{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.45153433084487915, "min": 0.45153433084487915, "max": 1.4062343835830688, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 13509.9072265625, "min": 13509.9072265625, "max": 42659.52734375, "count": 33 }, "Pyramids.Step.mean": { "value": 989920.0, "min": 29952.0, "max": 989920.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989920.0, "min": 29952.0, "max": 989920.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.5727611184120178, "min": -0.08905193209648132, "max": 0.5727611184120178, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 162.09140014648438, "min": -21.37246322631836, "max": 162.09140014648438, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -0.007756403181701899, "min": -0.012437771074473858, "max": 0.3378222584724426, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -2.1950621604919434, "min": -3.2586960792541504, "max": 81.4151611328125, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.0698572995459026, "min": 0.06722000251531161, "max": 0.07352810231413995, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9780021936426364, "min": 0.511838404029031, "max": 1.0346281533255057, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.017577760698006165, "min": 0.0005561509906003066, "max": 0.017577760698006165, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.2460886497720863, "min": 0.007229962877803985, "max": 0.2460886497720863, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.288940427528575e-06, "min": 7.288940427528575e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010204516598540004, "min": 0.00010204516598540004, "max": 0.0035075990308003993, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.1024296142857143, "min": 0.1024296142857143, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4340146000000003, "min": 1.3886848, "max": 2.5691996000000006, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00025271846714285725, "min": 0.00025271846714285725, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0035380585400000015, "min": 0.0035380585400000015, "max": 0.11694304004000002, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.011265001259744167, "min": 0.011265001259744167, "max": 0.4198058247566223, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.1577100157737732, "min": 0.1577100157737732, "max": 2.938640832901001, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 329.5217391304348, "min": 329.5217391304348, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30316.0, "min": 15984.0, "max": 33320.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.6257173734838548, "min": -1.0000000521540642, "max": 1.6385585974002708, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 149.56599836051464, "min": -29.52340167760849, "max": 149.56599836051464, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.6257173734838548, "min": -1.0000000521540642, "max": 1.6385585974002708, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 149.56599836051464, "min": -29.52340167760849, "max": 149.56599836051464, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.03820430362168775, "min": 0.03820430362168775, "max": 7.9384287456050515, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.5147959331952734, "min": 3.4133540045586415, "max": 127.01485992968082, "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": "1696321508", "python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [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": "0.31.0.dev0", "mlagents_envs_version": "0.31.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.11.0+cu102", "numpy_version": "1.21.2", "end_time_seconds": "1696324159" }, "total": 2650.20342808, "count": 1, "self": 0.43916874200021994, "children": { "run_training.setup": { "total": 0.049421357000028365, "count": 1, "self": 0.049421357000028365 }, "TrainerController.start_learning": { "total": 2649.7148379809996, "count": 1, "self": 1.9919695151047563, "children": { "TrainerController._reset_env": { "total": 2.0767939669999578, "count": 1, "self": 2.0767939669999578 }, "TrainerController.advance": { "total": 2645.5689022258944, "count": 63786, "self": 1.874029655981758, "children": { "env_step": { "total": 1474.4330202810002, "count": 63786, "self": 1338.9078955800178, "children": { "SubprocessEnvManager._take_step": { "total": 134.30821059790742, "count": 63786, "self": 4.717661260875957, "children": { "TorchPolicy.evaluate": { "total": 129.59054933703146, "count": 62572, "self": 129.59054933703146 } } }, "workers": { "total": 1.2169141030749415, "count": 63786, "self": 0.0, "children": { "worker_root": { "total": 2644.9109081209945, "count": 63786, "is_parallel": true, "self": 1436.195656942985, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005560300000070129, "count": 1, "is_parallel": true, "self": 0.004495441999551986, "children": { "_process_rank_one_or_two_observation": { "total": 0.001064858000518143, "count": 8, "is_parallel": true, "self": 0.001064858000518143 } } }, "UnityEnvironment.step": { "total": 0.06451919599976463, "count": 1, "is_parallel": true, "self": 0.0005658699992636684, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0009482800001023861, "count": 1, "is_parallel": true, "self": 0.0009482800001023861 }, "communicator.exchange": { "total": 0.05946156600020913, "count": 1, "is_parallel": true, "self": 0.05946156600020913 }, "steps_from_proto": { "total": 0.0035434800001894473, "count": 1, "is_parallel": true, "self": 0.00048553999931755243, "children": { "_process_rank_one_or_two_observation": { "total": 0.003057940000871895, "count": 8, "is_parallel": true, "self": 0.003057940000871895 } } } } } } }, "UnityEnvironment.step": { "total": 1208.7152511780096, "count": 63785, "is_parallel": true, "self": 33.85332789417362, "children": { "UnityEnvironment._generate_step_input": { "total": 18.615647245977925, "count": 63785, "is_parallel": true, "self": 18.615647245977925 }, "communicator.exchange": { "total": 1057.1329615889222, "count": 63785, "is_parallel": true, "self": 1057.1329615889222 }, "steps_from_proto": { "total": 99.11331444893585, "count": 63785, "is_parallel": true, "self": 21.22202660007406, "children": { "_process_rank_one_or_two_observation": { "total": 77.8912878488618, "count": 510280, "is_parallel": true, "self": 77.8912878488618 } } } } } } } } } } }, "trainer_advance": { "total": 1169.2618522889125, "count": 63786, "self": 3.795920761742309, "children": { "process_trajectory": { "total": 131.88881813118087, "count": 63786, "self": 131.71570583218136, "children": { "RLTrainer._checkpoint": { "total": 0.17311229899951286, "count": 2, "self": 0.17311229899951286 } } }, "_update_policy": { "total": 1033.5771133959893, "count": 450, "self": 308.78296924211054, "children": { "TorchPPOOptimizer.update": { "total": 724.7941441538787, "count": 22764, "self": 724.7941441538787 } } } } } } }, "trainer_threads": { "total": 7.700000423938036e-07, "count": 1, "self": 7.700000423938036e-07 }, "TrainerController._save_models": { "total": 0.0771715030004998, "count": 1, "self": 0.0009152890006589587, "children": { "RLTrainer._checkpoint": { "total": 0.07625621399984084, "count": 1, "self": 0.07625621399984084 } } } } } } }