|
{ |
|
"name": "root", |
|
"gauges": { |
|
"Pyramids.Policy.Entropy.mean": { |
|
"value": 0.5232324004173279, |
|
"min": 0.5232324004173279, |
|
"max": 0.6523197293281555, |
|
"count": 17 |
|
}, |
|
"Pyramids.Policy.Entropy.sum": { |
|
"value": 15320.244140625, |
|
"min": 15320.244140625, |
|
"max": 21037.91015625, |
|
"count": 17 |
|
}, |
|
"Pyramids.Environment.EpisodeLength.mean": { |
|
"value": 404.962962962963, |
|
"min": 197.84615384615384, |
|
"max": 600.9577464788732, |
|
"count": 17 |
|
}, |
|
"Pyramids.Environment.EpisodeLength.sum": { |
|
"value": 32802.0, |
|
"min": 2572.0, |
|
"max": 42668.0, |
|
"count": 17 |
|
}, |
|
"Pyramids.Step.mean": { |
|
"value": 1499999.0, |
|
"min": 1019968.0, |
|
"max": 1499999.0, |
|
"count": 17 |
|
}, |
|
"Pyramids.Step.sum": { |
|
"value": 1499999.0, |
|
"min": 1019968.0, |
|
"max": 1499999.0, |
|
"count": 17 |
|
}, |
|
"Pyramids.Policy.ExtrinsicValueEstimate.mean": { |
|
"value": 0.4259289503097534, |
|
"min": 0.11843127012252808, |
|
"max": 0.4484640657901764, |
|
"count": 17 |
|
}, |
|
"Pyramids.Policy.ExtrinsicValueEstimate.sum": { |
|
"value": 116.70452880859375, |
|
"min": 18.949003219604492, |
|
"max": 123.77608489990234, |
|
"count": 17 |
|
}, |
|
"Pyramids.Policy.RndValueEstimate.mean": { |
|
"value": 0.05657263472676277, |
|
"min": 0.05657263472676277, |
|
"max": 1.2450746297836304, |
|
"count": 17 |
|
}, |
|
"Pyramids.Policy.RndValueEstimate.sum": { |
|
"value": 15.50090217590332, |
|
"min": 15.50090217590332, |
|
"max": 328.69970703125, |
|
"count": 17 |
|
}, |
|
"Pyramids.Environment.CumulativeReward.mean": { |
|
"value": 1.4720829087423115, |
|
"min": 0.9842666441367732, |
|
"max": 1.8021538395148058, |
|
"count": 17 |
|
}, |
|
"Pyramids.Environment.CumulativeReward.sum": { |
|
"value": 120.71079851686954, |
|
"min": 23.427999913692474, |
|
"max": 120.71079851686954, |
|
"count": 17 |
|
}, |
|
"Pyramids.Policy.ExtrinsicReward.mean": { |
|
"value": 1.4720829087423115, |
|
"min": 0.9842666441367732, |
|
"max": 1.8021538395148058, |
|
"count": 17 |
|
}, |
|
"Pyramids.Policy.ExtrinsicReward.sum": { |
|
"value": 120.71079851686954, |
|
"min": 23.427999913692474, |
|
"max": 120.71079851686954, |
|
"count": 17 |
|
}, |
|
"Pyramids.Policy.RndReward.mean": { |
|
"value": 0.039570829975518126, |
|
"min": 0.027655479211646777, |
|
"max": 0.07700000182942152, |
|
"count": 17 |
|
}, |
|
"Pyramids.Policy.RndReward.sum": { |
|
"value": 3.2448080579924863, |
|
"min": 0.3595212297514081, |
|
"max": 5.544000131718349, |
|
"count": 17 |
|
}, |
|
"Pyramids.Losses.PolicyLoss.mean": { |
|
"value": 0.06957989918279323, |
|
"min": 0.0650359852782761, |
|
"max": 0.07350506128487824, |
|
"count": 17 |
|
}, |
|
"Pyramids.Losses.PolicyLoss.sum": { |
|
"value": 0.20873969754837968, |
|
"min": 0.0650359852782761, |
|
"max": 0.214029216568128, |
|
"count": 17 |
|
}, |
|
"Pyramids.Losses.ValueLoss.mean": { |
|
"value": 0.016916838877713652, |
|
"min": 0.012689931795026633, |
|
"max": 0.23801002937717364, |
|
"count": 17 |
|
}, |
|
"Pyramids.Losses.ValueLoss.sum": { |
|
"value": 0.05075051663314095, |
|
"min": 0.018842904370103497, |
|
"max": 0.7140300881315209, |
|
"count": 17 |
|
}, |
|
"Pyramids.Policy.LearningRate.mean": { |
|
"value": 3.4420321860222244e-06, |
|
"min": 3.4420321860222244e-06, |
