|
{ |
|
"name": "root", |
|
"gauges": { |
|
"Pyramids.Policy.Entropy.mean": { |
|
"value": 0.2702971398830414, |
|
"min": 0.2702971398830414, |
|
"max": 1.2891076803207397, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.Entropy.sum": { |
|
"value": 8113.2392578125, |
|
"min": 8113.2392578125, |
|
"max": 39106.37109375, |
|
"count": 33 |
|
}, |
|
"Pyramids.Step.mean": { |
|
"value": 989971.0, |
|
"min": 29936.0, |
|
"max": 989971.0, |
|
"count": 33 |
|
}, |
|
"Pyramids.Step.sum": { |
|
"value": 989971.0, |
|
"min": 29936.0, |
|
"max": 989971.0, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.ExtrinsicValueEstimate.mean": { |
|
"value": 0.4744797646999359, |
|
"min": -0.10347743332386017, |
|
"max": 0.5322203636169434, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.ExtrinsicValueEstimate.sum": { |
|
"value": 129.53297424316406, |
|
"min": -24.834583282470703, |
|
"max": 144.76393127441406, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.RndValueEstimate.mean": { |
|
"value": 0.0038337113801389933, |
|
"min": -0.012685767374932766, |
|
"max": 0.39543870091438293, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.RndValueEstimate.sum": { |
|
"value": 1.0466032028198242, |
|
"min": -3.5139575004577637, |
|
"max": 96.09160614013672, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.PolicyLoss.mean": { |
|
"value": 0.0673648516080686, |
|
"min": 0.06549121167890483, |
|
"max": 0.07230482210122448, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.PolicyLoss.sum": { |
|
"value": 0.9431079225129604, |
|
"min": 0.4885109620501325, |
|
"max": 1.061638241497955, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.ValueLoss.mean": { |
|
"value": 0.01454445901825758, |
|
"min": 0.0003146042189352528, |
|
"max": 0.015206249028457988, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.ValueLoss.sum": { |
|
"value": 0.20362242625560611, |
|
"min": 0.004089854846158286, |
|
"max": 0.22237124988654008, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.LearningRate.mean": { |
|
"value": 7.498318929164287e-06, |
|
"min": 7.498318929164287e-06, |
|
"max": 0.00029515063018788575, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.LearningRate.sum": { |
|
"value": 0.00010497646500830002, |
|
"min": 0.00010497646500830002, |
|
"max": 0.0036341239886254, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.Epsilon.mean": { |
|
"value": 0.10249940714285713, |
|
"min": 0.10249940714285713, |
|
"max": 0.19838354285714285, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.Epsilon.sum": { |
|
"value": 1.4349916999999999, |
|
"min": 1.3886848, |
|
"max": 2.6113746000000004, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.Beta.mean": { |
|
"value": 0.0002596907735714286, |
|
"min": 0.0002596907735714286, |
|
"max": 0.00983851593142857, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.Beta.sum": { |
|
"value": 0.0036356708300000007, |
|
"min": 0.0036356708300000007, |
|
"max": 0.12115632254000003, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.RNDLoss.mean": { |
|
"value": 0.013456364162266254, |
|
"min": 0.013456364162266254, |
|
"max": 0.48522648215293884, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.RNDLoss.sum": { |
|
"value": 0.18838909268379211, |
|
"min": 0.18838909268379211, |
|
"max": 3.396585464477539, |
|
"count": 33 |
|
}, |
|
"Pyramids.Environment.EpisodeLength.mean": { |
|
"value": 393.2105263157895, |
|
"min": 341.32941176470587, |
|
"max": 999.0, |
|
"count": 33 |
|
}, |
|
"Pyramids.Environment.EpisodeLength.sum": { |
|
"value": 29884.0, |
|
"min": 16863.0, |
|
"max": 33458.0, |
|
"count": 33 |
|
}, |
|
"Pyramids.Environment.CumulativeReward.mean": { |
|
"value": 1.4488341895569312, |
|
"min": -0.9997625509276986, |
|
"max": 1.6351293948643348, |
|
"count": 33 |
|
}, |
|
"Pyramids.Environment.CumulativeReward.sum": { |
|
"value": 110.11139840632677, |
|
"min": -31.992401629686356, |
|
"max": 138.98599856346846, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.ExtrinsicReward.mean": { |
|
"value": 1.4488341895569312, |
|
"min": -0.9997625509276986, |
|
"max": 1.6351293948643348, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.ExtrinsicReward.sum": { |
|
"value": 110.11139840632677, |
|
"min": -31.992401629686356, |
|
"max": 138.98599856346846, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.RndReward.mean": { |
|
"value": 0.055180177631547464, |
|
"min": 0.0501192481332349, |
|
"max": 8.82132951126379, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.RndReward.sum": { |
|
"value": 4.193693499997607, |
|
"min": 4.193693499997607, |
|
"max": 149.96260169148445, |
|
