{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.4067095518112183, "min": 1.4067095518112183, "max": 1.4294543266296387, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 72555.265625, "min": 67753.59375, "max": 78819.7890625, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 97.59960552268245, "min": 88.28828828828829, "max": 394.9763779527559, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 49483.0, "min": 49000.0, "max": 50162.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999333.0, "min": 49856.0, "max": 1999333.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999333.0, "min": 49856.0, "max": 1999333.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.3505499362945557, "min": 0.08207014948129654, "max": 2.4085299968719482, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1191.728759765625, "min": 10.340838432312012, "max": 1282.08740234375, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.58903086173699, "min": 1.9089207171447693, "max": 3.8928719222396984, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 1819.6386469006538, "min": 240.52401036024094, "max": 2024.5286318659782, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.58903086173699, "min": 1.9089207171447693, "max": 3.8928719222396984, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 1819.6386469006538, "min": 240.52401036024094, "max": 2024.5286318659782, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.018643239073086685, "min": 0.014273006619623631, "max": 0.02036685783629461, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.03728647814617337, "min": 0.028546013239247263, "max": 0.05986203937015186, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.047305415260295074, "min": 0.02286746921017766, "max": 0.06115943385909001, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.09461083052059015, "min": 0.04573493842035532, "max": 0.17148052739600342, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 4.670123443324989e-06, "min": 4.670123443324989e-06, "max": 0.00029530665156445, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 9.340246886649977e-06, "min": 9.340246886649977e-06, "max": 0.00084413716862095, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.10155667500000001, "min": 0.10155667500000001, "max": 0.19843555000000002, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.20311335000000003, "min": 0.20311335000000003, "max": 0.58137905, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 8.76780824999998e-05, "min": 8.76780824999998e-05, "max": 0.004921933945, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.0001753561649999996, "min": 0.0001753561649999996, "max": 0.014070814594999998, "count": 40 }, "Huggy.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 40 }, "Huggy.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 40 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1694983010", "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/Huggy.yaml --env=./trained-envs-executables/linux/Huggy/Huggy --run-id=Huggy --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": "1694985712" }, "total": 2702.181000149, "count": 1, "self": 0.43914443899939215, "children": { "run_training.setup": { "total": 0.05686293600001591, "count": 1, "self": 0.05686293600001591 }, "TrainerController.start_learning": { "total": 2701.6849927740004, "count": 1, "self": 4.8788775500470365, "children": { "TrainerController._reset_env": { "total": 4.46066552800005, "count": 1, "self": 4.46066552800005 }, "TrainerController.advance": { "total": 2692.218525975954, "count": 231714, "self": 5.090203206173555, "children": { "env_step": { "total": 2103.48209392088, "count": 231714, "self": 1774.7478516008848, "children": { "SubprocessEnvManager._take_step": { "total": 325.43019692190046, "count": 231714, "self": 18.477453762987693, "children": { "TorchPolicy.evaluate": { "total": 306.95274315891277, "count": 223022, "self": 306.95274315891277 } } }, "workers": { "total": 3.3040453980945585, "count": 231714, "self": 0.0, "children": { "worker_root": { "total": 2693.518315896068, "count": 231714, "is_parallel": true, "self": 1245.718864345105, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0010452709999526633, "count": 1, "is_parallel": true, "self": 0.00027753099993788055, "children": { "_process_rank_one_or_two_observation": { "total": 0.0007677400000147827, "count": 2, "is_parallel": true, "self": 0.0007677400000147827 } } }, "UnityEnvironment.step": { "total": 0.03206938200003151, "count": 1, "is_parallel": true, "self": 0.00043791600000986364, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00023426999996445375, "count": 1, "is_parallel": true, "self": 0.00023426999996445375 }, "communicator.exchange": { "total": 0.030447402000049806, "count": 1, "is_parallel": true, "self": 0.030447402000049806 }, "steps_from_proto": { "total": 0.0009497940000073868, "count": 1, "is_parallel": true, "self": 0.00026848499999232445, "children": { "_process_rank_one_or_two_observation": { "total": 0.0006813090000150623, "count": 2, "is_parallel": true, "self": 0.0006813090000150623 } } } } } } }, "UnityEnvironment.step": { "total": 1447.799451550963, "count": 231713, "is_parallel": true, "self": 43.02528714188884, "children": { "UnityEnvironment._generate_step_input": { "total": 91.67174273406465, "count": 231713, "is_parallel": true, "self": 91.67174273406465 }, "communicator.exchange": { "total": 1204.8418598579574, "count": 231713, "is_parallel": true, "self": 1204.8418598579574 }, "steps_from_proto": { "total": 108.26056181705223, "count": 231713, "is_parallel": true, "self": 40.8877516261598, "children": { "_process_rank_one_or_two_observation": { "total": 67.37281019089244, "count": 463426, "is_parallel": true, "self": 67.37281019089244 } } } } } } } } } } }, "trainer_advance": { "total": 583.6462288489005, "count": 231714, "self": 7.646671936923326, "children": { "process_trajectory": { "total": 151.94440166597678, "count": 231714, "self": 150.47472433497774, "children": { "RLTrainer._checkpoint": { "total": 1.4696773309990476, "count": 10, "self": 1.4696773309990476 } } }, "_update_policy": { "total": 424.05515524600037, "count": 96, "self": 361.57759487499163, "children": { "TorchPPOOptimizer.update": { "total": 62.477560371008735, "count": 2880, "self": 62.477560371008735 } } } } } } }, "trainer_threads": { "total": 1.05399976746412e-06, "count": 1, "self": 1.05399976746412e-06 }, "TrainerController._save_models": { "total": 0.12692266599970026, "count": 1, "self": 0.002576068999587733, "children": { "RLTrainer._checkpoint": { "total": 0.12434659700011252, "count": 1, "self": 0.12434659700011252 } } } } } } }