{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 1.4812062978744507, "min": 1.4812062978744507, "max": 1.4812062978744507, "count": 1 }, "Pyramids.Policy.Entropy.sum": { "value": 44933.875, "min": 44933.875, "max": 44933.875, "count": 1 }, "Pyramids.Step.mean": { "value": 29952.0, "min": 29952.0, "max": 29952.0, "count": 1 }, "Pyramids.Step.sum": { "value": 29952.0, "min": 29952.0, "max": 29952.0, "count": 1 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": -0.15425539016723633, "min": -0.15425539016723633, "max": -0.15425539016723633, "count": 1 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": -36.558528900146484, "min": -36.558528900146484, "max": -36.558528900146484, "count": 1 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.2783486545085907, "min": 0.2783486545085907, "max": 0.2783486545085907, "count": 1 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 65.9686279296875, "min": 65.9686279296875, "max": 65.9686279296875, "count": 1 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.07419968735200524, "min": 0.07419968735200524, "max": 0.07419968735200524, "count": 1 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.5193978114640367, "min": 0.5193978114640367, "max": 0.5193978114640367, "count": 1 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.005059755446744944, "min": 0.005059755446744944, "max": 0.005059755446744944, "count": 1 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.035418288127214606, "min": 0.035418288127214606, "max": 0.035418288127214606, "count": 1 }, "Pyramids.Policy.LearningRate.mean": { "value": 0.00013835433959619045, "min": 0.00013835433959619045, "max": 0.00013835433959619045, "count": 1 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.0009684803771733332, "min": 0.0009684803771733332, "max": 0.0009684803771733332, "count": 1 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.1461180952380953, "min": 0.1461180952380953, "max": 0.1461180952380953, "count": 1 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.022826666666667, "min": 1.022826666666667, "max": 1.022826666666667, "count": 1 }, "Pyramids.Policy.Beta.mean": { "value": 0.004617197714285715, "min": 0.004617197714285715, "max": 0.004617197714285715, "count": 1 }, "Pyramids.Policy.Beta.sum": { "value": 0.032320384, "min": 0.032320384, "max": 0.032320384, "count": 1 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.4187086522579193, "min": 0.4187086522579193, "max": 0.4187086522579193, "count": 1 }, "Pyramids.Losses.RNDLoss.sum": { "value": 2.9309606552124023, "min": 2.9309606552124023, "max": 2.9309606552124023, "count": 1 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 999.0, "min": 999.0, "max": 999.0, "count": 1 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 15984.0, "min": 15984.0, "max": 15984.0, "count": 1 }, "Pyramids.Environment.CumulativeReward.mean": { "value": -1.0000000521540642, "min": -1.0000000521540642, "max": -1.0000000521540642, "count": 1 }, "Pyramids.Environment.CumulativeReward.sum": { "value": -16.000000834465027, "min": -16.000000834465027, "max": -16.000000834465027, "count": 1 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": -1.0000000521540642, "min": -1.0000000521540642, "max": -1.0000000521540642, "count": 1 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": -16.000000834465027, "min": -16.000000834465027, "max": -16.000000834465027, "count": 1 }, "Pyramids.Policy.RndReward.mean": { "value": 7.737010681070387, "min": 7.737010681070387, "max": 7.737010681070387, "count": 1 }, "Pyramids.Policy.RndReward.sum": { "value": 123.7921708971262, "min": 123.7921708971262, "max": 123.7921708971262, "count": 1 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 1 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 1 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1696409185", "python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [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 --force", "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": "1696409248" }, "total": 62.80977841600003, "count": 1, "self": 0.475672502000009, "children": { "run_training.setup": { "total": 0.042352799000013874, "count": 1, "self": 0.042352799000013874 }, "TrainerController.start_learning": { "total": 62.291753115000006, "count": 1, "self": 0.043879270999639175, "children": { "TrainerController._reset_env": { "total": 4.1580085819999795, "count": 1, "self": 4.1580085819999795 }, "TrainerController.advance": { "total": 57.98057972400039, "count": 1896, "self": 0.04740730399998938, "children": { "env_step": { "total": 40.73302810399866, "count": 1896, "self": 37.143377515999816, "children": { "SubprocessEnvManager._take_step": { "total": 3.564516381998885, "count": 1896, "self": 0.15346569299987323, "children": { "TorchPolicy.evaluate": { "total": 3.411050688999012, "count": 1896, "self": 3.411050688999012 } } }, "workers": { "total": 0.025134205999961523, "count": 1896, "self": 0.0, "children": { "worker_root": { "total": 61.90972296199959, "count": 1896, "is_parallel": true, "self": 28.712086783998927, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0018741109999496075, "count": 1, "is_parallel": true, "self": 0.0005606059999649915, "children": { "_process_rank_one_or_two_observation": { "total": 0.001313504999984616, "count": 8, "is_parallel": true, "self": 0.001313504999984616 } } }, "UnityEnvironment.step": { "total": 0.05450469400000202, "count": 1, "is_parallel": true, "self": 0.000610489000052894, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004940829999782181, "count": 1, "is_parallel": true, "self": 0.0004940829999782181 }, "communicator.exchange": { "total": 0.05015548299996908, "count": 1, "is_parallel": true, "self": 0.05015548299996908 }, "steps_from_proto": { "total": 0.0032446390000018255, "count": 1, "is_parallel": true, "self": 0.00040584600003512605, "children": { "_process_rank_one_or_two_observation": { "total": 0.0028387929999666994, "count": 8, "is_parallel": true, "self": 0.0028387929999666994 } } } } } } }, "UnityEnvironment.step": { "total": 33.197636178000664, "count": 1895, "is_parallel": true, "self": 1.0362381160014706, "children": { "UnityEnvironment._generate_step_input": { "total": 0.7158879019996789, "count": 1895, "is_parallel": true, "self": 0.7158879019996789 }, "communicator.exchange": { "total": 28.19574069999993, "count": 1895, "is_parallel": true, "self": 28.19574069999993 }, "steps_from_proto": { "total": 3.249769459999584, "count": 1895, "is_parallel": true, "self": 0.6464213789997189, "children": { "_process_rank_one_or_two_observation": { "total": 2.603348080999865, "count": 15160, "is_parallel": true, "self": 2.603348080999865 } } } } } } } } } } }, "trainer_advance": { "total": 17.20014431600174, "count": 1896, "self": 0.04911986700113857, "children": { "process_trajectory": { "total": 3.2575707140005647, "count": 1896, "self": 3.2575707140005647 }, "_update_policy": { "total": 13.893453735000037, "count": 7, "self": 8.855323338999824, "children": { "TorchPPOOptimizer.update": { "total": 5.038130396000213, "count": 663, "self": 5.038130396000213 } } } } } } }, "trainer_threads": { "total": 1.0210000027655042e-06, "count": 1, "self": 1.0210000027655042e-06 }, "TrainerController._save_models": { "total": 0.10928451699999187, "count": 1, "self": 0.001251668999998401, "children": { "RLTrainer._checkpoint": { "total": 0.10803284799999346, "count": 1, "self": 0.10803284799999346 } } } } } } }