{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.18439249694347382, "min": 0.15623076260089874, "max": 1.438191294670105, "count": 70 }, "Pyramids.Policy.Entropy.sum": { "value": 5469.81884765625, "min": 4661.92578125, "max": 43628.97265625, "count": 70 }, "Pyramids.Step.mean": { "value": 2099982.0, "min": 29952.0, "max": 2099982.0, "count": 70 }, "Pyramids.Step.sum": { "value": 2099982.0, "min": 29952.0, "max": 2099982.0, "count": 70 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.711632251739502, "min": -0.099168561398983, "max": 0.8245366215705872, "count": 70 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 209.21987915039062, "min": -23.89962387084961, "max": 249.8345947265625, "count": 70 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.004840258974581957, "min": -0.016620762646198273, "max": 0.36599379777908325, "count": 70 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 1.4230360984802246, "min": -4.670434474945068, "max": 87.83850860595703, "count": 70 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06790220571352394, "min": 0.06467182691988708, "max": 0.07316600889161864, "count": 70 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 1.0185330857028592, "min": 0.5108137817221396, "max": 1.0900373466218154, "count": 70 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.016380924475417332, "min": 0.0006232886346490559, "max": 0.01723222451012892, "count": 70 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.24571386713126, "min": 0.006856174981139615, "max": 0.24571386713126, "count": 70 }, "Pyramids.Policy.LearningRate.mean": { "value": 4.989409657650941e-06, "min": 4.989409657650941e-06, "max": 0.0002977125614093801, "count": 70 }, "Pyramids.Policy.LearningRate.sum": { "value": 7.484114486476412e-05, "min": 7.484114486476412e-05, "max": 0.003695770922793396, "count": 70 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.1016631037735849, "min": 0.1016631037735849, "max": 0.19923752021563343, "count": 70 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.5249465566037734, "min": 1.394662641509434, "max": 2.6711144811320757, "count": 70 }, "Pyramids.Policy.Beta.mean": { "value": 0.00017614406698113203, "min": 0.00017614406698113203, "max": 0.009923828269541779, "count": 70 }, "Pyramids.Policy.Beta.sum": { "value": 0.0026421610047169804, "min": 0.0026421610047169804, "max": 0.12320916613207546, "count": 70 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.008758272975683212, "min": 0.00859245378524065, "max": 0.5725786089897156, "count": 70 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.13137409090995789, "min": 0.12029435485601425, "max": 4.008050441741943, "count": 70 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 272.3482142857143, "min": 227.48507462686567, "max": 999.0, "count": 70 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30503.0, "min": 15984.0, "max": 32582.0, "count": 70 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.6754035267286596, "min": -1.0000000521540642, "max": 1.7564263418316841, "count": 70 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 189.32059852033854, "min": -31.995601639151573, "max": 235.28979843854904, "count": 70 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.6754035267286596, "min": -1.0000000521540642, "max": 1.7564263418316841, "count": 70 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 189.32059852033854, "min": -31.995601639151573, "max": 235.28979843854904, "count": 70 }, "Pyramids.Policy.RndReward.mean": { "value": 0.024742245137000216, "min": 0.021651323840115602, "max": 12.01644935272634, "count": 70 }, "Pyramids.Policy.RndReward.sum": { "value": 2.7958737004810246, "min": 2.4907763985393103, "max": 192.26318964362144, "count": 70 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 70 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 70 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1688467587", "python_version": "3.10.12 (main, Jun 7 2023, 12:45:35) [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 --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": "1688472543" }, "total": 4955.187998482999, "count": 1, "self": 0.49427580699830287, "children": { "run_training.setup": { "total": 0.040805112000043664, "count": 1, "self": 0.040805112000043664 }, "TrainerController.start_learning": { "total": 4954.652917564001, "count": 1, "self": 2.6767007728731187, "children": { "TrainerController._reset_env": { "total": 4.310329653000053, "count": 1, "self": 4.310329653000053 }, "TrainerController.advance": { "total": 4947.571646521127, "count": 137240, "self": 2.830588385165356, "children": { "env_step": { "total": 3605.0408502358705, "count": 137240, "self": 3381.735969493785, "children": { "SubprocessEnvManager._take_step": { "total": 221.686436046057, "count": 137240, "self": 9.579735433220094, "children": { "TorchPolicy.evaluate": { "total": 212.1067006128369, "count": 132553, "self": 212.1067006128369 } } }, "workers": { "total": 1.618444696028746, "count": 137240, "self": 0.0, "children": { "worker_root": { "total": 4944.231098039809, "count": 137240, "is_parallel": true, "self": 1796.1372172009073, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.004516095000099085, "count": 1, "is_parallel": true, "self": 0.0032033120005507953, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013127829995482898, "count": 8, "is_parallel": true, "self": 0.0013127829995482898 } } }, "UnityEnvironment.step": { "total": 0.04744769399985671, "count": 1, "is_parallel": true, "self": 0.0006106179998823791, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004667739999604237, "count": 1, "is_parallel": true, "self": 0.0004667739999604237 }, "communicator.exchange": { "total": 0.04446434500005125, "count": 1, "is_parallel": true, "self": 0.04446434500005125 }, "steps_from_proto": { "total": 0.0019059569999626547, "count": 1, "is_parallel": true, "self": 0.0003804600000876235, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015254969998750312, "count": 8, "is_parallel": true, "self": 0.0015254969998750312 } } } } } } }, "UnityEnvironment.step": { "total": 3148.0938808389014, "count": 137239, "is_parallel": true, "self": 70.63722457688209, "children": { "UnityEnvironment._generate_step_input": { "total": 46.992340410930865, "count": 137239, "is_parallel": true, "self": 46.992340410930865 }, "communicator.exchange": { "total": 2817.5013925040635, "count": 137239, "is_parallel": true, "self": 2817.5013925040635 }, "steps_from_proto": { "total": 212.96292334702503, "count": 137239, "is_parallel": true, "self": 41.40697616860507, "children": { "_process_rank_one_or_two_observation": { "total": 171.55594717841996, "count": 1097912, "is_parallel": true, "self": 171.55594717841996 } } } } } } } } } } }, "trainer_advance": { "total": 1339.700207900091, "count": 137240, "self": 5.497120208967999, "children": { "process_trajectory": { "total": 230.6076661561185, "count": 137240, "self": 230.20851767111822, "children": { "RLTrainer._checkpoint": { "total": 0.3991484850002962, "count": 4, "self": 0.3991484850002962 } } }, "_update_policy": { "total": 1103.5954215350046, "count": 976, "self": 705.6789926020608, "children": { "TorchPPOOptimizer.update": { "total": 397.91642893294375, "count": 48318, "self": 397.91642893294375 } } } } } } }, "trainer_threads": { "total": 9.530003808322363e-07, "count": 1, "self": 9.530003808322363e-07 }, "TrainerController._save_models": { "total": 0.09423966400026984, "count": 1, "self": 0.0014097210005274974, "children": { "RLTrainer._checkpoint": { "total": 0.09282994299974234, "count": 1, "self": 0.09282994299974234 } } } } } } }