|
"max": 9.751626749459999e-05, |
|
"count": 17 |
|
}, |
|
"Pyramids.Policy.LearningRate.sum": { |
|
"value": 1.0326096558066673e-05, |
|
"min": 1.0326096558066673e-05, |
|
"max": 0.000277689207437, |
|
"count": 17 |
|
}, |
|
"Pyramids.Policy.Epsilon.mean": { |
|
"value": 0.1011473111111111, |
|
"min": 0.1011473111111111, |
|
"max": 0.1325054, |
|
"count": 17 |
|
}, |
|
"Pyramids.Policy.Epsilon.sum": { |
|
"value": 0.3034419333333333, |
|
"min": 0.1325054, |
|
"max": 0.392563, |
|
"count": 17 |
|
}, |
|
"Pyramids.Policy.Beta.mean": { |
|
"value": 0.0001246163800000001, |
|
"min": 0.0001246163800000001, |
|
"max": 0.00325728946, |
|
"count": 17 |
|
}, |
|
"Pyramids.Policy.Beta.sum": { |
|
"value": 0.0003738491400000003, |
|
"min": 0.0003738491400000003, |
|
"max": 0.009277043700000001, |
|
"count": 17 |
|
}, |
|
"Pyramids.Losses.RNDLoss.mean": { |
|
"value": 0.009489244781434536, |
|
"min": 0.009489244781434536, |
|
"max": 0.013286218047142029, |
|
"count": 17 |
|
}, |
|
"Pyramids.Losses.RNDLoss.sum": { |
|
"value": 0.028467733412981033, |
|
"min": 0.013286218047142029, |
|
"max": 0.037529509514570236, |
|
"count": 17 |
|
}, |
|
"Pyramids.IsTraining.mean": { |
|
"value": 1.0, |
|
"min": 1.0, |
|
"max": 1.0, |
|
"count": 17 |
|
}, |
|
"Pyramids.IsTraining.sum": { |
|
"value": 1.0, |
|
"min": 1.0, |
|
"max": 1.0, |
|
"count": 17 |
|
} |
|
}, |
|
"metadata": { |
|
"timer_format_version": "0.1.0", |
|
"start_time_seconds": "1657475177", |
|
"python_version": "3.9.12 (main, Apr 5 2022, 06:56:58) \n[GCC 7.5.0]", |
|
"command_line_arguments": "/home/croumegous/anaconda3/bin/mlagents-learn ./config/ppo/PyramidsRND.yaml --env=./trained-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids Training --no-graphics --resume --num-envs=6", |
|
"mlagents_version": "0.29.0", |
|
"mlagents_envs_version": "0.29.0", |
|
"communication_protocol_version": "1.5.0", |
|
"pytorch_version": "1.8.1+cu102", |
|
"numpy_version": "1.21.2", |
|
"end_time_seconds": "1657475781" |
|
}, |
|
"total": 604.4553445449856, |
|
"count": 1, |
|
"self": 0.5220658960170113, |
|
"children": { |
|
"run_training.setup": { |
|
"total": 0.1380659579881467, |
|
"count": 1, |
|
"self": 0.1380659579881467 |
|
}, |
|
"TrainerController.start_learning": { |
|
"total": 603.7952126909804, |
|
"count": 1, |
|
"self": 0.6036529306147713, |
|
"children": { |
|
"TrainerController._reset_env": { |
|
"total": 1.094167639996158, |
|
"count": 1, |
|
"self": 1.094167639996158 |
|
}, |
|
"TrainerController.advance": { |
|
"total": 602.0302254493581, |
|
"count": 14292, |
|
"self": 0.6131680982653052, |
|
"children": { |
|
"env_step": { |
|
"total": 215.26839798039873, |
|
"count": 14292, |
|
"self": 102.20081120968098, |
|
"children": { |
|
"SubprocessEnvManager._take_step": { |
|
"total": 112.53998055655393, |
|
"count": 32448, |
|
"self": 3.326057362719439, |
|
"children": { |
|
"TorchPolicy.evaluate": { |
|
"total": 109.21392319383449, |
|
"count": 31593, |
|
"self": 13.063611366873374, |
|
"children": { |
|
"TorchPolicy.sample_actions": { |
|
"total": 96.15031182696112, |
|
"count": 31593, |
|
"self": 96.15031182696112 |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"workers": { |
|
"total": 0.5276062141638249, |
|
"count": 14292, |
|
"self": 0.0, |
|
"children": { |
|
"worker_root": { |
|
"total": 3620.9184799286013, |
|
"count": 32446, |
|
"is_parallel": true, |
|
"self": 2760.676755047578, |
|
"children": { |
|
"run_training.setup": { |
|
"total": 0.0, |
|
"count": 0, |
|
"is_parallel": true, |
|
"self": 0.0, |
|
"children": { |
|
"steps_from_proto": { |
|
"total": 0.009709863021271303, |
|
"count": 6, |
|
"is_parallel": true, |
|
"self": 0.0031293840147554874, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 0.006580479006515816, |
|
"count": 48, |
|
"is_parallel": true, |
|
"self": 0.006580479006515816 |
|
} |
|
} |
|
}, |
|
"UnityEnvironment.step": { |
|
"total": 0.26533120800741017, |
|
"count": 6, |
|
"is_parallel": true, |
|
"self": 0.0023486900026910007, |
|
"children": { |
|
"UnityEnvironment._generate_step_input": { |
|
"total": 0.0019346830085851252, |
|
"count": 6, |
|
"is_parallel": true, |
|
"self": 0.0019346830085851252 |
|
}, |
|
"communicator.exchange": { |
|
"total": 0.2523903500114102, |
|
"count": 6, |
|
"is_parallel": true, |
|
"self": 0.2523903500114102 |
|
}, |
|
"steps_from_proto": { |
|
"total": 0.008657484984723851, |
|
"count": 6, |
|
"is_parallel": true, |
|
"self": 0.0023871990269981325, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 0.006270285957725719, |
|
"count": 48, |
|
"is_parallel": true, |
|
"self": 0.006270285957725719 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"UnityEnvironment.step": { |
|
"total": 860.2417248810234, |
|
"count": 32440, |
|
"is_parallel": true, |
|
"self": 11.578526362165576, |
|
"children": { |
|
"UnityEnvironment._generate_step_input": { |
|
"total": 9.945916284690611, |
|
"count": 32440, |
|
"is_parallel": true, |
|
"self": 9.945916284690611 |
|
}, |
|
"communicator.exchange": { |
|
"total": 797.9835143611999, |
|
"count": 32440, |
|
"is_parallel": true, |
|
"self": 797.9835143611999 |
|
}, |
|
"steps_from_proto": { |
|
"total": 40.73376787296729, |
|
"count": 32440, |
|
"is_parallel": true, |
|
"self": 10.74560030020075, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 29.988167572766542, |
|
"count": 259520, |
|
"is_parallel": true, |
|
"self": 29.988167572766542 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"trainer_advance": { |
|
"total": 386.1486593706941, |
|
"count": 14292, |
|
"self": 1.1303736354166176, |
|
"children": { |
|
"process_trajectory": { |
|
"total": 98.46494501631241, |
|
"count": 14292, |
|
"self": 98.38362689132919, |
|
"children": { |
|
"RLTrainer._checkpoint": { |
|
"total": 0.08131812498322688, |
|
"count": 1, |
|
"self": 0.08131812498322688 |
|
} |
|
} |
|
}, |
|
"_update_policy": { |
|
"total": 286.55334071896505, |
|
"count": 40, |
|
"self": 102.66448892449262, |
|
"children": { |
|
"TorchPPOOptimizer.update": { |
|
"total": 183.88885179447243, |
|
"count": 11538, |
|
"self": 183.88885179447243 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"trainer_threads": { |
|
"total": 9.369978215545416e-07, |
|
"count": 1, |
|
"self": 9.369978215545416e-07 |
|
}, |
|
"TrainerController._save_models": { |
|
"total": 0.06716573401354253, |
|
"count": 1, |
|
"self": 0.001113346021156758, |
|
"children": { |
|
"RLTrainer._checkpoint": { |
|
"total": 0.06605238799238577, |
|
"count": 1, |
|
"self": 0.06605238799238577 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |