{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.5548283457756042, "min": 0.5478066205978394, "max": 1.343166470527649, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 16618.21875, "min": 16372.84375, "max": 40746.296875, "count": 33 }, "Pyramids.Step.mean": { "value": 989914.0, "min": 29952.0, "max": 989914.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989914.0, "min": 29952.0, "max": 989914.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": -0.009701108559966087, "min": -0.027501562610268593, "max": 0.006844534073024988, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": -2.3379671573638916, "min": -6.6278767585754395, "max": 1.6563771963119507, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.042118024080991745, "min": 0.038220711052417755, "max": 0.714160144329071, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 10.150444030761719, "min": 9.184642791748047, "max": 169.25595092773438, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06937680793537253, "min": 0.06544931462943242, "max": 0.07417337220178975, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9712753110952154, "min": 0.5091262181281466, "max": 1.0500981600632135, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.0006671878213796112, "min": 2.429345335206178e-05, "max": 0.012193126144808041, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.009340629499314556, "min": 0.0003401083469288649, "max": 0.08535188301365629, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.775904550921427e-06, "min": 7.775904550921427e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010886266371289999, "min": 0.00010886266371289999, "max": 0.0032546177151274998, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10259193571428572, "min": 0.10259193571428572, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4362871000000001, "min": 1.3691136000000002, "max": 2.4844622, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00026893437785714284, "min": 0.00026893437785714284, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0037650812899999997, "min": 0.0037650812899999997, "max": 0.10850876275, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.043518248945474625, "min": 0.04106331989169121, "max": 0.6545859575271606, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.6092554926872253, "min": 0.5748865008354187, "max": 4.582101821899414, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 972.2903225806451, "min": 896.5, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30141.0, "min": 15984.0, "max": 32374.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": -0.7146581159003319, "min": -1.0000000521540642, "max": -0.47576367697029404, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": -22.15440159291029, "min": -32.000001668930054, "max": -15.700201340019703, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": -0.7146581159003319, "min": -1.0000000521540642, "max": -0.47576367697029404, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": -22.15440159291029, "min": -32.000001668930054, "max": -15.700201340019703, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.4264755182554044, "min": 0.3975419149254308, "max": 13.446727706119418, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 13.220741065917537, "min": 11.865816544741392, "max": 215.1476432979107, "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": "1684910582", "python_version": "3.10.11 (main, Apr 5 2023, 14:15:10) [GCC 9.4.0]", "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 --torch-device cuda:0", "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": "1684912515" }, "total": 1932.5416005400002, "count": 1, "self": 0.49198436700021375, "children": { "run_training.setup": { "total": 0.06565657700002703, "count": 1, "self": 0.06565657700002703 }, "TrainerController.start_learning": { "total": 1931.983959596, "count": 1, "self": 1.264382122010602, "children": { "TrainerController._reset_env": { "total": 4.561444543000107, "count": 1, "self": 4.561444543000107 }, "TrainerController.advance": { "total": 1926.068758600989, "count": 63289, "self": 1.2637379550058085, "children": { "env_step": { "total": 1299.3724154320362, "count": 63289, "self": 1196.1722497859942, "children": { "SubprocessEnvManager._take_step": { "total": 102.44318881602885, "count": 63289, "self": 4.566027193024638, "children": { "TorchPolicy.evaluate": { "total": 97.87716162300421, "count": 62564, "self": 97.87716162300421 } } }, "workers": { "total": 0.7569768300131727, "count": 63289, "self": 0.0, "children": { "worker_root": { "total": 1927.5808488870637, "count": 63289, "is_parallel": true, "self": 837.8230016470454, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0025692060000892525, "count": 1, "is_parallel": true, "self": 0.0007157379998261604, "children": { "_process_rank_one_or_two_observation": { "total": 0.001853468000263092, "count": 8, "is_parallel": true, "self": 0.001853468000263092 } } }, "UnityEnvironment.step": { "total": 0.04331913600003645, "count": 1, "is_parallel": true, "self": 0.0005240830000730057, "children": { "UnityEnvironment._generate_step_input": { "total": 0.000465892999955031, "count": 1, "is_parallel": true, "self": 0.000465892999955031 }, "communicator.exchange": { "total": 0.04062580599998, "count": 1, "is_parallel": true, "self": 0.04062580599998 }, "steps_from_proto": { "total": 0.001703354000028412, "count": 1, "is_parallel": true, "self": 0.00034590500013109704, "children": { "_process_rank_one_or_two_observation": { "total": 0.001357448999897315, "count": 8, "is_parallel": true, "self": 0.001357448999897315 } } } } } } }, "UnityEnvironment.step": { "total": 1089.7578472400182, "count": 63288, "is_parallel": true, "self": 30.82191178993162, "children": { "UnityEnvironment._generate_step_input": { "total": 21.959418965995837, "count": 63288, "is_parallel": true, "self": 21.959418965995837 }, "communicator.exchange": { "total": 942.4144531270224, "count": 63288, "is_parallel": true, "self": 942.4144531270224 }, "steps_from_proto": { "total": 94.56206335706838, "count": 63288, "is_parallel": true, "self": 18.956046673184574, "children": { "_process_rank_one_or_two_observation": { "total": 75.60601668388381, "count": 506304, "is_parallel": true, "self": 75.60601668388381 } } } } } } } } } } }, "trainer_advance": { "total": 625.432605213947, "count": 63289, "self": 2.3884990449275847, "children": { "process_trajectory": { "total": 102.42527161102225, "count": 63289, "self": 102.22635177602206, "children": { "RLTrainer._checkpoint": { "total": 0.19891983500019705, "count": 2, "self": 0.19891983500019705 } } }, "_update_policy": { "total": 520.6188345579972, "count": 444, "self": 339.1423938050168, "children": { "TorchPPOOptimizer.update": { "total": 181.47644075298035, "count": 22737, "self": 181.47644075298035 } } } } } } }, "trainer_threads": { "total": 9.589998626324814e-07, "count": 1, "self": 9.589998626324814e-07 }, "TrainerController._save_models": { "total": 0.08937337100041987, "count": 1, "self": 0.0013874860005671508, "children": { "RLTrainer._checkpoint": { "total": 0.08798588499985271, "count": 1, "self": 0.08798588499985271 } } } } } } }