{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.37652289867401123, "min": 0.37652289867401123, "max": 1.436599850654602, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 11380.0283203125, "min": 11354.3740234375, "max": 43580.69140625, "count": 33 }, "Pyramids.Step.mean": { "value": 989951.0, "min": 29952.0, "max": 989951.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989951.0, "min": 29952.0, "max": 989951.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.5506382584571838, "min": -0.09329011291265488, "max": 0.5506382584571838, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 152.52679443359375, "min": -22.48291778564453, "max": 152.52679443359375, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -0.0018263672245666385, "min": -0.044549278914928436, "max": 0.277172327041626, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -0.5059037208557129, "min": -12.295600891113281, "max": 66.79853057861328, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.0654769404611129, "min": 0.06426968996293865, "max": 0.07489251552581026, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9166771664555806, "min": 0.5183019131802066, "max": 1.061087959931077, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.016150275889750838, "min": 0.0007694677559457324, "max": 0.016178661424628163, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.22610386245651173, "min": 0.01000308082729452, "max": 0.22650125994479428, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.509376068335711e-06, "min": 7.509376068335711e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010513126495669995, "min": 0.00010513126495669995, "max": 0.0033772933742355995, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10250309285714287, "min": 0.10250309285714287, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4350433000000002, "min": 1.3886848, "max": 2.4428680000000003, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002600589764285714, "min": 0.0002600589764285714, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0036408256699999994, "min": 0.0036408256699999994, "max": 0.11259386356000001, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.01042871829122305, "min": 0.01042128261178732, "max": 0.3692907989025116, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.14600205421447754, "min": 0.14600205421447754, "max": 2.585035562515259, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 313.752688172043, "min": 313.752688172043, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29179.0, "min": 15984.0, "max": 32694.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.6432236388966601, "min": -1.0000000521540642, "max": 1.6432236388966601, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 152.8197984173894, "min": -30.726001664996147, "max": 152.8197984173894, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.6432236388966601, "min": -1.0000000521540642, "max": 1.6432236388966601, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 152.8197984173894, "min": -30.726001664996147, "max": 152.8197984173894, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.03392372502518507, "min": 0.03392372502518507, "max": 6.7182495119050145, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.154906427342212, "min": 3.1096321904915385, "max": 107.49199219048023, "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": "1716079497", "python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [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 Training1 --no-graphics", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.2.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1716081214" }, "total": 1717.4346699110001, "count": 1, "self": 0.37259913099978803, "children": { "run_training.setup": { "total": 0.052248417000100744, "count": 1, "self": 0.052248417000100744 }, "TrainerController.start_learning": { "total": 1717.0098223630002, "count": 1, "self": 1.4664126249724632, "children": { "TrainerController._reset_env": { "total": 2.7651567050002086, "count": 1, "self": 2.7651567050002086 }, "TrainerController.advance": { "total": 1712.6945013240281, "count": 63729, "self": 1.4620264120892443, "children": { "env_step": { "total": 1127.7683877849836, "count": 63729, "self": 995.7486885929659, "children": { "SubprocessEnvManager._take_step": { "total": 131.12954971905287, "count": 63729, "self": 4.668639563066108, "children": { "TorchPolicy.evaluate": { "total": 126.46091015598677, "count": 62571, "self": 126.46091015598677 } } }, "workers": { "total": 0.890149472964822, "count": 63729, "self": 0.0, "children": { "worker_root": { "total": 1714.628749190055, "count": 63729, "is_parallel": true, "self": 825.1364934440483, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0020743759998822497, "count": 1, "is_parallel": true, "self": 0.0006309439993401611, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014434320005420886, "count": 8, "is_parallel": true, "self": 0.0014434320005420886 } } }, "UnityEnvironment.step": { "total": 0.04751515999987532, "count": 1, "is_parallel": true, "self": 0.0004903399999420799, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00030232299991439504, "count": 1, "is_parallel": true, "self": 0.00030232299991439504 }, "communicator.exchange": { "total": 0.04552664600009848, "count": 1, "is_parallel": true, "self": 0.04552664600009848 }, "steps_from_proto": { "total": 0.001195850999920367, "count": 1, "is_parallel": true, "self": 0.0002620349996504956, "children": { "_process_rank_one_or_two_observation": { "total": 0.0009338160002698714, "count": 8, "is_parallel": true, "self": 0.0009338160002698714 } } } } } } }, "UnityEnvironment.step": { "total": 889.4922557460068, "count": 63728, "is_parallel": true, "self": 23.073786019014733, "children": { "UnityEnvironment._generate_step_input": { "total": 14.26574539699186, "count": 63728, "is_parallel": true, "self": 14.26574539699186 }, "communicator.exchange": { "total": 787.0313077150101, "count": 63728, "is_parallel": true, "self": 787.0313077150101 }, "steps_from_proto": { "total": 65.12141661499004, "count": 63728, "is_parallel": true, "self": 14.321510185033503, "children": { "_process_rank_one_or_two_observation": { "total": 50.799906429956536, "count": 509824, "is_parallel": true, "self": 50.799906429956536 } } } } } } } } } } }, "trainer_advance": { "total": 583.4640871269553, "count": 63729, "self": 2.8439207299918507, "children": { "process_trajectory": { "total": 115.1977968579663, "count": 63729, "self": 114.94663029096591, "children": { "RLTrainer._checkpoint": { "total": 0.2511665670003822, "count": 2, "self": 0.2511665670003822 } } }, "_update_policy": { "total": 465.42236953899715, "count": 444, "self": 269.7341147379882, "children": { "TorchPPOOptimizer.update": { "total": 195.68825480100895, "count": 22839, "self": 195.68825480100895 } } } } } } }, "trainer_threads": { "total": 1.1169999652338447e-05, "count": 1, "self": 1.1169999652338447e-05 }, "TrainerController._save_models": { "total": 0.08374053899979117, "count": 1, "self": 0.0013389329997153254, "children": { "RLTrainer._checkpoint": { "total": 0.08240160600007584, "count": 1, "self": 0.08240160600007584 } } } } } } }