|
{ |
|
"name": "root", |
|
"gauges": { |
|
"Pyramids.Policy.Entropy.mean": { |
|
"value": 0.49001896381378174, |
|
"min": 0.49001896381378174, |
|
"max": 1.5034692287445068, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.Entropy.sum": { |
|
"value": 14645.6865234375, |
|
"min": 14645.6865234375, |
|
"max": 45609.2421875, |
|
"count": 33 |
|
}, |
|
"Pyramids.Step.mean": { |
|
"value": 989891.0, |
|
"min": 29952.0, |
|
"max": 989891.0, |
|
"count": 33 |
|
}, |
|
"Pyramids.Step.sum": { |
|
"value": 989891.0, |
|
"min": 29952.0, |
|
"max": 989891.0, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.ExtrinsicValueEstimate.mean": { |
|
"value": 0.3086230456829071, |
|
"min": -0.09220867604017258, |
|
"max": 0.3086230456829071, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.ExtrinsicValueEstimate.sum": { |
|
"value": 80.85923767089844, |
|
"min": -22.2222900390625, |
|
"max": 80.85923767089844, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.RndValueEstimate.mean": { |
|
"value": -0.00924289133399725, |
|
"min": -0.00924289133399725, |
|
"max": 0.1579740196466446, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.RndValueEstimate.sum": { |
|
"value": -2.421637535095215, |
|
"min": -2.421637535095215, |
|
"max": 37.439842224121094, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.PolicyLoss.mean": { |
|
"value": 0.06914126428948972, |
|
"min": 0.06517837084824005, |
|
"max": 0.07285535915814668, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.PolicyLoss.sum": { |
|
"value": 1.0371189643423457, |
|
"min": 0.47732801350795706, |
|
"max": 1.0505344594906396, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.ValueLoss.mean": { |
|
"value": 0.011857123350442287, |
|
"min": 0.00029982233889350754, |
|
"max": 0.012120653791060438, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.ValueLoss.sum": { |
|
"value": 0.1778568502566343, |
|
"min": 0.003897690405615598, |
|
"max": 0.1778568502566343, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.LearningRate.mean": { |
|
"value": 7.4828375057533364e-06, |
|
"min": 7.4828375057533364e-06, |
|
"max": 0.00029515063018788575, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.LearningRate.sum": { |
|
"value": 0.00011224256258630004, |
|
"min": 0.00011224256258630004, |
|
"max": 0.0033832094722635996, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.Epsilon.mean": { |
|
"value": 0.1024942466666667, |
|
"min": 0.1024942466666667, |
|
"max": 0.19838354285714285, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.Epsilon.sum": { |
|
"value": 1.5374137000000005, |
|
"min": 1.3886848, |
|
"max": 2.5277364000000007, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.Beta.mean": { |
|
"value": 0.00025917524200000017, |
|
"min": 0.00025917524200000017, |
|
"max": 0.00983851593142857, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.Beta.sum": { |
|
"value": 0.0038876286300000024, |
|
"min": 0.0038876286300000024, |
|
"max": 0.11280086635999999, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.RNDLoss.mean": { |
|
"value": 0.007337408140301704, |
|
"min": 0.007315743248909712, |
|
"max": 0.20766839385032654, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.RNDLoss.sum": { |
|
"value": 0.11006112396717072, |
|
"min": 0.10242040455341339, |
|
"max": 1.4536787271499634, |
|
"count": 33 |
|
}, |
|
"Pyramids.Environment.EpisodeLength.mean": { |
|
"value": 527.5833333333334, |
|
"min": 527.5833333333334, |
|
"max": 999.0, |
|
"count": 33 |
|
}, |
|
"Pyramids.Environment.EpisodeLength.sum": { |
|
"value": 31655.0, |
|
"min": 15984.0, |
|
"max": 32729.0, |
|
"count": 33 |
|
}, |
|
"Pyramids.Environment.CumulativeReward.mean": { |
|
"value": 1.1723133134345214, |
|
"min": -1.0000000521540642, |
|
"max": 1.1723133134345214, |
|
"count": 33 |
|
}, |
|
"Pyramids.Environment.CumulativeReward.sum": { |
|
"value": 70.33879880607128, |
|
"min": -30.731001660227776, |
|
"max": 70.33879880607128, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.ExtrinsicReward.mean": { |
|
"value": 1.1723133134345214, |
|
"min": -1.0000000521540642, |
|
"max": 1.1723133134345214, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.ExtrinsicReward.sum": { |
|
"value": 70.33879880607128, |
|
"min": -30.731001660227776, |
|
"max": 70.33879880607128, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.RndReward.mean": { |
|
"value": 0.04111563407835395, |
|
"min": 0.04111563407835395, |
|
"max": 7.148975944379345, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.RndReward.sum": { |
|
"value": 2.4669380447012372, |
|
"min": 2.316392977605574, |
|
"max": 114.38361511006951, |
|
"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": "1690314777", |
|
"python_version": "3.10.6 (main, May 29 2023, 11:10:38) [GCC 11.3.0]", |
|
"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": "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": "1690316881" |
|
}, |
|
"total": 2103.512406506, |
|
"count": 1, |
|
"self": 0.532003005999286, |
|
"children": { |
|
"run_training.setup": { |
|
"total": 0.03505809200009935, |
|
"count": 1, |
|
"self": 0.03505809200009935 |
|
}, |
|
"TrainerController.start_learning": { |
|
"total": 2102.9453454080003, |
|
"count": 1, |
|
"self": 1.4242780520585256, |
|
"children": { |
|
"TrainerController._reset_env": { |
|
"total": 4.034055599999874, |
|
"count": 1, |
|
"self": 4.034055599999874 |
|
}, |
|
"TrainerController.advance": { |
|
"total": 2097.322601750942, |
|
"count": 63317, |
|
"self": 1.402749899922128, |
|
"children": { |
|
"env_step": { |
|
"total": 1413.8305108029597, |
|
"count": 63317, |
|
"self": 1297.8667542019907, |
|
"children": { |
|
"SubprocessEnvManager._take_step": { |
|
"total": 115.1542121799207, |
|
"count": 63317, |
|
"self": 4.712077865981428, |
|
"children": { |
|
"TorchPolicy.evaluate": { |
|
"total": 110.44213431393928, |
|
"count": 62564, |
|
"self": 110.44213431393928 |
|
} |
|
} |
|
}, |
|
"workers": { |
|
"total": 0.8095444210482583, |
|
"count": 63317, |
|
"self": 0.0, |
|
"children": { |
|
"worker_root": { |
|
"total": 2098.1707575230316, |
|
"count": 63317, |
|
"is_parallel": true, |
|
"self": 912.6269584240035, |
|
"children": { |
|
"run_training.setup": { |
|
"total": 0.0, |
|
"count": 0, |
|
"is_parallel": true, |
|
"self": 0.0, |
|
"children": { |
|
"steps_from_proto": { |
|
"total": 0.0017652750000252126, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.000537261999625116, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 0.0012280130004000966, |
|
"count": 8, |
|
"is_parallel": true, |
|
"self": 0.0012280130004000966 |
|
} |
|
} |
|
}, |
|
"UnityEnvironment.step": { |
|
"total": 0.046720362000087334, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0005681690001893003, |
|
"children": { |
|
"UnityEnvironment._generate_step_input": { |
|
"total": 0.0004731819999506115, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0004731819999506115 |
|
}, |
|
"communicator.exchange": { |
|
"total": 0.04389173999993545, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.04389173999993545 |
|
}, |
|
"steps_from_proto": { |
|
"total": 0.0017872710000119696, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0003627640005561261, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 0.0014245069994558435, |
|
"count": 8, |
|
"is_parallel": true, |
|
"self": 0.0014245069994558435 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"UnityEnvironment.step": { |
|
"total": 1185.543799099028, |
|
"count": 63316, |
|
"is_parallel": true, |
|
"self": 33.81992554412932, |
|
"children": { |
|
"UnityEnvironment._generate_step_input": { |
|
"total": 22.51350517788933, |
|
"count": 63316, |
|
"is_parallel": true, |
|
"self": 22.51350517788933 |
|
}, |
|
"communicator.exchange": { |
|
"total": 1029.5202450829786, |
|
"count": 63316, |
|
"is_parallel": true, |
|
"self": 1029.5202450829786 |
|
}, |
|
"steps_from_proto": { |
|
"total": 99.69012329403085, |
|
"count": 63316, |
|
"is_parallel": true, |
|
"self": 19.978628200085495, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 79.71149509394536, |
|
"count": 506528, |
|
"is_parallel": true, |
|
"self": 79.71149509394536 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"trainer_advance": { |
|
"total": 682.0893410480601, |
|
"count": 63317, |
|
"self": 2.48643520702376, |
|
"children": { |
|
"process_trajectory": { |
|
"total": 109.0537140320348, |
|
"count": 63317, |
|
"self": 108.72710298603488, |
|
"children": { |
|
"RLTrainer._checkpoint": { |
|
"total": 0.3266110459999254, |
|
"count": 2, |
|
"self": 0.3266110459999254 |
|
} |
|
} |
|
}, |
|
"_update_policy": { |
|
"total": 570.5491918090015, |
|
"count": 448, |
|
"self": 350.8069666059655, |
|
"children": { |
|
"TorchPPOOptimizer.update": { |
|
"total": 219.742225203036, |
|
"count": 22797, |
|
"self": 219.742225203036 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"trainer_threads": { |
|
"total": 9.630002750782296e-07, |
|
"count": 1, |
|
"self": 9.630002750782296e-07 |
|
}, |
|
"TrainerController._save_models": { |
|
"total": 0.1644090419999884, |
|
"count": 1, |
|
"self": 0.003010126999924978, |
|
"children": { |
|
"RLTrainer._checkpoint": { |
|
"total": 0.16139891500006343, |
|
"count": 1, |
|
"self": 0.16139891500006343 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |