|
{ |
|
"name": "root", |
|
"gauges": { |
|
"SoccerTwos.Policy.Entropy.mean": { |
|
"value": 1.4520150423049927, |
|
"min": 0.7600547075271606, |
|
"max": 2.7271010875701904, |
|
"count": 3720 |
|
}, |
|
"SoccerTwos.Policy.Entropy.sum": { |
|
"value": 29969.58984375, |
|
"min": 7536.6240234375, |
|
"max": 93600.9609375, |
|
"count": 3720 |
|
}, |
|
"SoccerTwos.Environment.EpisodeLength.mean": { |
|
"value": 60.426829268292686, |
|
"min": 45.81730769230769, |
|
"max": 999.0, |
|
"count": 3720 |
|
}, |
|
"SoccerTwos.Environment.EpisodeLength.sum": { |
|
"value": 19820.0, |
|
"min": 728.0, |
|
"max": 31968.0, |
|
"count": 3720 |
|
}, |
|
"SoccerTwos.Step.mean": { |
|
"value": 49999982.0, |
|
"min": 9719129.0, |
|
"max": 49999982.0, |
|
"count": 4029 |
|
}, |
|
"SoccerTwos.Step.sum": { |
|
"value": 49999982.0, |
|
"min": 9719129.0, |
|
"max": 49999982.0, |
|
"count": 4029 |
|
}, |
|
"SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { |
|
"value": 0.0003452410746831447, |
|
"min": -0.13563020527362823, |
|
"max": 0.15037940442562103, |
|
"count": 4029 |
|
}, |
|
"SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { |
|
"value": 0.05627429485321045, |
|
"min": -21.247425079345703, |
|
"max": 21.253253936767578, |
|
"count": 4029 |
|
}, |
|
"SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { |
|
"value": -0.0007321242010220885, |
|
"min": -0.13747014105319977, |
|
"max": 0.1504291594028473, |
|
"count": 4029 |
|
}, |
|
"SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { |
|
"value": -0.11933624744415283, |
|
"min": -22.01276397705078, |
|
"max": 21.558879852294922, |
|
"count": 4029 |
|
}, |
|
"SoccerTwos.Environment.CumulativeReward.mean": { |
|
"value": 0.0, |
|
"min": 0.0, |
|
"max": 0.0, |
|
"count": 4029 |
|
}, |
|
"SoccerTwos.Environment.CumulativeReward.sum": { |
|
"value": 0.0, |
|
"min": 0.0, |
|
"max": 0.0, |
|
"count": 4029 |
|
}, |
|
"SoccerTwos.Policy.ExtrinsicReward.mean": { |
|
"value": -0.0448466232217894, |
|
"min": -0.7511777778466543, |
|
"max": 0.46390356974942343, |
|
"count": 4029 |
|
}, |
|
"SoccerTwos.Policy.ExtrinsicReward.sum": { |
|
"value": -7.309999585151672, |
|
"min": -65.32599985599518, |
|
"max": 54.91760015487671, |
|
"count": 4029 |
|
}, |
|
"SoccerTwos.Environment.GroupCumulativeReward.mean": { |
|
"value": -0.0448466232217894, |
|
"min": -0.7511777778466543, |
|
"max": 0.46390356974942343, |
|
"count": 4029 |
|
}, |
|
"SoccerTwos.Environment.GroupCumulativeReward.sum": { |
|
"value": -7.309999585151672, |
|
"min": -65.32599985599518, |
|
"max": 54.91760015487671, |
|
"count": 4029 |
|
}, |
|
"SoccerTwos.IsTraining.mean": { |
|
"value": 1.0, |
|
"min": 1.0, |
|
"max": 1.0, |
|
"count": 4029 |
|
}, |
|
"SoccerTwos.IsTraining.sum": { |
|
"value": 1.0, |
|
"min": 1.0, |
|
"max": 1.0, |
|
"count": 4029 |
|
}, |
|
"SoccerTwos.Losses.PolicyLoss.mean": { |
|
"value": 0.016204263491090387, |
|
"min": 0.011210557220814129, |
|
"max": 0.025820606861573954, |
|
"count": 1769 |
|
}, |
|
"SoccerTwos.Losses.PolicyLoss.sum": { |
|
"value": 0.016204263491090387, |
|
"min": 0.011210557220814129, |
|
"max": 0.025820606861573954, |
|
"count": 1769 |
|
}, |
|
"SoccerTwos.Losses.ValueLoss.mean": { |
|
"value": 0.10153596500555674, |
|
"min": 8.006682608172584e-12, |
|
"max": 0.11404849837223689, |
|
"count": 1769 |
|
}, |
|
"SoccerTwos.Losses.ValueLoss.sum": { |
|
"value": 0.10153596500555674, |
|
"min": 8.006682608172584e-12, |
|
"max": 0.11404849837223689, |
|
"count": 1769 |
|
}, |
|
"SoccerTwos.Losses.BaselineLoss.mean": { |
|
"value": 0.10298408692081769, |
|
"min": 9.83027506948474e-12, |
|
"max": 0.11587948948144913, |
|
"count": 1769 |
|
}, |
|
"SoccerTwos.Losses.BaselineLoss.sum": { |
|
"value": 0.10298408692081769, |
|
"min": 9.83027506948474e-12, |
|
"max": 0.11587948948144913, |
|
"count": 1769 |
|
}, |
|
"SoccerTwos.Policy.LearningRate.mean": { |
|
"value": 0.0003, |
|
"min": 0.0003, |
|
"max": 0.0003, |
