{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.710411012172699, "min": 0.654377281665802, "max": 1.3753466606140137, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 21244.130859375, "min": 19652.2578125, "max": 41722.515625, "count": 33 }, "Pyramids.Step.mean": { "value": 989974.0, "min": 29952.0, "max": 989974.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989974.0, "min": 29952.0, "max": 989974.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.05114472657442093, "min": -0.12620264291763306, "max": 0.07648573815822601, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 12.530458450317383, "min": -29.91002655029297, "max": 18.81549072265625, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.02154143713414669, "min": 0.008817550726234913, "max": 0.4165940284729004, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 5.277652263641357, "min": 2.1603000164031982, "max": 98.7327880859375, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.065779289554515, "min": 0.06490331644895668, "max": 0.07514343264518263, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.92091005376321, "min": 0.5123003884951247, "max": 1.0520080570325567, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.005244340651695369, "min": 7.720048138314167e-05, "max": 0.008385977909379533, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.07342076912373516, "min": 0.0010036062579808418, "max": 0.10029345009873698, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.648018879264283e-06, "min": 7.648018879264283e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010707226430969998, "min": 0.00010707226430969998, "max": 0.0033709396763535, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10254930714285715, "min": 0.10254930714285715, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4356903, "min": 1.3886848, "max": 2.4236465000000003, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00026467578357142863, "min": 0.00026467578357142863, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0037054609700000007, "min": 0.0037054609700000007, "max": 0.11238228535, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.013204381801187992, "min": 0.013204381801187992, "max": 0.4460248649120331, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.18486134707927704, "min": 0.18486134707927704, "max": 3.122174024581909, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 826.5, "min": 757.3589743589744, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 31407.0, "min": 15984.0, "max": 33069.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": -0.09002109244465828, "min": -1.0000000521540642, "max": 0.21664099853772384, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": -3.4208015128970146, "min": -31.994401678442955, "max": 8.44899894297123, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": -0.09002109244465828, "min": -1.0000000521540642, "max": 0.21664099853772384, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": -3.4208015128970146, "min": -31.994401678442955, "max": 8.44899894297123, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.11229849981119562, "min": 0.10832251825083333, "max": 9.284771942533553, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 4.267342992825434, "min": 4.2245782117825, "max": 148.55635108053684, "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": "1677169885", "python_version": "3.8.10 (default, Nov 14 2022, 12:59:47) \n[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", "mlagents_version": "0.29.0.dev0", "mlagents_envs_version": "0.29.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.8.1+cu102", "numpy_version": "1.22.4", "end_time_seconds": "1677172034" }, "total": 2149.154496711, "count": 1, "self": 0.42936596300023666, "children": { "run_training.setup": { "total": 0.10830747699992571, "count": 1, "self": 0.10830747699992571 }, "TrainerController.start_learning": { "total": 2148.6168232709997, "count": 1, "self": 1.2642462161184085, "children": { "TrainerController._reset_env": { "total": 6.1724365119998765, "count": 1, "self": 6.1724365119998765 }, "TrainerController.advance": { "total": 2141.089984640882, "count": 63116, "self": 1.2893763728980048, "children": { "env_step": { "total": 1397.947639543917, "count": 63116, "self": 1289.89100721784, "children": { "SubprocessEnvManager._take_step": { "total": 107.30597686603505, "count": 63116, "self": 4.547928265026258, "children": { "TorchPolicy.evaluate": { "total": 102.7580486010088, "count": 62556, "self": 34.818594432078044, "children": { "TorchPolicy.sample_actions": { "total": 67.93945416893075, "count": 62556, "self": 67.93945416893075 } } } } }, "workers": { "total": 0.7506554600417985, "count": 63116, "self": 0.0, "children": { "worker_root": { "total": 2144.385907513075, "count": 63116, "is_parallel": true, "self": 962.5597936450831, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.001859450000210927, "count": 1, "is_parallel": true, "self": 0.0006454449999182543, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012140050002926728, "count": 8, "is_parallel": true, "self": 0.0012140050002926728 } } }, "UnityEnvironment.step": { "total": 0.048362428000018554, "count": 1, "is_parallel": true, "self": 0.0005252579999250884, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004778700003953418, "count": 1, "is_parallel": true, "self": 0.0004778700003953418 }, "communicator.exchange": { "total": 0.04571542399980899, "count": 1, "is_parallel": true, "self": 0.04571542399980899 }, "steps_from_proto": { "total": 0.0016438759998891328, "count": 1, "is_parallel": true, "self": 0.0004248229993208952, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012190530005682376, "count": 8, "is_parallel": true, "self": 0.0012190530005682376 } } } } } } }, "UnityEnvironment.step": { "total": 1181.8261138679918, "count": 63115, "is_parallel": true, "self": 30.687249917954887, "children": { "UnityEnvironment._generate_step_input": { "total": 22.508686043991474, "count": 63115, "is_parallel": true, "self": 22.508686043991474 }, "communicator.exchange": { "total": 1039.488640887992, "count": 63115, "is_parallel": true, "self": 1039.488640887992 }, "steps_from_proto": { "total": 89.14153701805344, "count": 63115, "is_parallel": true, "self": 20.80824628497021, "children": { "_process_rank_one_or_two_observation": { "total": 68.33329073308323, "count": 504920, "is_parallel": true, "self": 68.33329073308323 } } } } } } } } } } }, "trainer_advance": { "total": 741.8529687240671, "count": 63116, "self": 2.2980312699642127, "children": { "process_trajectory": { "total": 160.25611025208855, "count": 63116, "self": 160.0766865390883, "children": { "RLTrainer._checkpoint": { "total": 0.17942371300023296, "count": 2, "self": 0.17942371300023296 } } }, "_update_policy": { "total": 579.2988272020143, "count": 443, "self": 227.88909313702425, "children": { "TorchPPOOptimizer.update": { "total": 351.40973406499006, "count": 22797, "self": 351.40973406499006 } } } } } } }, "trainer_threads": { "total": 1.3299995771376416e-06, "count": 1, "self": 1.3299995771376416e-06 }, "TrainerController._save_models": { "total": 0.09015457199984667, "count": 1, "self": 0.001557521999529854, "children": { "RLTrainer._checkpoint": { "total": 0.08859705000031681, "count": 1, "self": 0.08859705000031681 } } } } } } }