{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.331845223903656, "min": 0.3223000168800354, "max": 1.4673115015029907, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 9827.927734375, "min": 9679.314453125, "max": 44512.36328125, "count": 33 }, "Pyramids.Step.mean": { "value": 989912.0, "min": 29952.0, "max": 989912.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989912.0, "min": 29952.0, "max": 989912.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.7736473679542542, "min": -0.08461209386587143, "max": 0.7736473679542542, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 230.5469207763672, "min": -20.39151382446289, "max": 230.5469207763672, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -0.003178016049787402, "min": -0.023423412814736366, "max": 0.2531691789627075, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -0.9470487833023071, "min": -6.956753730773926, "max": 61.01377487182617, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.07206878411359087, "min": 0.06574794774323457, "max": 0.07477334491786047, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 1.0089629775902722, "min": 0.5058581718949845, "max": 1.0463636762305053, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.015180644784344449, "min": 0.0007433808066167112, "max": 0.01687183386994071, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.2125290269808223, "min": 0.006690427259550401, "max": 0.23620567417916993, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.52810463352143e-06, "min": 7.52810463352143e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010539346486930002, "min": 0.00010539346486930002, "max": 0.0035073215308928994, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.1025093357142857, "min": 0.1025093357142857, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4351306999999998, "min": 1.3886848, "max": 2.5691071000000005, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00026068263785714295, "min": 0.00026068263785714295, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.003649556930000001, "min": 0.003649556930000001, "max": 0.11693379929000002, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.009338201023638248, "min": 0.009338201023638248, "max": 0.414471298456192, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.13073481619358063, "min": 0.13073481619358063, "max": 2.901298999786377, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 259.1140350877193, "min": 243.99193548387098, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29539.0, "min": 15984.0, "max": 32660.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.7057912123569272, "min": -1.0000000521540642, "max": 1.7515759828090667, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 194.4601982086897, "min": -29.932001672685146, "max": 218.94699785113335, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.7057912123569272, "min": -1.0000000521540642, "max": 1.7515759828090667, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 194.4601982086897, "min": -29.932001672685146, "max": 218.94699785113335, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.02503391235644047, "min": 0.024924523378373125, "max": 8.082937270402908, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 2.8538660086342134, "min": 2.8538660086342134, "max": 129.32699632644653, "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": "1778499289", "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]", "command_line_arguments": "/home/jnforja/rl-study/snowballtarget-mlagents/.conda/envs/snowballtarget/bin/mlagents-learn ./config/ppo/PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=PyramidsTraining --no-graphics --torch-device=cuda:0", "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": "1778499936" }, "total": 646.5179483689999, "count": 1, "self": 0.16666633900058514, "children": { "run_training.setup": { "total": 0.008726637999643572, "count": 1, "self": 0.008726637999643572 }, "TrainerController.start_learning": { "total": 646.3425553919997, "count": 1, "self": 0.45686317597073867, "children": { "TrainerController._reset_env": { "total": 0.8798847580001166, "count": 1, "self": 0.8798847580001166 }, "TrainerController.advance": { "total": 644.9820132290288, "count": 64304, "self": 0.42346517391024463, "children": { "env_step": { "total": 446.1734713760593, "count": 64304, "self": 401.74157748706375, "children": { "SubprocessEnvManager._take_step": { "total": 44.132685786963066, "count": 64304, "self": 1.4446606558854, "children": { "TorchPolicy.evaluate": { "total": 42.688025131077666, "count": 62565, "self": 42.688025131077666 } } }, "workers": { "total": 0.2992081020324804, "count": 64304, "self": 0.0, "children": { "worker_root": { "total": 645.6849024569469, "count": 64304, "is_parallel": true, "self": 274.4424321319884, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0006001100000503357, "count": 1, "is_parallel": true, "self": 0.00019040600045627798, "children": { "_process_rank_one_or_two_observation": { "total": 0.0004097039995940577, "count": 8, "is_parallel": true, "self": 0.0004097039995940577 } } }, "UnityEnvironment.step": { "total": 0.015857291999964218, "count": 1, "is_parallel": true, "self": 0.00012799299975085887, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00015862800000832067, "count": 1, "is_parallel": true, "self": 0.00015862800000832067 }, "communicator.exchange": { "total": 0.015182578999883845, "count": 1, "is_parallel": true, "self": 0.015182578999883845 }, "steps_from_proto": { "total": 0.00038809200032119406, "count": 1, "is_parallel": true, "self": 0.00010553800075285835, "children": { "_process_rank_one_or_two_observation": { "total": 0.0002825539995683357, "count": 8, "is_parallel": true, "self": 0.0002825539995683357 } } } } } } }, "UnityEnvironment.step": { "total": 371.2424703249585, "count": 64303, "is_parallel": true, "self": 6.288384951980788, "children": { "UnityEnvironment._generate_step_input": { "total": 4.4210258330108445, "count": 64303, "is_parallel": true, "self": 4.4210258330108445 }, "communicator.exchange": { "total": 343.6721177369959, "count": 64303, "is_parallel": true, "self": 343.6721177369959 }, "steps_from_proto": { "total": 16.860941802970956, "count": 64303, "is_parallel": true, "self": 3.752052638116311, "children": { "_process_rank_one_or_two_observation": { "total": 13.108889164854645, "count": 514424, "is_parallel": true, "self": 13.108889164854645 } } } } } } } } } } }, "trainer_advance": { "total": 198.38507667905924, "count": 64304, "self": 0.910179950048132, "children": { "process_trajectory": { "total": 44.63618490100953, "count": 64304, "self": 44.572340883009474, "children": { "RLTrainer._checkpoint": { "total": 0.06384401800005435, "count": 2, "self": 0.06384401800005435 } } }, "_update_policy": { "total": 152.83871182800158, "count": 449, "self": 89.01945516499973, "children": { "TorchPPOOptimizer.update": { "total": 63.81925666300185, "count": 22854, "self": 63.81925666300185 } } } } } } }, "trainer_threads": { "total": 5.609999789157882e-07, "count": 1, "self": 5.609999789157882e-07 }, "TrainerController._save_models": { "total": 0.023793668000053003, "count": 1, "self": 0.0005184970000300382, "children": { "RLTrainer._checkpoint": { "total": 0.023275171000022965, "count": 1, "self": 0.023275171000022965 } } } } } } }