kowalsky's picture
ppo-SnowballTarget
b1d5b54
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.8959912061691284,
"min": 0.8959912061691284,
"max": 2.8567588329315186,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 8554.923828125,
"min": 8554.923828125,
"max": 29256.06640625,
"count": 20
},
"SnowballTarget.Step.mean": {
"value": 199984.0,
"min": 9952.0,
"max": 199984.0,
"count": 20
},
"SnowballTarget.Step.sum": {
"value": 199984.0,
"min": 9952.0,
"max": 199984.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
"value": 13.153072357177734,
"min": 0.40350058674812317,
"max": 13.153072357177734,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2564.84912109375,
"min": 78.27911376953125,
"max": 2661.345703125,
"count": 20
},
"SnowballTarget.Environment.EpisodeLength.mean": {
"value": 199.0,
"min": 199.0,
"max": 199.0,
"count": 20
},
"SnowballTarget.Environment.EpisodeLength.sum": {
"value": 8756.0,
"min": 8756.0,
"max": 10945.0,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.06704840767619602,
"min": 0.06094029385952608,
"max": 0.07707991744631298,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2681936307047841,
"min": 0.25717640951259846,
"max": 0.36366128526609753,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.19458922221526212,
"min": 0.13375409936084978,
"max": 0.2717677593231201,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7783568888610485,
"min": 0.5350163974433991,
"max": 1.3588387966156004,
"count": 20
},
"SnowballTarget.Policy.LearningRate.mean": {
"value": 1.347009730600001e-05,
"min": 1.347009730600001e-05,
"max": 0.00048647000270600005,
"count": 20
},
"SnowballTarget.Policy.LearningRate.sum": {
"value": 5.388038922400004e-05,
"min": 5.388038922400004e-05,
"max": 0.00230860003828,
"count": 20
},
"SnowballTarget.Policy.Epsilon.mean": {
"value": 0.10269400000000001,
"min": 0.10269400000000001,
"max": 0.19729400000000002,
"count": 20
},
"SnowballTarget.Policy.Epsilon.sum": {
"value": 0.41077600000000003,
"min": 0.41077600000000003,
"max": 0.96172,
"count": 20
},
"SnowballTarget.Policy.Beta.mean": {
"value": 0.0001444306000000001,
"min": 0.0001444306000000001,
"max": 0.0048649706,
"count": 20
},
"SnowballTarget.Policy.Beta.sum": {
"value": 0.0005777224000000004,
"min": 0.0005777224000000004,
"max": 0.023089828,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.mean": {
"value": 25.704545454545453,
"min": 4.0227272727272725,
"max": 25.927272727272726,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1131.0,
"min": 177.0,
"max": 1426.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.704545454545453,
"min": 4.0227272727272725,
"max": 25.927272727272726,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1131.0,
"min": 177.0,
"max": 1426.0,
"count": 20
},
"SnowballTarget.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 20
},
"SnowballTarget.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 20
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1697782473",
"python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [GCC 11.4.0]",
"command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics",
"mlagents_version": "1.1.0.dev0",
"mlagents_envs_version": "1.1.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.1.0+cu118",
"numpy_version": "1.23.5",
"end_time_seconds": "1697782932"
},
"total": 459.6463920849999,
"count": 1,
"self": 0.7364332269999068,
"children": {
"run_training.setup": {
"total": 0.04342987199993331,
"count": 1,
"self": 0.04342987199993331
},
"TrainerController.start_learning": {
"total": 458.86652898600005,
"count": 1,
"self": 0.5243044430005739,
"children": {
"TrainerController._reset_env": {
"total": 8.760359839999865,
"count": 1,
"self": 8.760359839999865
},
"TrainerController.advance": {
"total": 449.44277761999933,
"count": 18203,
"self": 0.252186298015431,
"children": {
"env_step": {
"total": 449.1905913219839,
"count": 18203,
"self": 306.0898404359864,
"children": {
"SubprocessEnvManager._take_step": {
"total": 142.8293219989871,
"count": 18203,
"self": 1.421136611997781,
"children": {
"TorchPolicy.evaluate": {
"total": 141.40818538698932,
"count": 18203,
"self": 141.40818538698932
}
}
},
"workers": {
"total": 0.27142888701041556,
"count": 18203,
"self": 0.0,
"children": {
"worker_root": {
"total": 457.69256667400487,
"count": 18203,
"is_parallel": true,
"self": 226.94605388201353,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.004572165000126915,
"count": 1,
"is_parallel": true,
"self": 0.0030919930004529306,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0014801719996739848,
"count": 10,
"is_parallel": true,
"self": 0.0014801719996739848
}
}
},
"UnityEnvironment.step": {
"total": 0.03629106799985493,
"count": 1,
"is_parallel": true,
"self": 0.0007627959996625577,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00041554300014468026,
"count": 1,
"is_parallel": true,
"self": 0.00041554300014468026
},
"communicator.exchange": {
"total": 0.032914097000002585,
"count": 1,
"is_parallel": true,
"self": 0.032914097000002585
},
"steps_from_proto": {
"total": 0.0021986320000451087,
"count": 1,
"is_parallel": true,
"self": 0.0004322930001308123,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0017663389999142964,
"count": 10,
"is_parallel": true,
"self": 0.0017663389999142964
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 230.74651279199134,
"count": 18202,
"is_parallel": true,
"self": 10.369573113993056,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.284481323996715,
"count": 18202,
"is_parallel": true,
"self": 5.284481323996715
},
"communicator.exchange": {
"total": 182.18067273701308,
"count": 18202,
"is_parallel": true,
"self": 182.18067273701308
},
"steps_from_proto": {
"total": 32.91178561698848,
"count": 18202,
"is_parallel": true,
"self": 6.222919539010263,
"children": {
"_process_rank_one_or_two_observation": {
"total": 26.68886607797822,
"count": 182020,
"is_parallel": true,
"self": 26.68886607797822
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.00013589600007435365,
"count": 1,
"self": 0.00013589600007435365,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 445.75923234408515,
"count": 467926,
"is_parallel": true,
"self": 9.98863001197401,
"children": {
"process_trajectory": {
"total": 251.36608609411132,
"count": 467926,
"is_parallel": true,
"self": 250.65063359311148,
"children": {
"RLTrainer._checkpoint": {
"total": 0.7154525009998451,
"count": 4,
"is_parallel": true,
"self": 0.7154525009998451
}
}
},
"_update_policy": {
"total": 184.40451623799981,
"count": 90,
"is_parallel": true,
"self": 58.08203457499144,
"children": {
"TorchPPOOptimizer.update": {
"total": 126.32248166300838,
"count": 4587,
"is_parallel": true,
"self": 126.32248166300838
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.13895118700020248,
"count": 1,
"self": 0.0011480540001684858,
"children": {
"RLTrainer._checkpoint": {
"total": 0.137803133000034,
"count": 1,
"self": 0.137803133000034
}
}
}
}
}
}
}