{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.4871171712875366, "min": 0.4871171712875366, "max": 1.4056684970855713, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 14683.66015625, "min": 14683.66015625, "max": 42642.359375, "count": 33 }, "Pyramids.Step.mean": { "value": 989991.0, "min": 29952.0, "max": 989991.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989991.0, "min": 29952.0, "max": 989991.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.50260990858078, "min": -0.09626083821058273, "max": 0.5178943276405334, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 137.21250915527344, "min": -23.198862075805664, "max": 140.349365234375, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -0.02941048890352249, "min": -0.02941048890352249, "max": 0.31740519404411316, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -8.02906322479248, "min": -8.02906322479248, "max": 76.4946517944336, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.07002971045375388, "min": 0.06399952096097283, "max": 0.07546017403322103, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 1.050445656806308, "min": 0.5282212182325472, "max": 1.050445656806308, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.016233284478463856, "min": 0.00010467113523033659, "max": 0.016738079448901665, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.24349926717695783, "min": 0.0014653958932247123, "max": 0.24349926717695783, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.499857500079997e-06, "min": 7.499857500079997e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00011249786250119995, "min": 0.00011249786250119995, "max": 0.0036333934888688997, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10249992000000001, "min": 0.10249992000000001, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.5374988, "min": 1.3886848, "max": 2.6111310999999997, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00025974200799999995, "min": 0.00025974200799999995, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.003896130119999999, "min": 0.003896130119999999, "max": 0.12113199689, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.016349447891116142, "min": 0.016348913311958313, "max": 0.5291975736618042, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.24524171650409698, "min": 0.22888478636741638, "max": 3.704383134841919, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 343.8414634146341, "min": 343.8414634146341, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 28195.0, "min": 15984.0, "max": 32863.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.6073658293703708, "min": -1.0000000521540642, "max": 1.6073658293703708, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 131.8039980083704, "min": -31.998401671648026, "max": 131.8039980083704, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.6073658293703708, "min": -1.0000000521540642, "max": 1.6073658293703708, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 131.8039980083704, "min": -31.998401671648026, "max": 131.8039980083704, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.058103720209612394, "min": 0.05808856563449063, "max": 10.237157061696053, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 4.764505057188217, "min": 4.764505057188217, "max": 163.79451298713684, "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": "1787334393", "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]", "command_line_arguments": "/content/miniconda/envs/mlagents_env/bin/mlagents-learn ./config/ppo/PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids Training --no-graphics", "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": "1787338092" }, "total": 3698.9877712899997, "count": 1, "self": 1.5414472109996495, "children": { "run_training.setup": { "total": 0.03157433099977425, "count": 1, "self": 0.03157433099977425 }, "TrainerController.start_learning": { "total": 3697.4147497480003, "count": 1, "self": 2.0453070439298244, "children": { "TrainerController._reset_env": { "total": 2.722835991000011, "count": 1, "self": 2.722835991000011 }, "TrainerController.advance": { "total": 3692.5214831680705, "count": 63671, "self": 2.111212104027345, "children": { "env_step": { "total": 2659.747510483048, "count": 63671, "self": 2508.0272211541364, "children": { "SubprocessEnvManager._take_step": { "total": 150.30911013396917, "count": 63671, "self": 6.305778207922231, "children": { "TorchPolicy.evaluate": { "total": 144.00333192604694, "count": 62545, "self": 144.00333192604694 } } }, "workers": { "total": 1.4111791949421786, "count": 63671, "self": 0.0, "children": { "worker_root": { "total": 3689.802222620178, "count": 63671, "is_parallel": true, "self": 1357.3714682571713, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0030219750001378998, "count": 1, "is_parallel": true, "self": 0.001074918000085745, "children": { "_process_rank_one_or_two_observation": { "total": 0.0019470570000521548, "count": 8, "is_parallel": true, "self": 0.0019470570000521548 } } }, "UnityEnvironment.step": { "total": 0.06591223800023727, "count": 1, "is_parallel": true, "self": 0.0007534200003647129, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0006303039999693283, "count": 1, "is_parallel": true, "self": 0.0006303039999693283 }, "communicator.exchange": { "total": 0.06240051099985067, "count": 1, "is_parallel": true, "self": 0.06240051099985067 }, "steps_from_proto": { "total": 0.0021280030000525585, "count": 1, "is_parallel": true, "self": 0.0004346710002209875, "children": { "_process_rank_one_or_two_observation": { "total": 0.001693331999831571, "count": 8, "is_parallel": true, "self": 0.001693331999831571 } } } } } } }, "UnityEnvironment.step": { "total": 2332.4307543630066, "count": 63670, "is_parallel": true, "self": 51.18549284704022, "children": { "UnityEnvironment._generate_step_input": { "total": 33.177917775022706, "count": 63670, "is_parallel": true, "self": 33.177917775022706 }, "communicator.exchange": { "total": 2094.482936297872, "count": 63670, "is_parallel": true, "self": 2094.482936297872 }, "steps_from_proto": { "total": 153.58440744307154, "count": 63670, "is_parallel": true, "self": 31.129339534071278, "children": { "_process_rank_one_or_two_observation": { "total": 122.45506790900026, "count": 509360, "is_parallel": true, "self": 122.45506790900026 } } } } } } } } } } }, "trainer_advance": { "total": 1030.6627605809954, "count": 63671, "self": 3.6288916258349673, "children": { "process_trajectory": { "total": 142.8898040831691, "count": 63671, "self": 142.57889675716888, "children": { "RLTrainer._checkpoint": { "total": 0.3109073260002333, "count": 2, "self": 0.3109073260002333 } } }, "_update_policy": { "total": 884.1440648719913, "count": 453, "self": 352.72743449110976, "children": { "TorchPPOOptimizer.update": { "total": 531.4166303808815, "count": 22767, "self": 531.4166303808815 } } } } } } }, "trainer_threads": { "total": 1.6430003597633913e-06, "count": 1, "self": 1.6430003597633913e-06 }, "TrainerController._save_models": { "total": 0.1251219019995915, "count": 1, "self": 0.0027625719994830433, "children": { "RLTrainer._checkpoint": { "total": 0.12235933000010846, "count": 1, "self": 0.12235933000010846 } } } } } } }