{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.39301010966300964, "min": 0.39301010966300964, "max": 1.5046640634536743, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 11859.47265625, "min": 11856.771484375, "max": 45645.48828125, "count": 33 }, "Pyramids.Step.mean": { "value": 989973.0, "min": 29952.0, "max": 989973.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989973.0, "min": 29952.0, "max": 989973.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.6040273308753967, "min": -0.111550472676754, "max": 0.6143184900283813, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 171.54376220703125, "min": -26.772113800048828, "max": 171.54376220703125, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.2209559977054596, "min": -0.014017833396792412, "max": 0.2209559977054596, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 62.751502990722656, "min": -3.9670467376708984, "max": 62.751502990722656, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.0656839498323297, "min": 0.06342327179542433, "max": 0.07308980692288883, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9195752976526158, "min": 0.4921397646262187, "max": 1.0597024646304622, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.020094824160422468, "min": 0.0012329866016977148, "max": 0.020094824160422468, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.28132753824591455, "min": 0.013570270437174018, "max": 0.28132753824591455, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.5492760550357125e-06, "min": 7.5492760550357125e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010568986477049997, "min": 0.00010568986477049997, "max": 0.003634389188536999, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10251639285714285, "min": 0.10251639285714285, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4352295, "min": 1.3886848, "max": 2.6114630000000005, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002613876464285714, "min": 0.0002613876464285714, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0036594270499999996, "min": 0.0036594270499999996, "max": 0.1211651537, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.00968067068606615, "min": 0.00968067068606615, "max": 0.33414989709854126, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.13552938401699066, "min": 0.13552938401699066, "max": 2.3390493392944336, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 318.95959595959596, "min": 291.32608695652175, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 31577.0, "min": 15984.0, "max": 33740.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.620414123917469, "min": -1.0000000521540642, "max": 1.6787868958210277, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 160.42099826782942, "min": -29.88700173050165, "max": 179.63019785284996, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.620414123917469, "min": -1.0000000521540642, "max": 1.6787868958210277, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 160.42099826782942, "min": -29.88700173050165, "max": 179.63019785284996, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.031773945499526696, "min": 0.030495066803743375, "max": 6.623169501312077, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.1456206044531427, "min": 2.8055461459443904, "max": 105.97071202099323, "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": "1684396922", "python_version": "3.10.11 (main, Apr 5 2023, 14:15:10) [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": "0.31.0.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": "1684399374" }, "total": 2451.4251874379997, "count": 1, "self": 0.5273599069996635, "children": { "run_training.setup": { "total": 0.06677513299996463, "count": 1, "self": 0.06677513299996463 }, "TrainerController.start_learning": { "total": 2450.831052398, "count": 1, "self": 1.5669531019439091, "children": { "TrainerController._reset_env": { "total": 3.966861233000145, "count": 1, "self": 3.966861233000145 }, "TrainerController.advance": { "total": 2445.198272503056, "count": 64034, "self": 1.5454853840396936, "children": { "env_step": { "total": 1758.1466986279875, "count": 64034, "self": 1634.7866547479514, "children": { "SubprocessEnvManager._take_step": { "total": 122.45518504399547, "count": 64034, "self": 5.349831991963356, "children": { "TorchPolicy.evaluate": { "total": 117.10535305203211, "count": 62558, "self": 117.10535305203211 } } }, "workers": { "total": 0.9048588360406029, "count": 64034, "self": 0.0, "children": { "worker_root": { "total": 2445.036911239989, "count": 64034, "is_parallel": true, "self": 937.8822066350615, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0019188820001545537, "count": 1, "is_parallel": true, "self": 0.0007081440001002193, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012107380000543344, "count": 8, "is_parallel": true, "self": 0.0012107380000543344 } } }, "UnityEnvironment.step": { "total": 0.05496671600008085, "count": 1, "is_parallel": true, "self": 0.0005948910002189223, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005151719999503257, "count": 1, "is_parallel": true, "self": 0.0005151719999503257 }, "communicator.exchange": { "total": 0.05176968599994325, "count": 1, "is_parallel": true, "self": 0.05176968599994325 }, "steps_from_proto": { "total": 0.0020869669999683538, "count": 1, "is_parallel": true, "self": 0.0004065699999955541, "children": { "_process_rank_one_or_two_observation": { "total": 0.0016803969999727997, "count": 8, "is_parallel": true, "self": 0.0016803969999727997 } } } } } } }, "UnityEnvironment.step": { "total": 1507.1547046049275, "count": 64033, "is_parallel": true, "self": 34.36487856491635, "children": { "UnityEnvironment._generate_step_input": { "total": 26.374296453012448, "count": 64033, "is_parallel": true, "self": 26.374296453012448 }, "communicator.exchange": { "total": 1332.3132251160043, "count": 64033, "is_parallel": true, "self": 1332.3132251160043 }, "steps_from_proto": { "total": 114.10230447099434, "count": 64033, "is_parallel": true, "self": 23.646980152057495, "children": { "_process_rank_one_or_two_observation": { "total": 90.45532431893685, "count": 512264, "is_parallel": true, "self": 90.45532431893685 } } } } } } } } } } }, "trainer_advance": { "total": 685.5060884910292, "count": 64034, "self": 2.8950839530500616, "children": { "process_trajectory": { "total": 122.69821889197988, "count": 64034, "self": 122.39493756798015, "children": { "RLTrainer._checkpoint": { "total": 0.30328132399972674, "count": 2, "self": 0.30328132399972674 } } }, "_update_policy": { "total": 559.9127856459993, "count": 455, "self": 359.8703015469939, "children": { "TorchPPOOptimizer.update": { "total": 200.04248409900538, "count": 22815, "self": 200.04248409900538 } } } } } } }, "trainer_threads": { "total": 1.2310001693549566e-06, "count": 1, "self": 1.2310001693549566e-06 }, "TrainerController._save_models": { "total": 0.09896432899950014, "count": 1, "self": 0.0014632869997512898, "children": { "RLTrainer._checkpoint": { "total": 0.09750104199974885, "count": 1, "self": 0.09750104199974885 } } } } } } }