|
{ |
|
"name": "root", |
|
"gauges": { |
|
"SnowballTarget.Policy.Entropy.mean": { |
|
"value": 2.7782135009765625, |
|
"min": 2.7721009254455566, |
|
"max": 2.8902347087860107, |
|
"count": 20 |
|
}, |
|
"SnowballTarget.Policy.Entropy.sum": { |
|
"value": 4186.767578125, |
|
"min": 1921.06591796875, |
|
"max": 4307.4716796875, |
|
"count": 20 |
|
}, |
|
"SnowballTarget.Step.mean": { |
|
"value": 19992.0, |
|
"min": 960.0, |
|
"max": 19992.0, |
|
"count": 20 |
|
}, |
|
"SnowballTarget.Step.sum": { |
|
"value": 19992.0, |
|
"min": 960.0, |
|
"max": 19992.0, |
|
"count": 20 |
|
}, |
|
"SnowballTarget.Policy.ExtrinsicValueEstimate.mean": { |
|
"value": 1.8563480377197266, |
|
"min": 0.02834838069975376, |
|
"max": 1.8563480377197266, |
|
"count": 20 |
|
}, |
|
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { |
|
"value": 48.26504898071289, |
|
"min": 0.42522570490837097, |
|
"max": 48.26504898071289, |
|
"count": 20 |
|
}, |
|
"SnowballTarget.IsTraining.mean": { |
|
"value": 1.0, |
|
"min": 1.0, |
|
"max": 1.0, |
|
"count": 20 |
|
}, |
|
"SnowballTarget.IsTraining.sum": { |
|
"value": 1.0, |
|
"min": 1.0, |
|
"max": 1.0, |
|
"count": 20 |
|
}, |
|
"SnowballTarget.Environment.EpisodeLength.mean": { |
|
"value": 199.0, |
|
"min": 199.0, |
|
"max": 199.0, |
|
"count": 9 |
|
}, |
|
"SnowballTarget.Environment.EpisodeLength.sum": { |
|
"value": 2189.0, |
|
"min": 2189.0, |
|
"max": 2189.0, |
|
"count": 9 |
|
}, |
|
"SnowballTarget.Losses.PolicyLoss.mean": { |
|
"value": 0.06319518530126159, |
|
"min": 0.06319518530126159, |
|
"max": 0.08211942279127006, |
|
"count": 9 |
|
}, |
|
"SnowballTarget.Losses.PolicyLoss.sum": { |
|
"value": 0.06319518530126159, |
|
"min": 0.06319518530126159, |
|
"max": 0.08211942279127006, |
|
"count": 9 |
|
}, |
|
"SnowballTarget.Losses.ValueLoss.mean": { |
|
"value": 0.23654111547797335, |
|
"min": 0.06976678397725611, |
|
"max": 0.23654111547797335, |
|
"count": 9 |
|
}, |
|
"SnowballTarget.Losses.ValueLoss.sum": { |
|
"value": 0.23654111547797335, |
|
"min": 0.06976678397725611, |
|
"max": 0.23654111547797335, |
|
"count": 9 |
|
}, |
|
"SnowballTarget.Policy.LearningRate.mean": { |
|
"value": 4.320098559999991e-06, |
|
"min": 4.320098559999991e-06, |
|
"max": 0.00026832001056, |
|
"count": 9 |
|
}, |
|
"SnowballTarget.Policy.LearningRate.sum": { |
|
"value": 4.320098559999991e-06, |
|
"min": 4.320098559999991e-06, |
|
"max": 0.00026832001056, |
|
"count": 9 |
|
}, |
|
"SnowballTarget.Policy.Epsilon.mean": { |
|
"value": 0.10144, |
|
"min": 0.10144, |
|
"max": 0.18944000000000003, |
|
"count": 9 |
|
}, |
|
"SnowballTarget.Policy.Epsilon.sum": { |
|
"value": 0.10144, |
|
"min": 0.10144, |
|
"max": 0.18944000000000003, |
|
"count": 9 |
|
}, |
|
"SnowballTarget.Policy.Beta.mean": { |
|
"value": 8.185599999999986e-05, |
|
"min": 8.185599999999986e-05, |
|
"max": 0.0044730559999999996, |
|
"count": 9 |
|
}, |
|
"SnowballTarget.Policy.Beta.sum": { |
|
"value": 8.185599999999986e-05, |
|
"min": 8.185599999999986e-05, |
|
"max": 0.0044730559999999996, |
|
"count": 9 |
|
}, |
|
"SnowballTarget.Environment.CumulativeReward.mean": { |
|
"value": 5.636363636363637, |
|
"min": 2.3636363636363638, |
|
"max": 7.0, |
|
"count": 10 |
|
}, |
|
"SnowballTarget.Environment.CumulativeReward.sum": { |
|
"value": 62.0, |
|
"min": 7.0, |
|
"max": 67.0, |
|
"count": 10 |
|
}, |
|
"SnowballTarget.Policy.ExtrinsicReward.mean": { |
|
"value": 5.636363636363637, |
|
"min": 2.3636363636363638, |
|
"max": 7.0, |
|
"count": 10 |
|
}, |
|
"SnowballTarget.Policy.ExtrinsicReward.sum": { |
|
"value": 62.0, |
|
"min": 7.0, |
|
"max": 67.0, |
|
"count": 10 |
|
} |
|
}, |
|
"metadata": { |
|
"timer_format_version": "0.1.0", |
|
"start_time_seconds": "1712198708", |
|
"python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [GCC 11.4.0]", |
|
"command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics", |
|
"mlagents_version": "1.1.0.dev0", |
|
"mlagents_envs_version": "1.1.0.dev0", |
|
"communication_protocol_version": "1.5.0", |
|
"pytorch_version": "2.2.1+cu121", |
|
"numpy_version": "1.23.5", |
|
"end_time_seconds": "1712198758" |
|
}, |
|
"total": 49.94476474199996, |
|
"count": 1, |
|
"self": 0.4451240260000304, |
|
"children": { |
|
"run_training.setup": { |
|
"total": 0.05999714199992923, |
|
"count": 1, |
|
"self": 0.05999714199992923 |
|
}, |
|
"TrainerController.start_learning": { |
|
"total": 49.439643574, |
|
"count": 1, |
|
"self": 0.0878915770030062, |
|
"children": { |
|
"TrainerController._reset_env": { |
|
"total": 3.498892657000056, |
|
"count": 1, |
|
"self": 3.498892657000056 |
|
}, |
|
"TrainerController.advance": { |
|
"total": 45.76350254599697, |
|
"count": 1872, |
|
"self": 0.02817843999298475, |
|
"children": { |
|
"env_step": { |
|
"total": 45.735324106003986, |
|
"count": 1872, |
|
"self": 28.177305445004436, |
|
"children": { |
|
"SubprocessEnvManager._take_step": { |
|
"total": 17.5283142509993, |
|
"count": 1872, |
|
"self": 0.14613616900305715, |
|
"children": { |
|
"TorchPolicy.evaluate": { |
|
"total": 17.382178081996244, |
|
"count": 1872, |
|
"self": 17.382178081996244 |
|
} |
|
} |
|
}, |
|
"workers": { |
|
"total": 0.02970441000024948, |
|
"count": 1872, |
|
"self": 0.0, |
|
"children": { |
|
"worker_root": { |
|
"total": 49.272314619003964, |
|
"count": 1872, |
|
"is_parallel": true, |
|
"self": 27.324712364002494, |
|
"children": { |
|
"run_training.setup": { |
|
"total": 0.0, |
|
"count": 0, |
|
"is_parallel": true, |
|
"self": 0.0, |
|
"children": { |
|
"steps_from_proto": { |
|
"total": 0.007336522000059631, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.003287211000269963, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 0.004049310999789668, |
|
"count": 10, |
|
"is_parallel": true, |
|
"self": 0.004049310999789668 |
|
} |
|
} |
|
}, |
|
"UnityEnvironment.step": { |
|
"total": 0.035171697999999196, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0006839940001555078, |
|
"children": { |
|
"UnityEnvironment._generate_step_input": { |
|
"total": 0.0004326709999986633, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0004326709999986633 |
|
}, |
|
"communicator.exchange": { |
|
"total": 0.03196525499993186, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.03196525499993186 |
|
}, |
|
"steps_from_proto": { |
|
"total": 0.002089777999913167, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.00041910499999175954, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 0.0016706729999214076, |
|
"count": 10, |
|
"is_parallel": true, |
|
"self": 0.0016706729999214076 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"UnityEnvironment.step": { |
|
"total": 21.94760225500147, |
|
"count": 1871, |
|
"is_parallel": true, |
|
"self": 1.047796662005453, |
|
"children": { |
|
"UnityEnvironment._generate_step_input": { |
|
"total": 0.5427237929968669, |
|
"count": 1871, |
|
"is_parallel": true, |
|
"self": 0.5427237929968669 |
|
}, |
|
"communicator.exchange": { |
|
"total": 16.979106069999716, |
|
"count": 1871, |
|
"is_parallel": true, |
|
"self": 16.979106069999716 |
|
}, |
|
"steps_from_proto": { |
|
"total": 3.3779757299994344, |
|
"count": 1871, |
|
"is_parallel": true, |
|
"self": 0.6219151210079872, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 2.7560606089914472, |
|
"count": 18710, |
|
"is_parallel": true, |
|
"self": 2.7560606089914472 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"trainer_threads": { |
|
"total": 0.0002709350000031918, |
|
"count": 1, |
|
"self": 0.0002709350000031918, |
|
"children": { |
|
"thread_root": { |
|
"total": 0.0, |
|
"count": 0, |
|
"is_parallel": true, |
|
"self": 0.0, |
|
"children": { |
|
"trainer_advance": { |
|
"total": 45.21979735200625, |
|
"count": 71712, |
|
"is_parallel": true, |
|
"self": 1.5159403550302386, |
|
"children": { |
|
"process_trajectory": { |
|
"total": 24.942917492975653, |
|
"count": 71712, |
|
"is_parallel": true, |
|
"self": 24.126466782975626, |
|
"children": { |
|
"RLTrainer._checkpoint": { |
|
"total": 0.8164507100000264, |
|
"count": 4, |
|
"is_parallel": true, |
|
"self": 0.8164507100000264 |
|
} |
|
} |
|
}, |
|
"_update_policy": { |
|
"total": 18.760939504000362, |
|
"count": 9, |
|
"is_parallel": true, |
|
"self": 5.360667786000249, |
|
"children": { |
|
"TorchPPOOptimizer.update": { |
|
"total": 13.400271718000113, |
|
"count": 456, |
|
"is_parallel": true, |
|
"self": 13.400271718000113 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"TrainerController._save_models": { |
|
"total": 0.08908585899996524, |
|
"count": 1, |
|
"self": 0.0009637210000619234, |
|
"children": { |
|
"RLTrainer._checkpoint": { |
|
"total": 0.08812213799990332, |
|
"count": 1, |
|
"self": 0.08812213799990332 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |