{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.23843881487846375, "min": 0.23753118515014648, "max": 1.4292476177215576, "count": 52 }, "Pyramids.Policy.Entropy.sum": { "value": 7134.08935546875, "min": 7038.52392578125, "max": 43357.65625, "count": 52 }, "Pyramids.Step.mean": { "value": 1559896.0, "min": 29952.0, "max": 1559896.0, "count": 52 }, "Pyramids.Step.sum": { "value": 1559896.0, "min": 29952.0, "max": 1559896.0, "count": 52 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.8326560258865356, "min": -0.09205543994903564, "max": 0.8420236706733704, "count": 52 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 248.13150024414062, "min": -22.185361862182617, "max": 257.65924072265625, "count": 52 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.010321666486561298, "min": -0.00941386166960001, "max": 0.30597904324531555, "count": 52 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 3.0758566856384277, "min": -2.607639789581299, "max": 73.74095153808594, "count": 52 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.07147382796156357, "min": 0.06486261799195224, "max": 0.07377905931142677, "count": 52 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 1.00063359146189, "min": 0.48229706238743836, "max": 1.1066858896714016, "count": 52 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.01327213931332097, "min": 0.00015669237809535664, "max": 0.0166132790467921, "count": 52 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.1858099503864936, "min": 0.0020370009152396364, "max": 0.2491991857018815, "count": 52 }, "Pyramids.Policy.LearningRate.mean": { "value": 0.00014549105864585473, "min": 0.00014549105864585473, "max": 0.00029838354339596195, "count": 52 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.0020368748210419663, "min": 0.0020368748210419663, "max": 0.004027387257537632, "count": 52 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.1484970023809524, "min": 0.1484970023809524, "max": 0.19946118095238097, "count": 52 }, "Pyramids.Policy.Epsilon.sum": { "value": 2.0789580333333335, "min": 1.3962282666666668, "max": 2.842462366666667, "count": 52 }, "Pyramids.Policy.Beta.mean": { "value": 0.004854850537857143, "min": 0.004854850537857143, "max": 0.009946171977142856, "count": 52 }, "Pyramids.Policy.Beta.sum": { "value": 0.06796790753000001, "min": 0.06796790753000001, "max": 0.13426199043, "count": 52 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.01016409695148468, "min": 0.009826130233705044, "max": 0.469675749540329, "count": 52 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.14229735732078552, "min": 0.13936378061771393, "max": 3.2877302169799805, "count": 52 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 230.04724409448818, "min": 220.32575757575756, "max": 999.0, "count": 52 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29216.0, "min": 15984.0, "max": 32708.0, "count": 52 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.7541999853267445, "min": -1.0000000521540642, "max": 1.7697099173114499, "count": 52 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 222.78339813649654, "min": -30.99380160868168, "max": 235.2053981423378, "count": 52 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.7541999853267445, "min": -1.0000000521540642, "max": 1.7697099173114499, "count": 52 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 222.78339813649654, "min": -30.99380160868168, "max": 235.2053981423378, "count": 52 }, "Pyramids.Policy.RndReward.mean": { "value": 0.024360329406096472, "min": 0.023964540308591544, "max": 9.351730020716786, "count": 52 }, "Pyramids.Policy.RndReward.sum": { "value": 3.093761834574252, "min": 3.08454118440568, "max": 149.62768033146858, "count": 52 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 52 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 52 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1790469955", "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]", "command_line_arguments": "/usr/local/miniconda/envs/mlagents/bin/mlagents-learn /content/ml-agents/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": "2.8.0+cu128", "numpy_version": "1.23.5", "end_time_seconds": "1790473716" }, "total": 3761.398091067, "count": 1, "self": 0.4592522090001694, "children": { "run_training.setup": { "total": 0.022923066999965158, "count": 1, "self": 0.022923066999965158 }, "TrainerController.start_learning": { "total": 3760.9159157910003, "count": 1, "self": 1.9284425549435582, "children": { "TrainerController._reset_env": { "total": 3.4518364200000633, "count": 1, "self": 3.4518364200000633 }, "TrainerController.advance": { "total": 3755.3513909860562, "count": 101305, "self": 2.0638578332041106, "children": { "env_step": { "total": 2801.4038006209926, "count": 101305, "self": 2577.6385888391824, "children": { "SubprocessEnvManager._take_step": { "total": 222.5810634649638, "count": 101305, "self": 7.046059270903925, "children": { "TorchPolicy.evaluate": { "total": 215.53500419405987, "count": 98044, "self": 215.53500419405987 } } }, "workers": { "total": 1.1841483168466311, "count": 101304, "self": 0.0, "children": { "worker_root": { "total": 3751.5966338229764, "count": 101304, "is_parallel": true, "self": 1349.8627890279322, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.004818004000071596, "count": 1, "is_parallel": true, "self": 0.0035155789994405495, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013024250006310467, "count": 8, "is_parallel": true, "self": 0.0013024250006310467 } } }, "UnityEnvironment.step": { "total": 0.05150600199999644, "count": 1, "is_parallel": true, "self": 0.0006052000001091073, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005078389999653155, "count": 1, "is_parallel": true, "self": 0.0005078389999653155 }, "communicator.exchange": { "total": 0.04876108500002374, "count": 1, "is_parallel": true, "self": 0.04876108500002374 }, "steps_from_proto": { "total": 0.001631877999898279, "count": 1, "is_parallel": true, "self": 0.0003466269997716154, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012852510001266637, "count": 8, "is_parallel": true, "self": 0.0012852510001266637 } } } } } } }, "UnityEnvironment.step": { "total": 2401.733844795044, "count": 101303, "is_parallel": true, "self": 52.23696876606664, "children": { "UnityEnvironment._generate_step_input": { "total": 34.62122753802191, "count": 101303, "is_parallel": true, "self": 34.62122753802191 }, "communicator.exchange": { "total": 2149.950263898044, "count": 101303, "is_parallel": true, "self": 2149.950263898044 }, "steps_from_proto": { "total": 164.92538459291177, "count": 101303, "is_parallel": true, "self": 34.348601567288824, "children": { "_process_rank_one_or_two_observation": { "total": 130.57678302562294, "count": 810424, "is_parallel": true, "self": 130.57678302562294 } } } } } } } } } } }, "trainer_advance": { "total": 951.8837325318596, "count": 101304, "self": 3.8505665268289704, "children": { "process_trajectory": { "total": 173.1932540710327, "count": 101304, "self": 172.84371863903243, "children": { "RLTrainer._checkpoint": { "total": 0.34953543200026616, "count": 3, "self": 0.34953543200026616 } } }, "_update_policy": { "total": 774.8399119339979, "count": 721, "self": 413.7242994168921, "children": { "TorchPPOOptimizer.update": { "total": 361.1156125171058, "count": 35757, "self": 361.1156125171058 } } } } } } }, "trainer_threads": { "total": 1.4269999155658297e-06, "count": 1, "self": 1.4269999155658297e-06 }, "TrainerController._save_models": { "total": 0.1842444030007755, "count": 1, "self": 0.0015035500009616953, "children": { "RLTrainer._checkpoint": { "total": 0.1827408529998138, "count": 1, "self": 0.1827408529998138 } } } } } } }