"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": "1714226718", |
|
"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/PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids Training --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": "1714229142" |
|
}, |
|
"total": 2423.9578567800004, |
|
"count": 1, |
|
"self": 0.9005427810002402, |
|
"children": { |
|
"run_training.setup": { |
|
"total": 0.05190410800014433, |
|
"count": 1, |
|
"self": 0.05190410800014433 |
|
}, |
|
"TrainerController.start_learning": { |
|
"total": 2423.005409891, |
|
"count": 1, |
|
"self": 1.9327991999889491, |
|
"children": { |
|
"TrainerController._reset_env": { |
|
"total": 2.7842463960000714, |
|
"count": 1, |
|
"self": 2.7842463960000714 |
|
}, |
|
"TrainerController.advance": { |
|
"total": 2418.1523782500108, |
|
"count": 63773, |
|
"self": 1.9322518449685049, |
|
"children": { |
|
"env_step": { |
|
"total": 1763.9821685109837, |
|
"count": 63773, |
|
"self": 1602.9495349290542, |
|
"children": { |
|
"SubprocessEnvManager._take_step": { |
|
"total": 159.87333054199144, |
|
"count": 63773, |
|
"self": 5.900407892006115, |
|
"children": { |
|
"TorchPolicy.evaluate": { |
|
"total": 153.97292264998532, |
|
"count": 62553, |
|
"self": 153.97292264998532 |
|
} |
|
} |
|
}, |
|
"workers": { |
|
"total": 1.159303039938095, |
|
"count": 63773, |
|
"self": 0.0, |
|
"children": { |
|
"worker_root": { |
|
"total": 2416.5828318099148, |
|
"count": 63773, |
|
"is_parallel": true, |
|
"self": 960.615578661932, |
|
"children": { |
|
"run_training.setup": { |
|
"total": 0.0, |
|
"count": 0, |
|
"is_parallel": true, |
|
"self": 0.0, |
|
"children": { |
|
"steps_from_proto": { |
|
"total": 0.002841707000243332, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0007448990008924739, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 0.002096807999350858, |
|
"count": 8, |
|
"is_parallel": true, |
|
"self": 0.002096807999350858 |
|
} |
|
} |
|
}, |
|
"UnityEnvironment.step": { |
|
"total": 0.05291120099991531, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0006339979995573231, |
|
"children": { |
|
"UnityEnvironment._generate_step_input": { |
|
"total": 0.0005072590001873323, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0005072590001873323 |
|
}, |
|
"communicator.exchange": { |
|
"total": 0.05005217999996603, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.05005217999996603 |
|
}, |
|
"steps_from_proto": { |
|
"total": 0.0017177640002046246, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0003895810000358324, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 0.0013281830001687922, |
|
"count": 8, |
|
"is_parallel": true, |
|
"self": 0.0013281830001687922 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"UnityEnvironment.step": { |
|
"total": 1455.9672531479828, |
|
"count": 63772, |
|
"is_parallel": true, |
|
"self": 38.87572233597166, |
|
"children": { |
|
"UnityEnvironment._generate_step_input": { |
|
"total": 26.19753738605459, |
|
"count": 63772, |
|
"is_parallel": true, |
|
"self": 26.19753738605459 |
|
}, |
|
"communicator.exchange": { |
|
"total": 1276.5800462889888, |
|
"count": 63772, |
|
"is_parallel": true, |
|
"self": 1276.5800462889888 |
|
}, |
|
"steps_from_proto": { |
|
"total": 114.31394713696773, |
|
"count": 63772, |
|
"is_parallel": true, |
|
"self": 24.69237933182876, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 89.62156780513897, |
|
"count": 510176, |
|
"is_parallel": true, |
|
"self": 89.62156780513897 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"trainer_advance": { |
|
"total": 652.2379578940586, |
|
"count": 63773, |
|
"self": 3.6290027751147136, |
|
"children": { |
|
"process_trajectory": { |
|
"total": 138.6211657339536, |
|
"count": 63773, |
|
"self": 138.35645864895332, |
|
"children": { |
|
"RLTrainer._checkpoint": { |
|
"total": 0.26470708500028195, |
|
"count": 2, |
|
"self": 0.26470708500028195 |
|
} |
|
} |
|
}, |
|
"_update_policy": { |
|
"total": 509.98778938499026, |
|
"count": 457, |
|
"self": 298.5665553030167, |
|
"children": { |
|
"TorchPPOOptimizer.update": { |
|
"total": 211.42123408197358, |
|
"count": 22812, |
|
"self": 211.42123408197358 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"trainer_threads": { |
|
"total": 1.3990002116770484e-06, |
|
"count": 1, |
|
"self": 1.3990002116770484e-06 |
|
}, |
|
"TrainerController._save_models": { |
|
"total": 0.13598464599999716, |
|
"count": 1, |
|
"self": 0.002097545000651735, |
|
"children": { |
|
"RLTrainer._checkpoint": { |
|
"total": 0.13388710099934542, |
|
"count": 1, |
|
"self": 0.13388710099934542 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |