{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.2955581843852997, "min": 0.2747502326965332, "max": 1.6005821228027344, "count": 100 }, "Pyramids.Policy.Entropy.sum": { "value": 2998.14208984375, "min": 2798.183349609375, "max": 16389.9609375, "count": 100 }, "Pyramids.Step.mean": { "value": 999951.0, "min": 9984.0, "max": 999951.0, "count": 100 }, "Pyramids.Step.sum": { "value": 999951.0, "min": 9984.0, "max": 999951.0, "count": 100 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.6654378175735474, "min": -0.1540381908416748, "max": 0.7813151478767395, "count": 100 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 64.54747009277344, "min": -12.477093696594238, "max": 76.56888580322266, "count": 100 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.005953073501586914, "min": -0.09729652851819992, "max": 0.30549734830856323, "count": 100 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 0.5774481296539307, "min": -9.048577308654785, "max": 24.745285034179688, "count": 100 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.07172110477404203, "min": 0.0586659834586808, "max": 0.07878304312765193, "count": 100 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.28688441909616813, "min": 0.1337058456556406, "max": 0.39127714224741794, "count": 100 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.014707582364887156, "min": 0.00019025595812889747, "max": 0.019858406014585248, "count": 100 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.05883032945954862, "min": 0.0007610238325155899, "max": 0.09929203007292624, "count": 100 }, "Pyramids.Policy.LearningRate.mean": { "value": 1.4835995054999933e-06, "min": 1.4835995054999933e-06, "max": 0.0002981568006144, "count": 100 }, "Pyramids.Policy.LearningRate.sum": { "value": 5.934398021999973e-06, "min": 5.934398021999973e-06, "max": 0.0012819978726674, "count": 100 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.1004945, "min": 0.1004945, "max": 0.1993856, "count": 100 }, "Pyramids.Policy.Epsilon.sum": { "value": 0.401978, "min": 0.39717119999999995, "max": 0.9273326000000001, "count": 100 }, "Pyramids.Policy.Beta.mean": { "value": 5.940054999999979e-05, "min": 5.940054999999979e-05, "max": 0.00993862144, "count": 100 }, "Pyramids.Policy.Beta.sum": { "value": 0.00023760219999999915, "min": 0.00023760219999999915, "max": 0.04274052674, "count": 100 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.010158480145037174, "min": 0.010158480145037174, "max": 0.6577078700065613, "count": 100 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.0406339205801487, "min": 0.0406339205801487, "max": 1.3154157400131226, "count": 100 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 100 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 100 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 257.2631578947368, "min": 222.47826086956522, "max": 999.0, "count": 99 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 9776.0, "min": 603.0, "max": 15984.0, "count": 99 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.637436831271962, "min": -1.0000000521540642, "max": 1.7800888799958758, "count": 99 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 62.22259958833456, "min": -16.000000834465027, "max": 80.10399959981441, "count": 99 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.637436831271962, "min": -1.0000000521540642, "max": 1.7800888799958758, "count": 99 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 62.22259958833456, "min": -16.000000834465027, "max": 80.10399959981441, "count": 99 }, "Pyramids.Policy.RndReward.mean": { "value": 0.02774641904933991, "min": 0.023877781706525842, "max": 7.177274631336331, "count": 99 }, "Pyramids.Policy.RndReward.sum": { "value": 1.0543639238749165, "min": 0.9110401947691571, "max": 114.8363941013813, "count": 99 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1787486076", "python_version": "3.10.12 | packaged by conda-forge | (main, Jun 23 2023, 22:40:32) [GCC 12.3.0]", "command_line_arguments": "/content/mlagents310/bin/mlagents-learn /content/ml-agents/config/ppo/PyramidsRND_HF.yaml --env=/content/ml-agents/training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids1 --results-dir=/content/drive/MyDrive/HF_DeepRL_Unit5/Pyramids/results --no-graphics", "mlagents_version": "1.1.0", "mlagents_envs_version": "1.1.0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.1.1+cpu", "numpy_version": "1.23.5", "end_time_seconds": "1787490264" }, "total": 4188.032266593002, "count": 1, "self": 0.6529515950005589, "children": { "run_training.setup": { "total": 0.03629553599967039, "count": 1, "self": 0.03629553599967039 }, "TrainerController.start_learning": { "total": 4187.343019462001, "count": 1, "self": 2.094446508881447, "children": { "TrainerController._reset_env": { "total": 1.929896285999348, "count": 1, "self": 1.929896285999348 }, "TrainerController.advance": { "total": 4183.104363916122, "count": 64345, "self": 2.225138767460521, "children": { "env_step": { "total": 3097.410105198056, "count": 64345, "self": 2952.785838075484, "children": { "SubprocessEnvManager._take_step": { "total": 143.23881447907843, "count": 64345, "self": 6.317051528889351, "children": { "TorchPolicy.evaluate": { "total": 136.92176295018908, "count": 62560, "self": 136.92176295018908 } } }, "workers": { "total": 1.3854526434934087, "count": 64345, "self": 0.0, "children": { "worker_root": { "total": 4177.959397364599, "count": 64345, "is_parallel": true, "self": 1408.2953628406867, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.003124605000266456, "count": 1, "is_parallel": true, "self": 0.000906355004190118, "children": { "_process_rank_one_or_two_observation": { "total": 0.002218249996076338, "count": 8, "is_parallel": true, "self": 0.002218249996076338 } } }, "UnityEnvironment.step": { "total": 0.07438645799993537, "count": 1, "is_parallel": true, "self": 0.0017527049985801568, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005888550003874116, "count": 1, "is_parallel": true, "self": 0.0005888550003874116 }, "communicator.exchange": { "total": 0.06870571299987205, "count": 1, "is_parallel": true, "self": 0.06870571299987205 }, "steps_from_proto": { "total": 0.003339185001095757, "count": 1, "is_parallel": true, "self": 0.00046066399772826117, "children": { "_process_rank_one_or_two_observation": { "total": 0.0028785210033674957, "count": 8, "is_parallel": true, "self": 0.0028785210033674957 } } } } } } }, "UnityEnvironment.step": { "total": 2769.664034523912, "count": 64344, "is_parallel": true, "self": 51.98580021241287, "children": { "UnityEnvironment._generate_step_input": { "total": 33.44262606215307, "count": 64344, "is_parallel": true, "self": 33.44262606215307 }, "communicator.exchange": { "total": 2521.4422236939354, "count": 64344, "is_parallel": true, "self": 2521.4422236939354 }, "steps_from_proto": { "total": 162.79338455541074, "count": 64344, "is_parallel": true, "self": 32.41883957612845, "children": { "_process_rank_one_or_two_observation": { "total": 130.3745449792823, "count": 514752, "is_parallel": true, "self": 130.3745449792823 } } } } } } } } } } }, "trainer_advance": { "total": 1083.469119950605, "count": 64345, "self": 3.7547200758344843, "children": { "process_trajectory": { "total": 160.8547617767672, "count": 64345, "self": 159.13201149576344, "children": { "RLTrainer._checkpoint": { "total": 1.722750281003755, "count": 10, "self": 1.722750281003755 } } }, "_update_policy": { "total": 918.8596380980034, "count": 452, "self": 371.8709007099733, "children": { "TorchPPOOptimizer.update": { "total": 546.9887373880301, "count": 22776, "self": 546.9887373880301 } } } } } } }, "trainer_threads": { "total": 1.395997969666496e-06, "count": 1, "self": 1.395997969666496e-06 }, "TrainerController._save_models": { "total": 0.21431135500097298, "count": 1, "self": 0.022026874001312535, "children": { "RLTrainer._checkpoint": { "total": 0.19228448099966045, "count": 1, "self": 0.19228448099966045 } } } } } } }