | |
| "count": 2, | |
| "self": 0.25673781599971335 | |
| } | |
| } | |
| }, | |
| "_update_policy": { | |
| "total": 493.57636755700287, | |
| "count": 455, | |
| "self": 313.08640125101556, | |
| "children": { | |
| "TorchPPOOptimizer.update": { | |
| "total": 180.4899663059873, | |
| "count": 22800, | |
| "self": 180.4899663059873 | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| }, | |
| "trainer_threads": { | |
| "total": 1.5730001905467361e-06, | |
| "count": 1, | |
| "self": 1.5730001905467361e-06 | |
| }, | |
| "TrainerController._save_models": { | |
| "total": 0.1418945140003416, | |
| "count": 1, | |
| "self": 0.0019466880003164988, | |
| "children": { | |
| "RLTrainer._checkpoint": { | |
| "total": 0.1399478260000251, | |
| "count": 1, | |
| "self": 0.1399478260000251 | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } |