{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.5188078284263611, "min": 0.5188078284263611, "max": 1.481709361076355, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 15456.322265625, "min": 15456.322265625, "max": 44949.13671875, "count": 33 }, "Pyramids.Step.mean": { "value": 989980.0, "min": 29952.0, "max": 989980.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989980.0, "min": 29952.0, "max": 989980.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.5255312323570251, "min": -0.08148352801799774, "max": 0.565100908279419, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 144.52108764648438, "min": -19.719013214111328, "max": 157.66314697265625, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.016344405710697174, "min": 7.240166451083496e-05, "max": 0.17884252965450287, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 4.494711399078369, "min": 0.018245220184326172, "max": 43.27989196777344, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06842539946002271, "min": 0.06554764527759022, "max": 0.07381394984705184, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9579555924403179, "min": 0.48135303283088854, "max": 1.0238266342300146, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.012910056734687184, "min": 0.001606441897504447, "max": 0.01652961334946754, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.18074079428562057, "min": 0.020674617265688627, "max": 0.23141458689254557, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.714897428400001e-06, "min": 7.714897428400001e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.0001080085639976, "min": 0.0001080085639976, "max": 0.0036337783887406, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.1025716, "min": 0.1025716, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4360024, "min": 1.3886848, "max": 2.6112594000000002, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00026690284, "min": 0.00026690284, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0037366397600000004, "min": 0.0037366397600000004, "max": 0.12114481406000001, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.008420458063483238, "min": 0.008113379590213299, "max": 0.3145770728588104, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.11788640916347504, "min": 0.11358731985092163, "max": 2.2020394802093506, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 361.50602409638554, "min": 332.03333333333336, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30005.0, "min": 15984.0, "max": 33080.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.6129333085957027, "min": -1.0000000521540642, "max": 1.6448066481285626, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 135.48639792203903, "min": -29.111601658165455, "max": 148.03259833157063, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.6129333085957027, "min": -1.0000000521540642, "max": 1.6448066481285626, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 135.48639792203903, "min": -29.111601658165455, "max": 148.03259833157063, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.032033900821954286, "min": 0.02814182160703543, "max": 6.246562073007226, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 2.6908476690441603, "min": 2.493558108821162, "max": 99.94499316811562, "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": "1702464114", "python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [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": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.1.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1702466535" }, "total": 2421.38857725, "count": 1, "self": 0.7614029539990952, "children": { "run_training.setup": { "total": 0.05335162200026389, "count": 1, "self": 0.05335162200026389 }, "TrainerController.start_learning": { "total": 2420.5738226740004, "count": 1, "self": 1.5695702259899917, "children": { "TrainerController._reset_env": { "total": 3.1378248109995184, "count": 1, "self": 3.1378248109995184 }, "TrainerController.advance": { "total": 2415.7347364080115, "count": 63872, "self": 1.7800153700600276, "children": { "env_step": { "total": 1751.0125462969136, "count": 63872, "self": 1607.6097715629548, "children": { "SubprocessEnvManager._take_step": { "total": 142.41690136204488, "count": 63872, "self": 5.102496938902732, "children": { "TorchPolicy.evaluate": { "total": 137.31440442314215, "count": 62562, "self": 137.31440442314215 } } }, "workers": { "total": 0.98587337191384, "count": 63872, "self": 0.0, "children": { "worker_root": { "total": 2415.3826118009565, "count": 63872, "is_parallel": true, "self": 937.2579803409144, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0021170230002098833, "count": 1, "is_parallel": true, "self": 0.0006555669997396762, "children": { "_process_rank_one_or_two_observation": { "total": 0.001461456000470207, "count": 8, "is_parallel": true, "self": 0.001461456000470207 } } }, "UnityEnvironment.step": { "total": 0.04618839700015087, "count": 1, "is_parallel": true, "self": 0.0005622170001515769, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00046159599969541887, "count": 1, "is_parallel": true, "self": 0.00046159599969541887 }, "communicator.exchange": { "total": 0.04354872699968837, "count": 1, "is_parallel": true, "self": 0.04354872699968837 }, "steps_from_proto": { "total": 0.001615857000615506, "count": 1, "is_parallel": true, "self": 0.00034699800198723096, "children": { "_process_rank_one_or_two_observation": { "total": 0.001268858998628275, "count": 8, "is_parallel": true, "self": 0.001268858998628275 } } } } } } }, "UnityEnvironment.step": { "total": 1478.124631460042, "count": 63871, "is_parallel": true, "self": 35.619583644023805, "children": { "UnityEnvironment._generate_step_input": { "total": 24.637985143942387, "count": 63871, "is_parallel": true, "self": 24.637985143942387 }, "communicator.exchange": { "total": 1317.0922777539663, "count": 63871, "is_parallel": true, "self": 1317.0922777539663 }, "steps_from_proto": { "total": 100.77478491810962, "count": 63871, "is_parallel": true, "self": 20.60371004942772, "children": { "_process_rank_one_or_two_observation": { "total": 80.1710748686819, "count": 510968, "is_parallel": true, "self": 80.1710748686819 } } } } } } } } } } }, "trainer_advance": { "total": 662.9421747410379, "count": 63872, "self": 3.183706624939987, "children": { "process_trajectory": { "total": 135.2390778691024, "count": 63872, "self": 135.01634767310134, "children": { "RLTrainer._checkpoint": { "total": 0.22273019600106636, "count": 2, "self": 0.22273019600106636 } } }, "_update_policy": { "total": 524.5193902469955, "count": 455, "self": 312.2324619079409, "children": { "TorchPPOOptimizer.update": { "total": 212.2869283390546, "count": 22752, "self": 212.2869283390546 } } } } } } }, "trainer_threads": { "total": 1.7329994079773314e-06, "count": 1, "self": 1.7329994079773314e-06 }, "TrainerController._save_models": { "total": 0.13168949600003543, "count": 1, "self": 0.002195453000240377, "children": { "RLTrainer._checkpoint": { "total": 0.12949404299979506, "count": 1, "self": 0.12949404299979506 } } } } } } }