|
{ |
|
"name": "root", |
|
"gauges": { |
|
"Pyramids.Policy.Entropy.mean": { |
|
"value": 0.5227566361427307, |
|
"min": 0.5227566361427307, |
|
"max": 1.5130442380905151, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.Entropy.sum": { |
|
"value": 15691.0625, |
|
"min": 15691.0625, |
|
"max": 45899.7109375, |
|
"count": 33 |
|
}, |
|
"Pyramids.Step.mean": { |
|
"value": 989985.0, |
|
"min": 29952.0, |
|
"max": 989985.0, |
|
"count": 33 |
|
}, |
|
"Pyramids.Step.sum": { |
|
"value": 989985.0, |
|
"min": 29952.0, |
|
"max": 989985.0, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.ExtrinsicValueEstimate.mean": { |
|
"value": 0.4233270585536957, |
|
"min": -0.103851318359375, |
|
"max": 0.42442479729652405, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.ExtrinsicValueEstimate.sum": { |
|
"value": 113.45165252685547, |
|
"min": -25.028167724609375, |
|
"max": 114.17027282714844, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.RndValueEstimate.mean": { |
|
"value": 1.6036852598190308, |
|
"min": -0.011316122487187386, |
|
"max": 1.6036852598190308, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.RndValueEstimate.sum": { |
|
"value": 429.78765869140625, |
|
"min": -3.02140474319458, |
|
"max": 429.78765869140625, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.PolicyLoss.mean": { |
|
"value": 0.07047922759305773, |
|
"min": 0.06521506255491111, |
|
"max": 0.07502160772726363, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.PolicyLoss.sum": { |
|
"value": 0.9867091863028083, |
|
"min": 0.4977015996011959, |
|
"max": 1.0717928122224596, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.ValueLoss.mean": { |
|
"value": 0.324641490355134, |
|
"min": 9.967242569815033e-05, |
|
"max": 0.324641490355134, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.ValueLoss.sum": { |
|
"value": 4.544980864971876, |
|
"min": 0.0012957415340759542, |
|
"max": 4.544980864971876, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.LearningRate.mean": { |
|
"value": 7.37553325580714e-06, |
|
"min": 7.37553325580714e-06, |
|
"max": 0.00029515063018788575, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.LearningRate.sum": { |
|
"value": 0.00010325746558129996, |
|
"min": 0.00010325746558129996, |
|
"max": 0.003508567730477499, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.Epsilon.mean": { |
|
"value": 0.10245847857142856, |
|
"min": 0.10245847857142856, |
|
"max": 0.19838354285714285, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.Epsilon.sum": { |
|
"value": 1.4344187, |
|
"min": 1.3691136000000002, |
|
"max": 2.5695225000000006, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.Beta.mean": { |
|
"value": 0.0002556020092857142, |
|
"min": 0.0002556020092857142, |
|
"max": 0.00983851593142857, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.Beta.sum": { |
|
"value": 0.0035784281299999984, |
|
"min": 0.0035784281299999984, |
|
"max": 0.11697529775, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.RNDLoss.mean": { |
|
"value": 0.009180240333080292, |
|
"min": 0.00894622877240181, |
|
"max": 0.3266405165195465, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.RNDLoss.sum": { |
|
"value": 0.12852336466312408, |
|
"min": 0.12612619996070862, |
|
"max": 2.2864835262298584, |
|
"count": 33 |
|
}, |
|
"Pyramids.Environment.EpisodeLength.mean": { |
|
"value": 412.27142857142854, |
|
"min": 412.27142857142854, |
|
"max": 999.0, |
|
"count": 33 |
|
}, |
|
"Pyramids.Environment.EpisodeLength.sum": { |
|
"value": 28859.0, |
|
"min": 15984.0, |
|
"max": 32554.0, |
|
"count": 33 |
|
}, |
|
"Pyramids.Environment.CumulativeReward.mean": { |
|
"value": 1.4728140625315653, |
|
"min": -1.0000000521540642, |
|
"max": 1.4728140625315653, |
|
"count": 33 |
|
}, |
|
"Pyramids.Environment.CumulativeReward.sum": { |
|
"value": 104.56979843974113, |
|
"min": -32.000001668930054, |
|
"max": 104.56979843974113, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.ExtrinsicReward.mean": { |
|
"value": 1.4728140625315653, |
|
"min": -1.0000000521540642, |
|
"max": 1.4728140625315653, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.ExtrinsicReward.sum": { |
|
"value": 104.56979843974113, |
|
"min": -32.000001668930054, |
|
"max": 104.56979843974113, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.RndReward.mean": { |
|
"value": 0.03918750662295948, |
|
"min": 0.03918750662295948, |
|
"max": 6.462193723767996, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.RndReward.sum": { |
|
"value": 2.782312970230123, |
|
"min": 2.7782884165644646, |
|
"max": 103.39509958028793, |
|
"count": 33 |
|
}, |
|
"Pyramids.IsTraining.mean": { |
|
"value": 1.0, |
|
"min": 1.0, |
|
"max": 1.0, |
|
"count": 33 |
|
}, |
|
"Pyramids.IsTraining.sum": { |
|
"value": 1.0, |
|
"min": 1.0, |
|
"max": 1.0, |
|
"count": 33 |
|
} |
|
}, |
|
"metadata": { |
|
"timer_format_version": "0.1.0", |
|
"start_time_seconds": "1668351561", |
|
"python_version": "3.7.15 (default, Oct 12 2022, 19:14:55) \n[GCC 7.5.0]", |
|
"command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/PyramidsRND.yaml --env=./trained-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids Training --no-graphics", |
|
"mlagents_version": "0.29.0.dev0", |
|
"mlagents_envs_version": "0.29.0.dev0", |
|
"communication_protocol_version": "1.5.0", |
|
"pytorch_version": "1.8.1+cu102", |
|
"numpy_version": "1.21.6", |
|
"end_time_seconds": "1668353855" |
|
}, |
|
"total": 2293.223027514, |
|
"count": 1, |
|
"self": 0.439570329000162, |
|
"children": { |
|
"run_training.setup": { |
|
"total": 0.07085615300002246, |
|
"count": 1, |
|
"self": 0.07085615300002246 |
|
}, |
|
"TrainerController.start_learning": { |
|
"total": 2292.712601032, |
|
"count": 1, |
|
"self": 1.6959233729612606, |
|
"children": { |
|
"TrainerController._reset_env": { |
|
"total": 9.504904352999972, |
|
"count": 1, |
|
"self": 9.504904352999972 |
|
}, |
|
"TrainerController.advance": { |
|
"total": 2281.4126258330384, |
|
"count": 63481, |
|
"self": 1.8638428330195893, |
|
"children": { |
|
"env_step": { |
|
"total": 1518.4712097479864, |
|
"count": 63481, |
|
"self": 1393.1778515069846, |
|
"children": { |
|
"SubprocessEnvManager._take_step": { |
|
"total": 124.3795225689903, |
|
"count": 63481, |
|
"self": 5.304677962973642, |
|
"children": { |
|
"TorchPolicy.evaluate": { |
|
"total": 119.07484460601665, |
|
"count": 62569, |
|
"self": 39.79622806699433, |
|
"children": { |
|
"TorchPolicy.sample_actions": { |
|
"total": 79.27861653902232, |
|
"count": 62569, |
|
"self": 79.27861653902232 |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"workers": { |
|
"total": 0.9138356720117145, |
|
"count": 63481, |
|
"self": 0.0, |
|
"children": { |
|
"worker_root": { |
|
"total": 2287.610051639983, |
|
"count": 63481, |
|
"is_parallel": true, |
|
"self": 1015.3228645560005, |
|
"children": { |
|
"run_training.setup": { |
|
"total": 0.0, |
|
"count": 0, |
|
"is_parallel": true, |
|
"self": 0.0, |
|
"children": { |
|
"steps_from_proto": { |
|
"total": 0.007106899999996585, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.005238049000013234, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 0.0018688509999833514, |
|
"count": 8, |
|
"is_parallel": true, |
|
"self": 0.0018688509999833514 |
|
} |
|
} |
|
}, |
|
"UnityEnvironment.step": { |
|
"total": 0.05230104600002505, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0005565030000411753, |
|
"children": { |
|
"UnityEnvironment._generate_step_input": { |
|
"total": 0.0005169199999954799, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0005169199999954799 |
|
}, |
|
"communicator.exchange": { |
|
"total": 0.04933614800000896, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.04933614800000896 |
|
}, |
|
"steps_from_proto": { |
|
"total": 0.0018914749999794367, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0004964979999044772, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 0.0013949770000749595, |
|
"count": 8, |
|
"is_parallel": true, |
|
"self": 0.0013949770000749595 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"UnityEnvironment.step": { |
|
"total": 1272.2871870839824, |
|
"count": 63480, |
|
"is_parallel": true, |
|
"self": 30.863101088079247, |
|
"children": { |
|
"UnityEnvironment._generate_step_input": { |
|
"total": 27.839965423014064, |
|
"count": 63480, |
|
"is_parallel": true, |
|
"self": 27.839965423014064 |
|
}, |
|
"communicator.exchange": { |
|
"total": 1092.721828416977, |
|
"count": 63480, |
|
"is_parallel": true, |
|
"self": 1092.721828416977 |
|
}, |
|
"steps_from_proto": { |
|
"total": 120.8622921559122, |
|
"count": 63480, |
|
"is_parallel": true, |
|
"self": 28.38355998195709, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 92.47873217395511, |
|
"count": 507840, |
|
"is_parallel": true, |
|
"self": 92.47873217395511 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"trainer_advance": { |
|
"total": 761.0775732520324, |
|
"count": 63481, |
|
"self": 2.9562064840582707, |
|
"children": { |
|
"process_trajectory": { |
|
"total": 183.3881491089686, |
|
"count": 63481, |
|
"self": 183.18043031096875, |
|
"children": { |
|
"RLTrainer._checkpoint": { |
|
"total": 0.20771879799985982, |
|
"count": 2, |
|
"self": 0.20771879799985982 |
|
} |
|
} |
|
}, |
|
"_update_policy": { |
|
"total": 574.7332176590055, |
|
"count": 444, |
|
"self": 227.69583065701073, |
|
"children": { |
|
"TorchPPOOptimizer.update": { |
|
"total": 347.0373870019948, |
|
"count": 22827, |
|
"self": 347.0373870019948 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"trainer_threads": { |
|
"total": 9.660002433520276e-07, |
|
"count": 1, |
|
"self": 9.660002433520276e-07 |
|
}, |
|
"TrainerController._save_models": { |
|
"total": 0.09914650700011407, |
|
"count": 1, |
|
"self": 0.0017359459998260718, |
|
"children": { |
|
"RLTrainer._checkpoint": { |
|
"total": 0.097410561000288, |
|
"count": 1, |
|
"self": 0.097410561000288 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |