{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.5407678484916687, "min": 0.5407678484916687, "max": 1.4623218774795532, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 16024.0322265625, "min": 16024.0322265625, "max": 44360.99609375, "count": 33 }, "Pyramids.Step.mean": { "value": 989890.0, "min": 29952.0, "max": 989890.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989890.0, "min": 29952.0, "max": 989890.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.503671407699585, "min": -0.10175586491823196, "max": 0.5733243227005005, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 137.50228881835938, "min": -24.726675033569336, "max": 158.23751831054688, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.024476993829011917, "min": -0.23295113444328308, "max": 0.3963066041469574, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 6.682219505310059, "min": -61.26614761352539, "max": 93.92466735839844, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.0724736359247583, "min": 0.06483398421689691, "max": 0.07342556430880316, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 1.0146309029466163, "min": 0.49362125625815795, "max": 1.0838274830117978, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.014799059452863212, "min": 8.526768997569097e-05, "max": 0.017005501146195458, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.20718683234008498, "min": 0.0011937476596596737, "max": 0.25508251719293185, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.418604670021428e-06, "min": 7.418604670021428e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.0001038604653803, "min": 0.0001038604653803, "max": 0.003505248231584, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10247283571428575, "min": 0.10247283571428575, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4346197000000005, "min": 1.3691136000000002, "max": 2.568416, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00025703628785714284, "min": 0.00025703628785714284, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0035985080299999997, "min": 0.0035985080299999997, "max": 0.1168647584, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.008443105034530163, "min": 0.008443105034530163, "max": 0.42193976044654846, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.11820347607135773, "min": 0.11820347607135773, "max": 2.953578233718872, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 380.987012987013, "min": 329.25274725274727, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29336.0, "min": 15984.0, "max": 32652.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.4631376487094085, "min": -1.0000000521540642, "max": 1.6460577524370616, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 112.66159895062447, "min": -32.000001668930054, "max": 148.14519771933556, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.4631376487094085, "min": -1.0000000521540642, "max": 1.6460577524370616, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 112.66159895062447, "min": -32.000001668930054, "max": 148.14519771933556, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.03328385552113223, "min": 0.030734434690303816, "max": 8.5698985401541, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 2.5628568751271814, "min": 2.5628568751271814, "max": 137.1183766424656, "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": "1728152304", "python_version": "3.10.12 (main, Sep 11 2024, 15:47:36) [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": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.4.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1728155667" }, "total": 3363.203998131, "count": 1, "self": 1.0263237119997939, "children": { "run_training.setup": { "total": 0.13654329300015888, "count": 1, "self": 0.13654329300015888 }, "TrainerController.start_learning": { "total": 3362.041131126, "count": 1, "self": 2.2724594359974617, "children": { "TrainerController._reset_env": { "total": 4.304678932999877, "count": 1, "self": 4.304678932999877 }, "TrainerController.advance": { "total": 3355.365311287003, "count": 63737, "self": 2.6751873471212093, "children": { "env_step": { "total": 2189.66683478899, "count": 63737, "self": 2015.2593802531205, "children": { "SubprocessEnvManager._take_step": { "total": 172.95193703896825, "count": 63737, "self": 7.6877488959742095, "children": { "TorchPolicy.evaluate": { "total": 165.26418814299404, "count": 62573, "self": 165.26418814299404 } } }, "workers": { "total": 1.455517496901166, "count": 63737, "self": 0.0, "children": { "worker_root": { "total": 3354.4901359989726, "count": 63737, "is_parallel": true, "self": 1533.6672468509812, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.002672122999911153, "count": 1, "is_parallel": true, "self": 0.000864783999759311, "children": { "_process_rank_one_or_two_observation": { "total": 0.001807339000151842, "count": 8, "is_parallel": true, "self": 0.001807339000151842 } } }, "UnityEnvironment.step": { "total": 0.09196317099986118, "count": 1, "is_parallel": true, "self": 0.0033734350001850544, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005936099998962163, "count": 1, "is_parallel": true, "self": 0.0005936099998962163 }, "communicator.exchange": { "total": 0.08572852999986935, "count": 1, "is_parallel": true, "self": 0.08572852999986935 }, "steps_from_proto": { "total": 0.0022675959999105544, "count": 1, "is_parallel": true, "self": 0.0005178000001251348, "children": { "_process_rank_one_or_two_observation": { "total": 0.0017497959997854196, "count": 8, "is_parallel": true, "self": 0.0017497959997854196 } } } } } } }, "UnityEnvironment.step": { "total": 1820.8228891479914, "count": 63736, "is_parallel": true, "self": 52.39772183494438, "children": { "UnityEnvironment._generate_step_input": { "total": 30.95655688103011, "count": 63736, "is_parallel": true, "self": 30.95655688103011 }, "communicator.exchange": { "total": 1604.6491993810014, "count": 63736, "is_parallel": true, "self": 1604.6491993810014 }, "steps_from_proto": { "total": 132.81941105101555, "count": 63736, "is_parallel": true, "self": 28.75444018814369, "children": { "_process_rank_one_or_two_observation": { "total": 104.06497086287186, "count": 509888, "is_parallel": true, "self": 104.06497086287186 } } } } } } } } } } }, "trainer_advance": { "total": 1163.0232891508917, "count": 63737, "self": 4.66205958491696, "children": { "process_trajectory": { "total": 174.85832384197738, "count": 63737, "self": 174.6094879619768, "children": { "RLTrainer._checkpoint": { "total": 0.2488358800005699, "count": 2, "self": 0.2488358800005699 } } }, "_update_policy": { "total": 983.5029057239974, "count": 448, "self": 393.25808448401494, "children": { "TorchPPOOptimizer.update": { "total": 590.2448212399825, "count": 22845, "self": 590.2448212399825 } } } } } } }, "trainer_threads": { "total": 1.6429994502686895e-06, "count": 1, "self": 1.6429994502686895e-06 }, "TrainerController._save_models": { "total": 0.0986798270005238, "count": 1, "self": 0.004116694000003918, "children": { "RLTrainer._checkpoint": { "total": 0.09456313300051988, "count": 1, "self": 0.09456313300051988 } } } } } } }