|
"count": 1769 |
|
}, |
|
"SoccerTwos.Policy.LearningRate.sum": { |
|
"value": 0.0003, |
|
"min": 0.0003, |
|
"max": 0.0003, |
|
"count": 1769 |
|
}, |
|
"SoccerTwos.Policy.Epsilon.mean": { |
|
"value": 0.20000000000000007, |
|
"min": 0.19999999999999993, |
|
"max": 0.20000000000000007, |
|
"count": 1769 |
|
}, |
|
"SoccerTwos.Policy.Epsilon.sum": { |
|
"value": 0.20000000000000007, |
|
"min": 0.19999999999999993, |
|
"max": 0.20000000000000007, |
|
"count": 1769 |
|
}, |
|
"SoccerTwos.Policy.Beta.mean": { |
|
"value": 0.005000000000000001, |
|
"min": 0.005, |
|
"max": 0.005000000000000001, |
|
"count": 1769 |
|
}, |
|
"SoccerTwos.Policy.Beta.sum": { |
|
"value": 0.005000000000000001, |
|
"min": 0.005, |
|
"max": 0.005000000000000001, |
|
"count": 1769 |
|
}, |
|
"SoccerTwos.Self-play.ELO.mean": { |
|
"value": 1489.9007551486072, |
|
"min": 1198.8917852086022, |
|
"max": 1531.3354151309672, |
|
"count": 2952 |
|
}, |
|
"SoccerTwos.Self-play.ELO.sum": { |
|
"value": 244343.7238443716, |
|
"min": 2397.7835704172044, |
|
"max": 314247.1395444628, |
|
"count": 2952 |
|
} |
|
}, |
|
"metadata": { |
|
"timer_format_version": "0.1.0", |
|
"start_time_seconds": "1681964592", |
|
"python_version": "3.9.16 | packaged by conda-forge | (main, Feb 1 2023, 21:39:03) \n[GCC 11.3.0]", |
|
"command_line_arguments": "/home/feabries/anaconda3/envs/rl/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos.x86_64 --run-id=SoccerTwos --no-graphics --resume", |
|
"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": "1682004648" |
|
}, |
|
"total": 40056.408814703, |
|
"count": 1, |
|
"self": 0.21825561599689536, |
|
"children": { |
|
"run_training.setup": { |
|
"total": 0.005742882000049576, |
|
"count": 1, |
|
"self": 0.005742882000049576 |
|
}, |
|
"TrainerController.start_learning": { |
|
"total": 40056.184816205, |
|
"count": 1, |
|
"self": 40.46359234739066, |
|
"children": { |
|
"TrainerController._reset_env": { |
|
"total": 19.97204129998886, |
|
"count": 393, |
|
"self": 19.97204129998886 |
|
}, |
|
"TrainerController.advance": { |
|
"total": 39995.59990613362, |
|
"count": 2709289, |
|
"self": 40.555937749843, |
|
"children": { |
|
"env_step": { |
|
"total": 30263.74818917158, |
|
"count": 2709289, |
|
"self": 22358.534063959713, |
|
"children": { |
|
"SubprocessEnvManager._take_step": { |
|
"total": 7880.196310942975, |
|
"count": 2709290, |
|
"self": 214.63259805849884, |
|
"children": { |
|
"TorchPolicy.evaluate": { |
|
"total": 7665.563712884476, |
|
"count": 5097064, |
|
"self": 7665.563712884476 |
|
} |
|
} |
|
}, |
|
"workers": { |
|
"total": 25.017814268891243, |
|
"count": 2709289, |
|
"self": 0.0, |
|
"children": { |
|
"worker_root": { |
|
"total": 41802.571554351474, |
|
"count": 2709289, |
|
"is_parallel": true, |
|
"self": 23751.305271399193, |
|
"children": { |
|
"run_training.setup": { |
|
"total": 0.005742882000049576, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0, |
|
"children": { |
|
"steps_from_proto": { |
|
"total": 0.0014299950000804529, |
|
"count": 2, |
|
"is_parallel": true, |
|
"self": 0.000360868000143455, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 0.0010691269999369979, |
|
"count": 8, |
|
"is_parallel": true, |
|
"self": 0.0010691269999369979 |
|
} |
|
} |
|
}, |
|
"UnityEnvironment.step": { |
|
"total": 0.01554494800006978, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0003586600000744511, |
|
"children": { |
|
"UnityEnvironment._generate_step_input": { |
|
"total": 0.00028393699994921917, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.00028393699994921917 |
|
}, |
|
"communicator.exchange": { |
|
"total": 0.013777870000012626, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.013777870000012626 |
|
}, |
|
"steps_from_proto": { |
|
"total": 0.0011244810000334837, |
|
"count": 2, |
|
"is_parallel": true, |
|
"self": 0.000244575999886365, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 0.0008799050001471187, |
|
"count": 8, |
|
"is_parallel": true, |
|
"self": 0.0008799050001471187 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"steps_from_proto": { |
|
"total": 0.48583388100723823, |
|
"count": 784, |
|
"is_parallel": true, |
|
"self": 0.09789167203030047, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 0.38794220897693776, |
|
"count": 3136, |
|
"is_parallel": true, |
|
"self": 0.38794220897693776 |
|
} |
|
} |
|
}, |
|
"UnityEnvironment.step": { |
|
"total": 18050.774706189273, |
|
"count": 2709287, |
|
"is_parallel": true, |
|
"self": 1048.0504326501796, |
|
"children": { |
|
"UnityEnvironment._generate_step_input": { |
|
"total": 664.18439669697, |
|
"count": 2709287, |
|
"is_parallel": true, |
|
"self": 664.18439669697 |
|
}, |
|
"communicator.exchange": { |
|
"total": 13170.417143587474, |
|
"count": 2709287, |
|
"is_parallel": true, |
|
"self": 13170.417143587474 |
|
}, |
|
"steps_from_proto": { |
|
"total": 3168.122733254651, |
|
"count": 5418574, |
|
"is_parallel": true, |
|
"self": 641.2504717901356, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 2526.8722614645153, |
|
"count": 21674296, |
|
"is_parallel": true, |
|
"self": 2526.8722614645153 |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"TrainerController.start_learning": { |
|
"total": 0.0, |
|
"count": 0, |
|
"is_parallel": true, |
|
"self": 0.0, |
|
"children": { |
|
"TrainerController._reset_env": { |
|
"total": 14.475984652999841, |
|
"count": 19, |
|
"is_parallel": true, |
|
"self": 14.475984652999841 |
|
}, |
|
"TrainerController.advance": { |
|
"total": 1787.0852316278947, |
|
"count": 122151, |
|
"is_parallel": true, |
|
"self": 1.778869509944343, |
|
"children": { |
|
"env_step": { |
|
"total": 1399.5545137969136, |
|
"count": 122151, |
|
"is_parallel": true, |
|
"self": 1019.8674870789116, |
|
"children": { |
|
"SubprocessEnvManager._take_step": { |
|
"total": 378.55412077396954, |
|
"count": 122152, |
|
"is_parallel": true, |
|
"self": 10.628132477027293, |
|
"children": { |
|
"TorchPolicy.evaluate": { |
|
"total": 367.92598829694225, |
|
"count": 244094, |
|
"is_parallel": true, |
|
"self": 367.92598829694225 |
|
} |
|
} |
|
}, |
|
"workers": { |
|
"total": 1.1097727310318533, |
|
"count": 122151, |
|
"is_parallel": true, |
|
"self": 0.0, |
|
"children": { |
|
"worker_root": { |
|
"total": 1800.3439497059958, |
|
"count": 122151, |
|
"is_parallel": true, |
|
"self": 973.1760859440178, |
|
"children": { |
|
"run_training.setup": { |
|
"total": 0.0, |
|
"count": 0, |
|
"is_parallel": true, |
|
"self": 0.0, |
|
"children": { |
|
"steps_from_proto": { |
|
"total": 0.0014299950000804529, |
|
"count": 2, |
|
"is_parallel": true, |
|
"self": 0.000360868000143455, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 0.0010691269999369979, |
|
"count": 8, |
|
"is_parallel": true, |
|
"self": 0.0010691269999369979 |
|
} |
|
} |
|
}, |
|
"UnityEnvironment.step": { |
|
"total": 0.01554494800006978, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0003586600000744511, |
|
"children": { |
|
"UnityEnvironment._generate_step_input": { |
|
"total": 0.00028393699994921917, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.00028393699994921917 |
|
}, |
|
"communicator.exchange": { |
|
"total": 0.013777870000012626, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.013777870000012626 |
|
}, |
|
"steps_from_proto": { |
|
"total": 0.0011244810000334837, |
|
"count": 2, |
|
"is_parallel": true, |
|
"self": 0.000244575999886365, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 0.0008799050001471187, |
|
"count": 8, |
|
"is_parallel": true, |
|
"self": 0.0008799050001471187 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"steps_from_proto": { |
|
"total": 0.020454086999961874, |
|
"count": 36, |
|
"is_parallel": true, |
|
"self": 0.004265346001602666, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 0.016188740998359208, |
|
"count": 144, |
|
"is_parallel": true, |
|
"self": 0.016188740998359208 |
|
} |
|
} |
|
}, |
|
"UnityEnvironment.step": { |
|
"total": 827.147409674978, |
|
"count": 122150, |
|
"is_parallel": true, |
|
"self": 45.35365158468926, |
|
"children": { |
|
"UnityEnvironment._generate_step_input": { |
|
"total": 30.92889768201394, |
|
"count": 122150, |
|
"is_parallel": true, |
|
"self": 30.92889768201394 |
|
}, |
|
"communicator.exchange": { |
|
"total": 610.5170124280796, |
|
"count": 122150, |
|
"is_parallel": true, |
|
"self": 610.5170124280796 |
|
}, |
|
"steps_from_proto": { |
|
"total": 140.34784798019518, |
|
"count": 244300, |
|
"is_parallel": true, |
|
"self": 28.630700330274976, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 111.71714764992021, |
|
"count": 977200, |
|
"is_parallel": true, |
|
"self": 111.71714764992021 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"steps_from_proto": { |
|
"total": 0.0017852500004664762, |
|
"count": 2, |
|
"is_parallel": true, |
|
"self": 0.00036059700050827814, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 0.001424652999958198, |
|
"count": 8, |
|
"is_parallel": true, |
|
"self": 0.001424652999958198 |
|
} |
|
} |
|
}, |
|
"UnityEnvironment.step": { |
|
"total": 0.02134796300015296, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.00043702100083464757, |
|
"children": { |
|
"UnityEnvironment._generate_step_input": { |
|
"total": 0.00027023699976780335, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.00027023699976780335 |
|
}, |
|
"communicator.exchange": { |
|
"total": 0.019328221999785455, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.019328221999785455 |
|
}, |
|
"steps_from_proto": { |
|
"total": 0.0013124829997650522, |
|
"count": 2, |
|
"is_parallel": true, |
|
"self": 0.000258777000453847, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 0.0010537059993112052, |
|
"count": 8, |
|
"is_parallel": true, |
|
"self": 0.0010537059993112052 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"trainer_advance": { |
|
"total": 385.75184832103673, |
|
"count": 122151, |
|
"is_parallel": true, |
|
"self": 11.014248064073627, |
|
"children": { |
|
"process_trajectory": { |
|
"total": 95.58874794096005, |
|
"count": 122151, |
|
"is_parallel": true, |
|
"self": 94.95093006796037, |
|
"children": { |
|
"RLTrainer._checkpoint": { |
|
"total": 0.6378178729996762, |
|
"count": 4, |
|
"is_parallel": true, |
|
"self": 0.6378178729996762 |
|
} |
|
} |
|
}, |
|
"_update_policy": { |
|
"total": 279.14885231600306, |
|
"count": 61, |
|
"is_parallel": true, |
|
"self": 179.95948405299464, |
|
"children": { |
|
"TorchPOCAOptimizer.update": { |
|
"total": 99.18936826300842, |
|
"count": 2745, |
|
"is_parallel": true, |
|
"self": 99.18936826300842 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"trainer_advance": { |
|
"total": 9691.295779212192, |
|
"count": 2709289, |
|
"self": 256.6792850401034, |
|
"children": { |
|
"process_trajectory": { |
|
"total": 3543.0408101341645, |
|
"count": 2709289, |
|
"self": 3530.2062764951547, |
|
"children": { |
|
"RLTrainer._checkpoint": { |
|
"total": 12.834533639009805, |
|
"count": 81, |
|
"self": 12.834533639009805 |
|
} |
|
} |
|
}, |
|
"_update_policy": { |
|
"total": 5891.575684037924, |
|
"count": 1769, |
|
"self": 3768.1039287448225, |
|
"children": { |
|
"TorchPOCAOptimizer.update": { |
|
"total": 2123.471755293101, |
|
"count": 57972, |
|
"self": 2123.471755293101 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"trainer_threads": { |
|
"total": 5.370020517148077e-07, |
|
"count": 1, |
|
"self": 5.370020517148077e-07 |
|
}, |
|
"TrainerController._save_models": { |
|
"total": 0.14927588700084016, |
|
"count": 1, |
|
"self": 0.0010382600012235343, |
|
"children": { |
|
"RLTrainer._checkpoint": { |
|
"total": 0.14823762699961662, |
|
"count": 1, |
|
"self": 0.14823762699961662 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |