{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.3040502965450287, "min": 0.3040502965450287, "max": 1.5238757133483887, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 9204.2109375, "min": 9204.2109375, "max": 46228.29296875, "count": 33 }, "Pyramids.Step.mean": { "value": 989999.0, "min": 29952.0, "max": 989999.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989999.0, "min": 29952.0, "max": 989999.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.6490343809127808, "min": -0.11849452555179596, "max": 0.694838285446167, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 185.6238250732422, "min": -28.083202362060547, "max": 198.7237548828125, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.01583094336092472, "min": -0.007460307329893112, "max": 0.5277181267738342, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 4.527649879455566, "min": -2.05904483795166, "max": 128.23550415039062, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06594976840937132, "min": 0.06594976840937132, "max": 0.07291496922284839, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9232967577311985, "min": 0.47698796273278743, "max": 1.0354091498136806, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.014597381191422407, "min": 0.002009073983021208, "max": 0.024004689922254803, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.2043633366799137, "min": 0.024108887796254495, "max": 0.23037078973720784, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.437954663571429e-06, "min": 7.437954663571429e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010413136529, "min": 0.00010413136529, "max": 0.0037581133472956, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.1024792857142857, "min": 0.1024792857142857, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.43471, "min": 1.3886848, "max": 2.6527044, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00025768064285714283, "min": 0.00025768064285714283, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.003607529, "min": 0.003607529, "max": 0.12528516956, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.02472051791846752, "min": 0.02446679212152958, "max": 0.7727689146995544, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.346087247133255, "min": 0.3425350785255432, "max": 5.409382343292236, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 281.6090909090909, "min": 261.75892857142856, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30977.0, "min": 15984.0, "max": 32442.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.663827256384221, "min": -1.0000000521540642, "max": 1.6971788331866264, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 183.0209982022643, "min": -26.387801706790924, "max": 188.68119774758816, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.663827256384221, "min": -1.0000000521540642, "max": 1.6971788331866264, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 183.0209982022643, "min": -26.387801706790924, "max": 188.68119774758816, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.07273127073673426, "min": 0.06641569905280319, "max": 18.795794791541994, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 8.000439781040768, "min": 7.42138241698558, "max": 300.7327166646719, "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": "1701769796", "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": "1701772155" }, "total": 2359.695567042, "count": 1, "self": 0.47719057700032863, "children": { "run_training.setup": { "total": 0.05324767000001884, "count": 1, "self": 0.05324767000001884 }, "TrainerController.start_learning": { "total": 2359.165128795, "count": 1, "self": 1.4202763770658748, "children": { "TrainerController._reset_env": { "total": 2.971896135999941, "count": 1, "self": 2.971896135999941 }, "TrainerController.advance": { "total": 2354.6915404979336, "count": 64355, "self": 1.4892048119850188, "children": { "env_step": { "total": 1704.739517578007, "count": 64355, "self": 1568.3357887530515, "children": { "SubprocessEnvManager._take_step": { "total": 135.50969235690673, "count": 64355, "self": 4.90882982903122, "children": { "TorchPolicy.evaluate": { "total": 130.6008625278755, "count": 62561, "self": 130.6008625278755 } } }, "workers": { "total": 0.8940364680488528, "count": 64355, "self": 0.0, "children": { "worker_root": { "total": 2354.2044920548988, "count": 64355, "is_parallel": true, "self": 909.1266494489196, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.002048278000074788, "count": 1, "is_parallel": true, "self": 0.0006945780000933155, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013536999999814725, "count": 8, "is_parallel": true, "self": 0.0013536999999814725 } } }, "UnityEnvironment.step": { "total": 0.04974188899996079, "count": 1, "is_parallel": true, "self": 0.0005939019997640571, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005034830001022783, "count": 1, "is_parallel": true, "self": 0.0005034830001022783 }, "communicator.exchange": { "total": 0.04703579899978649, "count": 1, "is_parallel": true, "self": 0.04703579899978649 }, "steps_from_proto": { "total": 0.001608705000307964, "count": 1, "is_parallel": true, "self": 0.00034465100043235, "children": { "_process_rank_one_or_two_observation": { "total": 0.001264053999875614, "count": 8, "is_parallel": true, "self": 0.001264053999875614 } } } } } } }, "UnityEnvironment.step": { "total": 1445.0778426059792, "count": 64354, "is_parallel": true, "self": 34.53491042501082, "children": { "UnityEnvironment._generate_step_input": { "total": 25.40044706404342, "count": 64354, "is_parallel": true, "self": 25.40044706404342 }, "communicator.exchange": { "total": 1283.7025921369323, "count": 64354, "is_parallel": true, "self": 1283.7025921369323 }, "steps_from_proto": { "total": 101.43989297999269, "count": 64354, "is_parallel": true, "self": 20.75934694008629, "children": { "_process_rank_one_or_two_observation": { "total": 80.6805460399064, "count": 514832, "is_parallel": true, "self": 80.6805460399064 } } } } } } } } } } }, "trainer_advance": { "total": 648.4628181079415, "count": 64355, "self": 2.8842963139659332, "children": { "process_trajectory": { "total": 133.88539435397206, "count": 64355, "self": 133.60391198997195, "children": { "RLTrainer._checkpoint": { "total": 0.2814823640001123, "count": 2, "self": 0.2814823640001123 } } }, "_update_policy": { "total": 511.69312744000354, "count": 458, "self": 305.67145984404397, "children": { "TorchPPOOptimizer.update": { "total": 206.02166759595957, "count": 22788, "self": 206.02166759595957 } } } } } } }, "trainer_threads": { "total": 1.1060001270379871e-06, "count": 1, "self": 1.1060001270379871e-06 }, "TrainerController._save_models": { "total": 0.08141467800032842, "count": 1, "self": 0.0013614460003736895, "children": { "RLTrainer._checkpoint": { "total": 0.08005323199995473, "count": 1, "self": 0.08005323199995473 } } } } } } }