miki030's picture
First Push
327fb37
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.8823042511940002,
"min": 0.8823042511940002,
"max": 2.8617947101593018,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 8433.9462890625,
"min": 8433.9462890625,
"max": 29339.119140625,
"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": 13.163704872131348,
"min": 0.35610005259513855,
"max": 13.163704872131348,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2566.92236328125,
"min": 69.08341217041016,
"max": 2656.87646484375,
"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": 0.06357967357896496,
"min": 0.06280317467993454,
"max": 0.07478976764689957,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.25431869431585985,
"min": 0.25431869431585985,
"max": 0.35722783077896264,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.19014497787929052,
"min": 0.12198345073927924,
"max": 0.28826586105952073,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7605799115171621,
"min": 0.48793380295711697,
"max": 1.3492245519278094,
"count": 20
},
"SnowballTarget.Policy.LearningRate.mean": {
"value": 8.082097306000005e-06,
"min": 8.082097306000005e-06,
"max": 0.000291882002706,
"count": 20
},
"SnowballTarget.Policy.LearningRate.sum": {
"value": 3.232838922400002e-05,
"min": 3.232838922400002e-05,
"max": 0.00138516003828,
"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": 26.84090909090909,
"min": 3.409090909090909,
"max": 26.84090909090909,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1181.0,
"min": 150.0,
"max": 1422.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 26.84090909090909,
"min": 3.409090909090909,
"max": 26.84090909090909,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1181.0,
"min": 150.0,
"max": 1422.0,
"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": "1682066354",
"python_version": "3.9.16 (main, Dec 7 2022, 01:11:51) \n[GCC 9.4.0]",
"command_line_arguments": "/usr/local/bin/mlagents-learn SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget2 --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": "1682066811"
},
"total": 456.4491206550001,
"count": 1,
"self": 0.7367769279990171,
"children": {
"run_training.setup": {
"total": 0.11367178800082911,
"count": 1,
"self": 0.11367178800082911
},
"TrainerController.start_learning": {
"total": 455.59867193900027,
"count": 1,
"self": 0.5841662090506361,
"children": {
"TrainerController._reset_env": {
"total": 3.6112415929992494,
"count": 1,
"self": 3.6112415929992494
},
"TrainerController.advance": {
"total": 451.0920741259506,
"count": 18221,
"self": 0.2787513340563237,
"children": {
"env_step": {
"total": 450.8133227918943,
"count": 18221,
"self": 330.1206377598892,
"children": {
"SubprocessEnvManager._take_step": {
"total": 120.40922207901804,
"count": 18221,
"self": 1.687300393012265,
"children": {
"TorchPolicy.evaluate": {
"total": 118.72192168600577,
"count": 18221,
"self": 118.72192168600577
}
}
},
"workers": {
"total": 0.28346295298706536,
"count": 18221,
"self": 0.0,
"children": {
"worker_root": {
"total": 454.00224620301105,
"count": 18221,
"is_parallel": true,
"self": 214.18907626193413,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0018151089998355019,
"count": 1,
"is_parallel": true,
"self": 0.0005546559996219003,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0012604530002136016,
"count": 10,
"is_parallel": true,
"self": 0.0012604530002136016
}
}
},
"UnityEnvironment.step": {
"total": 0.03950745300062408,
"count": 1,
"is_parallel": true,
"self": 0.0005969140001980122,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00033758399968064623,
"count": 1,
"is_parallel": true,
"self": 0.00033758399968064623
},
"communicator.exchange": {
"total": 0.036283547000493854,
"count": 1,
"is_parallel": true,
"self": 0.036283547000493854
},
"steps_from_proto": {
"total": 0.0022894080002515693,
"count": 1,
"is_parallel": true,
"self": 0.0006311730012384942,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0016582349990130751,
"count": 10,
"is_parallel": true,
"self": 0.0016582349990130751
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 239.81316994107692,
"count": 18220,
"is_parallel": true,
"self": 9.695779577288704,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.305905002966938,
"count": 18220,
"is_parallel": true,
"self": 5.305905002966938
},
"communicator.exchange": {
"total": 193.80134969893334,
"count": 18220,
"is_parallel": true,
"self": 193.80134969893334
},
"steps_from_proto": {
"total": 31.010135661887944,
"count": 18220,
"is_parallel": true,
"self": 6.158726809086147,
"children": {
"_process_rank_one_or_two_observation": {
"total": 24.851408852801796,
"count": 182200,
"is_parallel": true,
"self": 24.851408852801796
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.00015524500031460775,
"count": 1,
"self": 0.00015524500031460775,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 447.7440670608885,
"count": 398435,
"is_parallel": true,
"self": 9.716678189653976,
"children": {
"process_trajectory": {
"total": 245.81442900722595,
"count": 398435,
"is_parallel": true,
"self": 244.08567776822565,
"children": {
"RLTrainer._checkpoint": {
"total": 1.728751239000303,
"count": 4,
"is_parallel": true,
"self": 1.728751239000303
}
}
},
"_update_policy": {
"total": 192.21295986400855,
"count": 90,
"is_parallel": true,
"self": 69.32823111397374,
"children": {
"TorchPPOOptimizer.update": {
"total": 122.88472875003481,
"count": 4587,
"is_parallel": true,
"self": 122.88472875003481
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.3110347659994659,
"count": 1,
"self": 0.003566184999726829,
"children": {
"RLTrainer._checkpoint": {
"total": 0.30746858099973906,
"count": 1,
"self": 0.30746858099973906
}
}
}
}
}
}
}