{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.47239044308662415, "min": 0.47239044308662415, "max": 1.4331653118133545, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 14028.1064453125, "min": 14028.1064453125, "max": 43476.50390625, "count": 33 }, "Pyramids.Step.mean": { "value": 989884.0, "min": 29952.0, "max": 989884.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989884.0, "min": 29952.0, "max": 989884.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.45157700777053833, "min": -0.09887171536684036, "max": 0.47841301560401917, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 122.82894897460938, "min": -23.828083038330078, "max": 128.69309997558594, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -0.7286822199821472, "min": -0.7286822199821472, "max": 0.31522977352142334, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -198.20156860351562, "min": -198.20156860351562, "max": 84.79680633544922, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06437175073300576, "min": 0.0631189383456323, "max": 0.07443314087827442, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9012045102620807, "min": 0.5058220864590405, "max": 1.0573811681265486, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.09172672515601984, "min": 0.00012889529375707597, "max": 0.09172672515601984, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 1.2841741521842778, "min": 0.0016756388188419876, "max": 1.2841741521842778, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.513233209907136e-06, "min": 7.513233209907136e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.0001051852649386999, "min": 0.0001051852649386999, "max": 0.0033827135724289, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10250437857142858, "min": 0.10250437857142858, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4350613, "min": 1.3886848, "max": 2.5275711000000003, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002601874192857141, "min": 0.0002601874192857141, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0036426238699999976, "min": 0.0036426238699999976, "max": 0.11278435289000002, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.005443534813821316, "min": 0.005443534813821316, "max": 0.38346466422080994, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.07620948553085327, "min": 0.07620948553085327, "max": 2.6842527389526367, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 404.5945945945946, "min": 400.5733333333333, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29940.0, "min": 15984.0, "max": 32294.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.5413270043964322, "min": -1.0000000521540642, "max": 1.5413270043964322, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 114.05819832533598, "min": -31.999601677060127, "max": 114.05819832533598, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.5413270043964322, "min": -1.0000000521540642, "max": 1.5413270043964322, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 114.05819832533598, "min": -31.999601677060127, "max": 114.05819832533598, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.022992338810090097, "min": 0.022992338810090097, "max": 7.7162781432271, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 1.701433071946667, "min": 1.701433071946667, "max": 123.4604502916336, "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": "1736207174", "python_version": "3.10.12 (main, Nov 6 2024, 20:22:13) [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": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.5.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1736209764" }, "total": 2589.9907784710003, "count": 1, "self": 0.6797090840000237, "children": { "run_training.setup": { "total": 0.06451856500007125, "count": 1, "self": 0.06451856500007125 }, "TrainerController.start_learning": { "total": 2589.2465508220002, "count": 1, "self": 2.054344916057744, "children": { "TrainerController._reset_env": { "total": 2.4245271870004217, "count": 1, "self": 2.4245271870004217 }, "TrainerController.advance": { "total": 2584.669127560942, "count": 63505, "self": 2.0832825067764134, "children": { "env_step": { "total": 1803.697049445036, "count": 63505, "self": 1600.5136480419833, "children": { "SubprocessEnvManager._take_step": { "total": 201.94631498500075, "count": 63505, "self": 6.066564813049808, "children": { "TorchPolicy.evaluate": { "total": 195.87975017195095, "count": 62558, "self": 195.87975017195095 } } }, "workers": { "total": 1.2370864180520584, "count": 63505, "self": 0.0, "children": { "worker_root": { "total": 2582.622771411031, "count": 63505, "is_parallel": true, "self": 1134.3641687561549, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.002382669999860809, "count": 1, "is_parallel": true, "self": 0.0007744540007479372, "children": { "_process_rank_one_or_two_observation": { "total": 0.001608215999112872, "count": 8, "is_parallel": true, "self": 0.001608215999112872 } } }, "UnityEnvironment.step": { "total": 0.05563085799985856, "count": 1, "is_parallel": true, "self": 0.0006949740009076777, "children": { "UnityEnvironment._generate_step_input": { "total": 0.000526602999343595, "count": 1, "is_parallel": true, "self": 0.000526602999343595 }, "communicator.exchange": { "total": 0.052541463999659754, "count": 1, "is_parallel": true, "self": 0.052541463999659754 }, "steps_from_proto": { "total": 0.0018678169999475358, "count": 1, "is_parallel": true, "self": 0.00041370800045115175, "children": { "_process_rank_one_or_two_observation": { "total": 0.001454108999496384, "count": 8, "is_parallel": true, "self": 0.001454108999496384 } } } } } } }, "UnityEnvironment.step": { "total": 1448.258602654876, "count": 63504, "is_parallel": true, "self": 41.55999414592043, "children": { "UnityEnvironment._generate_step_input": { "total": 27.537241372999233, "count": 63504, "is_parallel": true, "self": 27.537241372999233 }, "communicator.exchange": { "total": 1258.8986376470693, "count": 63504, "is_parallel": true, "self": 1258.8986376470693 }, "steps_from_proto": { "total": 120.26272948888709, "count": 63504, "is_parallel": true, "self": 25.9217230941631, "children": { "_process_rank_one_or_two_observation": { "total": 94.34100639472399, "count": 508032, "is_parallel": true, "self": 94.34100639472399 } } } } } } } } } } }, "trainer_advance": { "total": 778.8887956091294, "count": 63505, "self": 3.6700181463374975, "children": { "process_trajectory": { "total": 153.54413345279136, "count": 63505, "self": 153.31580913479047, "children": { "RLTrainer._checkpoint": { "total": 0.2283243180008867, "count": 2, "self": 0.2283243180008867 } } }, "_update_policy": { "total": 621.6746440100005, "count": 440, "self": 348.0379120510461, "children": { "TorchPPOOptimizer.update": { "total": 273.63673195895444, "count": 22851, "self": 273.63673195895444 } } } } } } }, "trainer_threads": { "total": 1.124000846175477e-06, "count": 1, "self": 1.124000846175477e-06 }, "TrainerController._save_models": { "total": 0.09855003399934503, "count": 1, "self": 0.0020817959994019475, "children": { "RLTrainer._checkpoint": { "total": 0.09646823799994309, "count": 1, "self": 0.09646823799994309 } } } } } } }