{ "name": "root", "gauges": { "Worm.Policy.Entropy.mean": { "value": 1.4186432361602783, "min": 1.41836416721344, "max": 1.418938398361206, "count": 3 }, "Worm.Policy.Entropy.sum": { "value": 42559.296875, "min": 42550.92578125, "max": 42568.15234375, "count": 3 }, "Worm.Environment.EpisodeLength.mean": { "value": 999.0, "min": 999.0, "max": 999.0, "count": 3 }, "Worm.Environment.EpisodeLength.sum": { "value": 29970.0, "min": 29970.0, "max": 29970.0, "count": 3 }, "Worm.Step.mean": { "value": 89000.0, "min": 29000.0, "max": 89000.0, "count": 3 }, "Worm.Step.sum": { "value": 89000.0, "min": 29000.0, "max": 89000.0, "count": 3 }, "Worm.Policy.ExtrinsicValueEstimate.mean": { "value": 0.04667310044169426, "min": 0.042724449187517166, "max": 0.04667310044169426, "count": 3 }, "Worm.Policy.ExtrinsicValueEstimate.sum": { "value": 1.4001929759979248, "min": 1.2612950801849365, "max": 1.4001929759979248, "count": 3 }, "Worm.Environment.CumulativeReward.mean": { "value": 0.48600394654398166, "min": 0.19933532153566677, "max": 0.48600394654398166, "count": 3 }, "Worm.Environment.CumulativeReward.sum": { "value": 14.580118396319449, "min": 5.9800596460700035, "max": 14.580118396319449, "count": 3 }, "Worm.Policy.ExtrinsicReward.mean": { "value": 0.48600394654398166, "min": 0.19933532153566677, "max": 0.48600394654398166, "count": 3 }, "Worm.Policy.ExtrinsicReward.sum": { "value": 14.580118396319449, "min": 5.9800596460700035, "max": 14.580118396319449, "count": 3 }, "Worm.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 3 }, "Worm.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 3 }, "Worm.Losses.PolicyLoss.mean": { "value": 0.021550595627299378, "min": 0.018366376078726415, "max": 0.021550595627299378, "count": 2 }, "Worm.Losses.PolicyLoss.sum": { "value": 0.021550595627299378, "min": 0.018366376078726415, "max": 0.021550595627299378, "count": 2 }, "Worm.Losses.ValueLoss.mean": { "value": 0.0020331353242952553, "min": 0.0020331353242952553, "max": 0.0084186820923129, "count": 2 }, "Worm.Losses.ValueLoss.sum": { "value": 0.0020331353242952553, "min": 0.0020331353242952553, "max": 0.0084186820923129, "count": 2 }, "Worm.Policy.LearningRate.mean": { "value": 0.00012000006, "min": 0.00012000006, "max": 0.00021000003000000005, "count": 2 }, "Worm.Policy.LearningRate.sum": { "value": 0.00012000006, "min": 0.00012000006, "max": 0.00021000003000000005, "count": 2 }, "Worm.Policy.Epsilon.mean": { "value": 0.13999999999999999, "min": 0.13999999999999999, "max": 0.16999999999999998, "count": 2 }, "Worm.Policy.Epsilon.sum": { "value": 0.13999999999999999, "min": 0.13999999999999999, "max": 0.16999999999999998, "count": 2 }, "Worm.Policy.Beta.mean": { "value": 0.002006, "min": 0.002006, "max": 0.003503, "count": 2 }, "Worm.Policy.Beta.sum": { "value": 0.002006, "min": 0.002006, "max": 0.003503, "count": 2 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1656848218", "python_version": "3.7.13 (default, Mar 29 2022, 02:18:16) \n[GCC 7.5.0]", "command_line_arguments": "/home/osanseviero/miniconda3/envs/mlagents/bin/mlagents-learn config/ppo/Worm.yaml --env=trained-envs-executables/linux/Worm/Worm --run-id=training --no-graphics", "mlagents_version": "0.29.0.dev0", "mlagents_envs_version": "0.29.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.8.0", "numpy_version": "1.21.5", "end_time_seconds": "1656848281" }, "total": 63.20981318899999, "count": 1, "self": 0.21756502699997782, "children": { "run_training.setup": { "total": 0.011864887000001545, "count": 1, "self": 0.011864887000001545 }, "TrainerController.start_learning": { "total": 62.98038327500001, "count": 1, "self": 0.11905975900333488, "children": { "TrainerController._reset_env": { "total": 2.0940638189999845, "count": 1, "self": 2.0940638189999845 }, "TrainerController.advance": { "total": 60.70532365099666, "count": 11000, "self": 0.12366392499302492, "children": { "env_step": { "total": 47.097982624001475, "count": 11000, "self": 37.81521809599985, "children": { "SubprocessEnvManager._take_step": { "total": 9.211672923999458, "count": 11000, "self": 0.4888320110017048, "children": { "TorchPolicy.evaluate": { "total": 8.722840912997754, "count": 11000, "self": 2.3672766420068, "children": { "TorchPolicy.sample_actions": { "total": 6.3555642709909534, "count": 11000, "self": 6.3555642709909534 } } } } }, "workers": { "total": 0.07109160400216297, "count": 11000, "self": 0.0, "children": { "worker_root": { "total": 62.43959642200389, "count": 11000, "is_parallel": true, "self": 31.027620766000723, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.00048800000001847366, "count": 1, "is_parallel": true, "self": 0.0001534439999204551, "children": { "_process_rank_one_or_two_observation": { "total": 0.00033455600009801856, "count": 2, "is_parallel": true, "self": 0.00033455600009801856 } } }, "UnityEnvironment.step": { "total": 0.012903008999956, "count": 1, "is_parallel": true, "self": 0.00010182199991959351, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00019712400001026253, "count": 1, "is_parallel": true, "self": 0.00019712400001026253 }, "communicator.exchange": { "total": 0.012344298000016352, "count": 1, "is_parallel": true, "self": 0.012344298000016352 }, "steps_from_proto": { "total": 0.00025976500000979286, "count": 1, "is_parallel": true, "self": 0.00010080200001993944, "children": { "_process_rank_one_or_two_observation": { "total": 0.00015896299998985342, "count": 2, "is_parallel": true, "self": 0.00015896299998985342 } } } } } } }, "UnityEnvironment.step": { "total": 31.411975656003165, "count": 10999, "is_parallel": true, "self": 0.8720366130122557, "children": { "UnityEnvironment._generate_step_input": { "total": 1.2969238320011982, "count": 10999, "is_parallel": true, "self": 1.2969238320011982 }, "communicator.exchange": { "total": 27.124492783997198, "count": 10999, "is_parallel": true, "self": 27.124492783997198 }, "steps_from_proto": { "total": 2.118522426992513, "count": 10999, "is_parallel": true, "self": 0.8417608799842355, "children": { "_process_rank_one_or_two_observation": { "total": 1.2767615470082774, "count": 21998, "is_parallel": true, "self": 1.2767615470082774 } } } } } } } } } } }, "trainer_advance": { "total": 13.483677102002162, "count": 11000, "self": 0.14227185999698122, "children": { "process_trajectory": { "total": 4.2275462980052225, "count": 11000, "self": 4.2275462980052225 }, "_update_policy": { "total": 9.113858943999958, "count": 3, "self": 7.840472577000469, "children": { "TorchPPOOptimizer.update": { "total": 1.273386366999489, "count": 126, "self": 1.273386366999489 } } } } } } }, "trainer_threads": { "total": 7.400000185953104e-07, "count": 1, "self": 7.400000185953104e-07 }, "TrainerController._save_models": { "total": 0.061935306000009405, "count": 1, "self": 0.0012024039999687375, "children": { "RLTrainer._checkpoint": { "total": 0.06073290200004067, "count": 1, "self": 0.06073290200004067 } } } } } } }