{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.6732721328735352, "min": 0.653671145439148, "max": 1.465767741203308, "count": 16 }, "Pyramids.Policy.Entropy.sum": { "value": 20101.212890625, "min": 19599.67578125, "max": 44465.53125, "count": 16 }, "Pyramids.Step.mean": { "value": 479954.0, "min": 29970.0, "max": 479954.0, "count": 16 }, "Pyramids.Step.sum": { "value": 479954.0, "min": 29970.0, "max": 479954.0, "count": 16 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.08239706605672836, "min": -0.09955029934644699, "max": 0.11746586859226227, "count": 16 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 20.516868591308594, "min": -23.991622924804688, "max": 27.956876754760742, "count": 16 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.020269012078642845, "min": 0.020269012078642845, "max": 0.21861574053764343, "count": 16 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 5.0469841957092285, "min": 5.0469841957092285, "max": 52.467777252197266, "count": 16 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06829765457188755, "min": 0.06619743894625643, "max": 0.07763925096231715, "count": 16 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9561671640064257, "min": 0.54347475673622, "max": 1.0030834898158596, "count": 16 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.007166939378207427, "min": 0.0007460488981029515, "max": 0.007549330405380402, "count": 16 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.10033715129490398, "min": 0.008206537879132466, "max": 0.10569062567532563, "count": 16 }, "Pyramids.Policy.LearningRate.mean": { "value": 2.153910710604286e-05, "min": 2.153910710604286e-05, "max": 0.00029047526031777135, "count": 16 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00030154749948460005, "min": 0.00030154749948460005, "max": 0.003061428179523999, "count": 16 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10717967142857143, "min": 0.10717967142857143, "max": 0.19682508571428572, "count": 16 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.5005154, "min": 1.3777756, "max": 2.3390922, "count": 16 }, "Pyramids.Policy.Beta.mean": { "value": 0.0007272491757142856, "min": 0.0007272491757142856, "max": 0.009682826062857142, "count": 16 }, "Pyramids.Policy.Beta.sum": { "value": 0.010181488459999999, "min": 0.010181488459999999, "max": 0.1020655524, "count": 16 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.02442983351647854, "min": 0.02442983351647854, "max": 0.4016760289669037, "count": 16 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.34201768040657043, "min": 0.34201768040657043, "max": 2.811732292175293, "count": 16 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 749.3170731707318, "min": 749.3170731707318, "max": 995.6451612903226, "count": 16 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30722.0, "min": 16513.0, "max": 33178.0, "count": 16 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 0.22610727842988038, "min": -0.933987550670281, "max": 0.3955631120816657, "count": 16 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 9.270398415625095, "min": -30.735601656138897, "max": 15.031398259103298, "count": 16 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 0.22610727842988038, "min": -0.933987550670281, "max": 0.3955631120816657, "count": 16 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 9.270398415625095, "min": -30.735601656138897, "max": 15.031398259103298, "count": 16 }, "Pyramids.Policy.RndReward.mean": { "value": 0.19009923869062487, "min": 0.19009923869062487, "max": 7.313870205379584, "count": 16 }, "Pyramids.Policy.RndReward.sum": { "value": 7.79406878631562, "min": 7.79406878631562, "max": 124.33579349145293, "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": "1704889193", "python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [GCC 11.4.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn --force ./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": "1704890286" }, "total": 1093.3259643409997, "count": 1, "self": 0.47641756499933763, "children": { "run_training.setup": { "total": 0.05583182600003056, "count": 1, "self": 0.05583182600003056 }, "TrainerController.start_learning": { "total": 1092.7937149500003, "count": 1, "self": 0.7282664170070348, "children": { "TrainerController._reset_env": { "total": 2.0598539469997377, "count": 1, "self": 2.0598539469997377 }, "TrainerController.advance": { "total": 1089.9154234449934, "count": 31647, "self": 0.770376152085646, "children": { "env_step": { "total": 773.8002881019429, "count": 31647, "self": 703.896375057891, "children": { "SubprocessEnvManager._take_step": { "total": 69.43605387903244, "count": 31647, "self": 2.5301177160217776, "children": { "TorchPolicy.evaluate": { "total": 66.90593616301067, "count": 31320, "self": 66.90593616301067 } } }, "workers": { "total": 0.4678591650194903, "count": 31647, "self": 0.0, "children": { "worker_root": { "total": 1089.9491252140324, "count": 31647, "is_parallel": true, "self": 449.72005977809613, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0019067639996137586, "count": 1, "is_parallel": true, "self": 0.000570811999750731, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013359519998630276, "count": 8, "is_parallel": true, "self": 0.0013359519998630276 } } }, "UnityEnvironment.step": { "total": 0.05693835400006719, "count": 1, "is_parallel": true, "self": 0.0006383700001606485, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005192419998820696, "count": 1, "is_parallel": true, "self": 0.0005192419998820696 }, "communicator.exchange": { "total": 0.053737048999664694, "count": 1, "is_parallel": true, "self": 0.053737048999664694 }, "steps_from_proto": { "total": 0.002043693000359781, "count": 1, "is_parallel": true, "self": 0.0005032470012338308, "children": { "_process_rank_one_or_two_observation": { "total": 0.00154044599912595, "count": 8, "is_parallel": true, "self": 0.00154044599912595 } } } } } } }, "UnityEnvironment.step": { "total": 640.2290654359363, "count": 31646, "is_parallel": true, "self": 17.983059374935237, "children": { "UnityEnvironment._generate_step_input": { "total": 13.180948778979655, "count": 31646, "is_parallel": true, "self": 13.180948778979655 }, "communicator.exchange": { "total": 556.1589696189799, "count": 31646, "is_parallel": true, "self": 556.1589696189799 }, "steps_from_proto": { "total": 52.90608766304149, "count": 31646, "is_parallel": true, "self": 10.8863978981517, "children": { "_process_rank_one_or_two_observation": { "total": 42.01968976488979, "count": 253168, "is_parallel": true, "self": 42.01968976488979 } } } } } } } } } } }, "trainer_advance": { "total": 315.34475919096485, "count": 31647, "self": 1.3326352658841643, "children": { "process_trajectory": { "total": 64.45908553808522, "count": 31647, "self": 64.34633551608522, "children": { "RLTrainer._checkpoint": { "total": 0.11275002200000017, "count": 1, "self": 0.11275002200000017 } } }, "_update_policy": { "total": 249.55303838699547, "count": 217, "self": 147.7943989129799, "children": { "TorchPPOOptimizer.update": { "total": 101.75863947401558, "count": 11418, "self": 101.75863947401558 } } } } } } }, "trainer_threads": { "total": 1.0490002750884742e-06, "count": 1, "self": 1.0490002750884742e-06 }, "TrainerController._save_models": { "total": 0.09017009199988024, "count": 1, "self": 0.0016466090000903932, "children": { "RLTrainer._checkpoint": { "total": 0.08852348299978985, "count": 1, "self": 0.08852348299978985 } } } } } } }