{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.9520696401596069, "min": 0.8406320214271545, "max": 1.4101276397705078, "count": 16 }, "Pyramids.Policy.Entropy.sum": { "value": 28470.69140625, "min": 25232.41015625, "max": 42777.6328125, "count": 16 }, "Pyramids.Step.mean": { "value": 479872.0, "min": 29952.0, "max": 479872.0, "count": 16 }, "Pyramids.Step.sum": { "value": 479872.0, "min": 29952.0, "max": 479872.0, "count": 16 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.09081744402647018, "min": -0.10135176032781601, "max": 0.09081744402647018, "count": 16 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 22.885995864868164, "min": -24.42577362060547, "max": 22.885995864868164, "count": 16 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.006325182039290667, "min": 0.006325182039290667, "max": 0.22273534536361694, "count": 16 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 1.593945860862732, "min": 1.593945860862732, "max": 52.78827667236328, "count": 16 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.07071898053358641, "min": 0.06704136512308209, "max": 0.07411111085165266, "count": 16 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9900657274702098, "min": 0.5187777759615686, "max": 1.0050012744422172, "count": 16 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.007869830364774932, "min": 0.00010159897771022627, "max": 0.00843525377623353, "count": 16 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.11017762510684906, "min": 0.0012191877325227153, "max": 0.11017762510684906, "count": 16 }, "Pyramids.Policy.LearningRate.mean": { "value": 0.00016055603933847856, "min": 0.00016055603933847856, "max": 0.00029515063018788575, "count": 16 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.0022477845507387, "min": 0.0020660544113152, "max": 0.0033712426762525, "count": 16 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.15351866428571428, "min": 0.15351866428571428, "max": 0.19838354285714285, "count": 16 }, "Pyramids.Policy.Epsilon.sum": { "value": 2.1492613, "min": 1.3886848, "max": 2.4427364000000003, "count": 16 }, "Pyramids.Policy.Beta.mean": { "value": 0.005356514562142857, "min": 0.005356514562142857, "max": 0.00983851593142857, "count": 16 }, "Pyramids.Policy.Beta.sum": { "value": 0.07499120387, "min": 0.06886961152, "max": 0.11239237525000001, "count": 16 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.01477581076323986, "min": 0.014663067646324635, "max": 0.35838285088539124, "count": 16 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.20686134696006775, "min": 0.20528294146060944, "max": 2.5086798667907715, "count": 16 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 691.0, "min": 691.0, "max": 999.0, "count": 16 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 31786.0, "min": 15984.0, "max": 32867.0, "count": 16 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 0.4826390973251799, "min": -1.0000000521540642, "max": 0.4826390973251799, "count": 16 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 22.201398476958275, "min": -31.99640165269375, "max": 22.201398476958275, "count": 16 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 0.4826390973251799, "min": -1.0000000521540642, "max": 0.4826390973251799, "count": 16 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 22.201398476958275, "min": -31.99640165269375, "max": 22.201398476958275, "count": 16 }, "Pyramids.Policy.RndReward.mean": { "value": 0.1050107365104929, "min": 0.1050107365104929, "max": 7.738513415679336, "count": 16 }, "Pyramids.Policy.RndReward.sum": { "value": 4.830493879482674, "min": 4.5902753956615925, "max": 123.81621465086937, "count": 16 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 16 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 16 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1790499812", "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]", "command_line_arguments": "/usr/local/envs/mlagents/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", "mlagents_envs_version": "1.1.0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.14.0+cu130", "numpy_version": "1.23.5", "end_time_seconds": "1790501094" }, "total": 1281.9088116170005, "count": 1, "self": 0.4785766180002611, "children": { "run_training.setup": { "total": 0.021874314000342565, "count": 1, "self": 0.021874314000342565 }, "TrainerController.start_learning": { "total": 1281.408360685, "count": 1, "self": 0.723044268999729, "children": { "TrainerController._reset_env": { "total": 2.4492074659992795, "count": 1, "self": 2.4492074659992795 }, "TrainerController.advance": { "total": 1278.1827282230006, "count": 31564, "self": 0.7953119220383087, "children": { "env_step": { "total": 927.0860002179452, "count": 31564, "self": 845.9655184538951, "children": { "SubprocessEnvManager._take_step": { "total": 80.69742139201844, "count": 31564, "self": 2.4935915020150787, "children": { "TorchPolicy.evaluate": { "total": 78.20382989000336, "count": 31315, "self": 78.20382989000336 } } }, "workers": { "total": 0.42306037203161395, "count": 31564, "self": 0.0, "children": { "worker_root": { "total": 1278.9189459399677, "count": 31564, "is_parallel": true, "self": 494.8137277389942, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.00242572899969673, "count": 1, "is_parallel": true, "self": 0.000811757999144902, "children": { "_process_rank_one_or_two_observation": { "total": 0.0016139710005518282, "count": 8, "is_parallel": true, "self": 0.0016139710005518282 } } }, "UnityEnvironment.step": { "total": 0.0502112889998898, "count": 1, "is_parallel": true, "self": 0.0005691500000466476, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00047637799980293494, "count": 1, "is_parallel": true, "self": 0.00047637799980293494 }, "communicator.exchange": { "total": 0.04711005900026066, "count": 1, "is_parallel": true, "self": 0.04711005900026066 }, "steps_from_proto": { "total": 0.002055701999779558, "count": 1, "is_parallel": true, "self": 0.00043601000106718857, "children": { "_process_rank_one_or_two_observation": { "total": 0.0016196919987123692, "count": 8, "is_parallel": true, "self": 0.0016196919987123692 } } } } } } }, "UnityEnvironment.step": { "total": 784.1052182009735, "count": 31563, "is_parallel": true, "self": 17.785392268940086, "children": { "UnityEnvironment._generate_step_input": { "total": 12.106061942979977, "count": 31563, "is_parallel": true, "self": 12.106061942979977 }, "communicator.exchange": { "total": 692.074507109026, "count": 31563, "is_parallel": true, "self": 692.074507109026 }, "steps_from_proto": { "total": 62.13925688002746, "count": 31563, "is_parallel": true, "self": 13.340318487837976, "children": { "_process_rank_one_or_two_observation": { "total": 48.798938392189484, "count": 252504, "is_parallel": true, "self": 48.798938392189484 } } } } } } } } } } }, "trainer_advance": { "total": 350.3014160830171, "count": 31564, "self": 1.2151123359944904, "children": { "process_trajectory": { "total": 67.80095942001662, "count": 31564, "self": 67.74959101101649, "children": { "RLTrainer._checkpoint": { "total": 0.0513684090001334, "count": 1, "self": 0.0513684090001334 } } }, "_update_policy": { "total": 281.285344327006, "count": 211, "self": 157.08280157898662, "children": { "TorchPPOOptimizer.update": { "total": 124.20254274801937, "count": 11460, "self": 124.20254274801937 } } } } } } }, "TrainerController._save_models": { "total": 0.05338072700033081, "count": 1, "self": 2.661300004547229e-05, "children": { "RLTrainer._checkpoint": { "total": 0.053354114000285335, "count": 1, "self": 0.053354114000285335 } } } } } } }