{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.18156345188617706, "min": 0.18156345188617706, "max": 1.420688271522522, "count": 100 }, "Pyramids.Policy.Entropy.sum": { "value": 5426.568359375, "min": 5426.568359375, "max": 43098.0, "count": 100 }, "Pyramids.Step.mean": { "value": 2999955.0, "min": 29952.0, "max": 2999955.0, "count": 100 }, "Pyramids.Step.sum": { "value": 2999955.0, "min": 29952.0, "max": 2999955.0, "count": 100 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.7171305418014526, "min": -0.11616557091474533, "max": 0.7910480499267578, "count": 100 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 207.250732421875, "min": -27.99590301513672, "max": 233.3591766357422, "count": 100 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.012714924290776253, "min": -0.009530092589557171, "max": 0.3983832895755768, "count": 100 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 3.6746129989624023, "min": -2.573125123977661, "max": 94.41683959960938, "count": 100 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06995108047669332, "min": 0.06442960445669348, "max": 0.07423106411734305, "count": 100 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9793151266737065, "min": 0.48506103207165885, "max": 1.0703263379594619, "count": 100 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.014491726253514307, "min": 5.1349296002963635e-05, "max": 0.01590841563656719, "count": 100 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.2028841675492003, "min": 0.0007188901440414909, "max": 0.22652584988585053, "count": 100 }, "Pyramids.Policy.LearningRate.mean": { "value": 1.4329638080928571e-06, "min": 1.4329638080928571e-06, "max": 0.00029838354339596195, "count": 100 }, "Pyramids.Policy.LearningRate.sum": { "value": 2.00614933133e-05, "min": 2.00614933133e-05, "max": 0.003969176876941066, "count": 100 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10047762142857143, "min": 0.10047762142857143, "max": 0.19946118095238097, "count": 100 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4066867, "min": 1.3897045333333333, "max": 2.7230589333333337, "count": 100 }, "Pyramids.Policy.Beta.mean": { "value": 5.771438071428572e-05, "min": 5.771438071428572e-05, "max": 0.009946171977142856, "count": 100 }, "Pyramids.Policy.Beta.sum": { "value": 0.0008080013300000001, "min": 0.0008080013300000001, "max": 0.13231358744, "count": 100 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.004526815842837095, "min": 0.004526815842837095, "max": 0.4065634608268738, "count": 100 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.06337542086839676, "min": 0.06337542086839676, "max": 2.8459441661834717, "count": 100 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 270.2882882882883, "min": 240.48818897637796, "max": 999.0, "count": 100 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30002.0, "min": 15984.0, "max": 32343.0, "count": 100 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.675850438172216, "min": -1.0000000521540642, "max": 1.7456929679763944, "count": 100 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 186.01939863711596, "min": -32.000001668930054, "max": 219.6347985714674, "count": 100 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.675850438172216, "min": -1.0000000521540642, "max": 1.7456929679763944, "count": 100 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 186.01939863711596, "min": -32.000001668930054, "max": 219.6347985714674, "count": 100 }, "Pyramids.Policy.RndReward.mean": { "value": 0.012909823336149776, "min": 0.011652973103327751, "max": 7.9355488028377295, "count": 100 }, "Pyramids.Policy.RndReward.sum": { "value": 1.432990390312625, "min": 1.354975987553189, "max": 126.96878084540367, "count": 100 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 100 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 100 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1689622587", "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]", "command_line_arguments": "/home/alexis/anaconda3/envs/RL-atari/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": "1689631464" }, "total": 8877.449359743001, "count": 1, "self": 0.4746413360007864, "children": { "run_training.setup": { "total": 0.029111758998624282, "count": 1, "self": 0.029111758998624282 }, "TrainerController.start_learning": { "total": 8876.945606648002, "count": 1, "self": 5.570567457307334, "children": { "TrainerController._reset_env": { "total": 4.621406649999699, "count": 1, "self": 4.621406649999699 }, "TrainerController.advance": { "total": 8866.278616228694, "count": 193223, "self": 5.194533382091322, "children": { "env_step": { "total": 5556.326287993597, "count": 193223, "self": 5131.200626420556, "children": { "SubprocessEnvManager._take_step": { "total": 421.44374237989905, "count": 193223, "self": 14.83729400559605, "children": { "TorchPolicy.evaluate": { "total": 406.606448374303, "count": 187559, "self": 406.606448374303 } } }, "workers": { "total": 3.681919193142676, "count": 193223, "self": 0.0, "children": { "worker_root": { "total": 8866.851769218476, "count": 193223, "is_parallel": true, "self": 4217.809607295734, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0019441830008872785, "count": 1, "is_parallel": true, "self": 0.00046595799722126685, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014782250036660116, "count": 8, "is_parallel": true, "self": 0.0014782250036660116 } } }, "UnityEnvironment.step": { "total": 0.05015854699740885, "count": 1, "is_parallel": true, "self": 0.0005326829996192828, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0006714449991704896, "count": 1, "is_parallel": true, "self": 0.0006714449991704896 }, "communicator.exchange": { "total": 0.0471893239991914, "count": 1, "is_parallel": true, "self": 0.0471893239991914 }, "steps_from_proto": { "total": 0.0017650949994276743, "count": 1, "is_parallel": true, "self": 0.0003558939897629898, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014092010096646845, "count": 8, "is_parallel": true, "self": 0.0014092010096646845 } } } } } } }, "UnityEnvironment.step": { "total": 4649.042161922742, "count": 193222, "is_parallel": true, "self": 113.5172158035457, "children": { "UnityEnvironment._generate_step_input": { "total": 119.17327090124309, "count": 193222, "is_parallel": true, "self": 119.17327090124309 }, "communicator.exchange": { "total": 4042.7642513550527, "count": 193222, "is_parallel": true, "self": 4042.7642513550527 }, "steps_from_proto": { "total": 373.5874238629003, "count": 193222, "is_parallel": true, "self": 76.44510890575111, "children": { "_process_rank_one_or_two_observation": { "total": 297.1423149571492, "count": 1545776, "is_parallel": true, "self": 297.1423149571492 } } } } } } } } } } }, "trainer_advance": { "total": 3304.757794853005, "count": 193223, "self": 9.85492751590209, "children": { "process_trajectory": { "total": 489.0513974952846, "count": 193223, "self": 487.50266571828615, "children": { "RLTrainer._checkpoint": { "total": 1.5487317769984656, "count": 6, "self": 1.5487317769984656 } } }, "_update_policy": { "total": 2805.8514698418185, "count": 1388, "self": 1756.8892519590336, "children": { "TorchPPOOptimizer.update": { "total": 1048.962217882785, "count": 68409, "self": 1048.962217882785 } } } } } } }, "trainer_threads": { "total": 1.4700017345603555e-06, "count": 1, "self": 1.4700017345603555e-06 }, "TrainerController._save_models": { "total": 0.4750148419989273, "count": 1, "self": 0.0021603089990094304, "children": { "RLTrainer._checkpoint": { "total": 0.47285453299991786, "count": 1, "self": 0.47285453299991786 } } } } } } }