{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.3366871774196625, "min": 0.3330022096633911, "max": 1.4219340085983276, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 10235.2900390625, "min": 9984.73828125, "max": 43135.7890625, "count": 33 }, "Pyramids.Step.mean": { "value": 989877.0, "min": 29952.0, "max": 989877.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989877.0, "min": 29952.0, "max": 989877.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.6816462874412537, "min": -0.07592428475618362, "max": 0.68465656042099, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 196.3141326904297, "min": -18.297752380371094, "max": 201.97369384765625, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.03980015218257904, "min": 0.00152592605445534, "max": 0.48404577374458313, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 11.462443351745605, "min": 0.41810375452041626, "max": 114.7188491821289, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06694541648806383, "min": 0.06646687135179279, "max": 0.07333578196485536, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 1.0041812473209575, "min": 0.5133504737539876, "max": 1.0666657999487748, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.01642445712414984, "min": 0.0006315113308721555, "max": 0.017227739065121143, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.2463668568622476, "min": 0.008209647301338021, "max": 0.2463668568622476, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.515037495019998e-06, "min": 7.515037495019998e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00011272556242529997, "min": 0.00011272556242529997, "max": 0.0035088470303843993, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10250498000000001, "min": 0.10250498000000001, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.5375747000000002, "min": 1.3886848, "max": 2.5696156, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00026024750199999996, "min": 0.00026024750199999996, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0039037125299999998, "min": 0.0039037125299999998, "max": 0.11698459844000002, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.010924839414656162, "min": 0.010924839414656162, "max": 0.6330909729003906, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.1638725847005844, "min": 0.15804336965084076, "max": 4.431636810302734, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 292.1588785046729, "min": 254.34234234234233, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 31261.0, "min": 15984.0, "max": 32686.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.6517513869939564, "min": -1.0000000521540642, "max": 1.7279071247737323, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 176.73739840835333, "min": -30.71720176190138, "max": 193.525597974658, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.6517513869939564, "min": -1.0000000521540642, "max": 1.7279071247737323, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 176.73739840835333, "min": -30.71720176190138, "max": 193.525597974658, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.03261350840656522, "min": 0.030612224453453303, "max": 13.677852573804557, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.4896453995024785, "min": 3.42856913878677, "max": 218.84564118087292, "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": "1705061374", "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 Training --no-graphics", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.1.2+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1705063949" }, "total": 2574.881598223, "count": 1, "self": 0.5274620090003737, "children": { "run_training.setup": { "total": 0.054025351999371196, "count": 1, "self": 0.054025351999371196 }, "TrainerController.start_learning": { "total": 2574.300110862, "count": 1, "self": 1.6097330481125027, "children": { "TrainerController._reset_env": { "total": 2.6791225780007153, "count": 1, "self": 2.6791225780007153 }, "TrainerController.advance": { "total": 2569.925552949887, "count": 64187, "self": 1.665976816926559, "children": { "env_step": { "total": 1886.1826631479453, "count": 64187, "self": 1742.468621815141, "children": { "SubprocessEnvManager._take_step": { "total": 142.6963787568602, "count": 64187, "self": 5.22195460990406, "children": { "TorchPolicy.evaluate": { "total": 137.47442414695615, "count": 62565, "self": 137.47442414695615 } } }, "workers": { "total": 1.0176625759440867, "count": 64187, "self": 0.0, "children": { "worker_root": { "total": 2568.3049121659824, "count": 64187, "is_parallel": true, "self": 957.5565839480278, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0017127769997387077, "count": 1, "is_parallel": true, "self": 0.0005435469984149677, "children": { "_process_rank_one_or_two_observation": { "total": 0.00116923000132374, "count": 8, "is_parallel": true, "self": 0.00116923000132374 } } }, "UnityEnvironment.step": { "total": 0.07309752099990874, "count": 1, "is_parallel": true, "self": 0.0005886429999009124, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00042253199990227586, "count": 1, "is_parallel": true, "self": 0.00042253199990227586 }, "communicator.exchange": { "total": 0.07046525700025086, "count": 1, "is_parallel": true, "self": 0.07046525700025086 }, "steps_from_proto": { "total": 0.0016210889998546918, "count": 1, "is_parallel": true, "self": 0.000329165000039211, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012919239998154808, "count": 8, "is_parallel": true, "self": 0.0012919239998154808 } } } } } } }, "UnityEnvironment.step": { "total": 1610.7483282179546, "count": 64186, "is_parallel": true, "self": 38.61767408814649, "children": { "UnityEnvironment._generate_step_input": { "total": 25.485541429919977, "count": 64186, "is_parallel": true, "self": 25.485541429919977 }, "communicator.exchange": { "total": 1438.957215160849, "count": 64186, "is_parallel": true, "self": 1438.957215160849 }, "steps_from_proto": { "total": 107.68789753903911, "count": 64186, "is_parallel": true, "self": 22.574713788824738, "children": { "_process_rank_one_or_two_observation": { "total": 85.11318375021438, "count": 513488, "is_parallel": true, "self": 85.11318375021438 } } } } } } } } } } }, "trainer_advance": { "total": 682.076912985015, "count": 64187, "self": 3.208744297985504, "children": { "process_trajectory": { "total": 136.31882239402785, "count": 64187, "self": 136.11881576502765, "children": { "RLTrainer._checkpoint": { "total": 0.2000066290001996, "count": 2, "self": 0.2000066290001996 } } }, "_update_policy": { "total": 542.5493462930017, "count": 453, "self": 322.5379275799869, "children": { "TorchPPOOptimizer.update": { "total": 220.0114187130148, "count": 22809, "self": 220.0114187130148 } } } } } } }, "trainer_threads": { "total": 9.109999155043624e-07, "count": 1, "self": 9.109999155043624e-07 }, "TrainerController._save_models": { "total": 0.08570137500009878, "count": 1, "self": 0.0013972209999337792, "children": { "RLTrainer._checkpoint": { "total": 0.084304154000165, "count": 1, "self": 0.084304154000165 } } } } } } }