{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.4362189471721649, "min": 0.4362189471721649, "max": 1.4933967590332031, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 13114.486328125, "min": 13114.486328125, "max": 45303.68359375, "count": 33 }, "Pyramids.Step.mean": { "value": 989961.0, "min": 29952.0, "max": 989961.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989961.0, "min": 29952.0, "max": 989961.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.5291139483451843, "min": -0.13015344738960266, "max": 0.6328531503677368, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 150.2683563232422, "min": -31.236827850341797, "max": 176.30767822265625, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -0.0485844649374485, "min": -0.0485844649374485, "max": 0.17798210680484772, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -13.797987937927246, "min": -13.797987937927246, "max": 42.71570587158203, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.07127943250945665, "min": 0.06584264160483144, "max": 0.07479747427250599, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 1.0691914876418498, "min": 0.4855498443207109, "max": 1.0691914876418498, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.015021717722993344, "min": 0.00059948886072111, "max": 0.016582418632987397, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.22532576584490016, "min": 0.005994888607211099, "max": 0.23215386086182357, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.4972175009599945e-06, "min": 7.4972175009599945e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00011245826251439992, "min": 0.00011245826251439992, "max": 0.003492554535815199, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10249904000000001, "min": 0.10249904000000001, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.5374856000000001, "min": 1.3886848, "max": 2.4641848, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002596540959999999, "min": 0.0002596540959999999, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.003894811439999998, "min": 0.003894811439999998, "max": 0.11643206152, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.012157434597611427, "min": 0.012157434597611427, "max": 0.3756782114505768, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.18236151337623596, "min": 0.1715967059135437, "max": 2.6297473907470703, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 356.64772727272725, "min": 294.08, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 31385.0, "min": 15984.0, "max": 32763.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.4842295267365195, "min": -1.0000000521540642, "max": 1.6859099862724543, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 130.61219835281372, "min": -30.999801620841026, "max": 168.59099862724543, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.4842295267365195, "min": -1.0000000521540642, "max": 1.6859099862724543, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 130.61219835281372, "min": -30.999801620841026, "max": 168.59099862724543, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.04466771369135875, "min": 0.03710477185493801, "max": 7.070317625068128, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.93075880483957, "min": 3.710477185493801, "max": 113.12508200109005, "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": "1751740616", "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=Pyramids Training --no-graphics", "mlagents_version": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.7.1+cu126", "numpy_version": "1.23.5", "end_time_seconds": "1751742793" }, "total": 2177.101828027, "count": 1, "self": 0.5873077870000998, "children": { "run_training.setup": { "total": 0.023170743000036964, "count": 1, "self": 0.023170743000036964 }, "TrainerController.start_learning": { "total": 2176.4913494969996, "count": 1, "self": 1.254073383060586, "children": { "TrainerController._reset_env": { "total": 3.198284070999989, "count": 1, "self": 3.198284070999989 }, "TrainerController.advance": { "total": 2171.958553721939, "count": 63896, "self": 1.3249061279771013, "children": { "env_step": { "total": 1530.8525650819731, "count": 63896, "self": 1390.0829189059361, "children": { "SubprocessEnvManager._take_step": { "total": 140.02154163902674, "count": 63896, "self": 4.472146760113674, "children": { "TorchPolicy.evaluate": { "total": 135.54939487891306, "count": 62556, "self": 135.54939487891306 } } }, "workers": { "total": 0.7481045370102493, "count": 63896, "self": 0.0, "children": { "worker_root": { "total": 2171.4223731589686, "count": 63896, "is_parallel": true, "self": 889.9754565229337, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005288386000074752, "count": 1, "is_parallel": true, "self": 0.004022711999823514, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012656740002512379, "count": 8, "is_parallel": true, "self": 0.0012656740002512379 } } }, "UnityEnvironment.step": { "total": 0.07286562600006619, "count": 1, "is_parallel": true, "self": 0.0005547050000132003, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00045417199999064906, "count": 1, "is_parallel": true, "self": 0.00045417199999064906 }, "communicator.exchange": { "total": 0.07014537800000653, "count": 1, "is_parallel": true, "self": 0.07014537800000653 }, "steps_from_proto": { "total": 0.0017113710000558058, "count": 1, "is_parallel": true, "self": 0.0003779050002776785, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013334659997781273, "count": 8, "is_parallel": true, "self": 0.0013334659997781273 } } } } } } }, "UnityEnvironment.step": { "total": 1281.446916636035, "count": 63895, "is_parallel": true, "self": 31.521942387039417, "children": { "UnityEnvironment._generate_step_input": { "total": 22.813482185070598, "count": 63895, "is_parallel": true, "self": 22.813482185070598 }, "communicator.exchange": { "total": 1133.4007584309627, "count": 63895, "is_parallel": true, "self": 1133.4007584309627 }, "steps_from_proto": { "total": 93.71073363296227, "count": 63895, "is_parallel": true, "self": 18.53749774307198, "children": { "_process_rank_one_or_two_observation": { "total": 75.1732358898903, "count": 511160, "is_parallel": true, "self": 75.1732358898903 } } } } } } } } } } }, "trainer_advance": { "total": 639.7810825119889, "count": 63896, "self": 2.3732463400401684, "children": { "process_trajectory": { "total": 124.69384245895003, "count": 63896, "self": 124.41405549395017, "children": { "RLTrainer._checkpoint": { "total": 0.27978696499985745, "count": 2, "self": 0.27978696499985745 } } }, "_update_policy": { "total": 512.7139937129987, "count": 447, "self": 287.035267336003, "children": { "TorchPPOOptimizer.update": { "total": 225.67872637699566, "count": 22776, "self": 225.67872637699566 } } } } } } }, "trainer_threads": { "total": 9.55000359681435e-07, "count": 1, "self": 9.55000359681435e-07 }, "TrainerController._save_models": { "total": 0.08043736599984186, "count": 1, "self": 0.001753952999933972, "children": { "RLTrainer._checkpoint": { "total": 0.07868341299990789, "count": 1, "self": 0.07868341299990789 } } } } } } }