Liamdu's picture
First Push
3d56202 verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.6484993696212769,
"min": 0.6484993696212769,
"max": 2.8676986694335938,
"count": 133
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 6170.4716796875,
"min": 6170.4716796875,
"max": 29368.1015625,
"count": 133
},
"SnowballTarget.Step.mean": {
"value": 1329952.0,
"min": 9952.0,
"max": 1329952.0,
"count": 133
},
"SnowballTarget.Step.sum": {
"value": 1329952.0,
"min": 9952.0,
"max": 1329952.0,
"count": 133
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
"value": 14.083314895629883,
"min": 0.281077116727829,
"max": 14.268333435058594,
"count": 133
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2746.246337890625,
"min": 54.528961181640625,
"max": 2924.026611328125,
"count": 133
},
"SnowballTarget.Environment.EpisodeLength.mean": {
"value": 199.0,
"min": 199.0,
"max": 199.0,
"count": 133
},
"SnowballTarget.Environment.EpisodeLength.sum": {
"value": 8756.0,
"min": 8756.0,
"max": 10945.0,
"count": 133
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.06667169780851455,
"min": 0.05788506969544745,
"max": 0.0779840610978592,
"count": 133
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2666867912340582,
"min": 0.2350830863262458,
"max": 0.389920305489296,
"count": 133
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.15595443882778579,
"min": 0.11321260226324348,
"max": 0.29578475376554564,
"count": 133
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.6238177553111431,
"min": 0.4528504090529739,
"max": 1.4115312902950772,
"count": 133
},
"SnowballTarget.Policy.LearningRate.mean": {
"value": 0.0001011882662706,
"min": 0.0001011882662706,
"max": 0.00029918820027059994,
"count": 133
},
"SnowballTarget.Policy.LearningRate.sum": {
"value": 0.0004047530650824,
"min": 0.0004047530650824,
"max": 0.0014885160038279998,
"count": 133
},
"SnowballTarget.Policy.Epsilon.mean": {
"value": 0.13372940000000003,
"min": 0.13372940000000003,
"max": 0.1997294,
"count": 133
},
"SnowballTarget.Policy.Epsilon.sum": {
"value": 0.5349176000000001,
"min": 0.5349176000000001,
"max": 0.996172,
"count": 133
},
"SnowballTarget.Policy.Beta.mean": {
"value": 0.0016930970600000004,
"min": 0.0016930970600000004,
"max": 0.004986497059999999,
"count": 133
},
"SnowballTarget.Policy.Beta.sum": {
"value": 0.0067723882400000015,
"min": 0.0067723882400000015,
"max": 0.024808982800000004,
"count": 133
},
"SnowballTarget.Environment.CumulativeReward.mean": {
"value": 27.955555555555556,
"min": 3.090909090909091,
"max": 28.454545454545453,
"count": 133
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1258.0,
"min": 136.0,
"max": 1543.0,
"count": 133
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 27.955555555555556,
"min": 3.090909090909091,
"max": 28.454545454545453,
"count": 133
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1258.0,
"min": 136.0,
"max": 1543.0,
"count": 133
},
"SnowballTarget.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 133
},
"SnowballTarget.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 133
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1708948277",
"python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [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=SnowballTarget2 --no-graphics",
"mlagents_version": "1.1.0.dev0",
"mlagents_envs_version": "1.1.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.2.1+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1708951111"
},
"total": 2834.360201249,
"count": 1,
"self": 0.005333064999831549,
"children": {
"run_training.setup": {
"total": 0.046772223000061786,
"count": 1,
"self": 0.046772223000061786
},
"TrainerController.start_learning": {
"total": 2834.308095961,
"count": 1,
"self": 4.090742536935068,
"children": {
"TrainerController._reset_env": {
"total": 2.1845971469999768,
"count": 1,
"self": 2.1845971469999768
},
"TrainerController.advance": {
"total": 2827.9469027110654,
"count": 121234,
"self": 1.6712141130055898,
"children": {
"env_step": {
"total": 2826.27568859806,
"count": 121234,
"self": 1833.077982510164,
"children": {
"SubprocessEnvManager._take_step": {
"total": 991.4470818789382,
"count": 121234,
"self": 9.362995876978971,
"children": {
"TorchPolicy.evaluate": {
"total": 982.0840860019592,
"count": 121234,
"self": 982.0840860019592
}
}
},
"workers": {
"total": 1.7506242089576745,
"count": 121233,
"self": 0.0,
"children": {
"worker_root": {
"total": 2826.9085666320766,
"count": 121233,
"is_parallel": true,
"self": 1396.375692659014,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.002167156999917097,
"count": 1,
"is_parallel": true,
"self": 0.0006473810001352831,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0015197759997818139,
"count": 10,
"is_parallel": true,
"self": 0.0015197759997818139
}
}
},
"UnityEnvironment.step": {
"total": 0.03687019299991334,
"count": 1,
"is_parallel": true,
"self": 0.0005768049999232971,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00039715900004466675,
"count": 1,
"is_parallel": true,
"self": 0.00039715900004466675
},
"communicator.exchange": {
"total": 0.033946359999958986,
"count": 1,
"is_parallel": true,
"self": 0.033946359999958986
},
"steps_from_proto": {
"total": 0.0019498689999863927,
"count": 1,
"is_parallel": true,
"self": 0.00038146200017763476,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001568406999808758,
"count": 10,
"is_parallel": true,
"self": 0.001568406999808758
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1430.5328739730626,
"count": 121232,
"is_parallel": true,
"self": 68.33889188997227,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 34.54267491996188,
"count": 121232,
"is_parallel": true,
"self": 34.54267491996188
},
"communicator.exchange": {
"total": 1110.8913708231398,
"count": 121232,
"is_parallel": true,
"self": 1110.8913708231398
},
"steps_from_proto": {
"total": 216.7599363399886,
"count": 121232,
"is_parallel": true,
"self": 39.588452338787306,
"children": {
"_process_rank_one_or_two_observation": {
"total": 177.1714840012013,
"count": 1212320,
"is_parallel": true,
"self": 177.1714840012013
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.0010158569998566236,
"count": 1,
"self": 0.0010158569998566236,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 2793.7884553791428,
"count": 4247561,
"is_parallel": true,
"self": 88.02062289315154,
"children": {
"process_trajectory": {
"total": 1529.5097596759847,
"count": 4247561,
"is_parallel": true,
"self": 1524.975416191984,
"children": {
"RLTrainer._checkpoint": {
"total": 4.534343484000601,
"count": 26,
"is_parallel": true,
"self": 4.534343484000601
}
}
},
"_update_policy": {
"total": 1176.2580728100065,
"count": 606,
"is_parallel": true,
"self": 343.2950407260389,
"children": {
"TorchPPOOptimizer.update": {
"total": 832.9630320839676,
"count": 30903,
"is_parallel": true,
"self": 832.9630320839676
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.08483770899965748,
"count": 1,
"self": 0.0009077349996005069,
"children": {
"RLTrainer._checkpoint": {
"total": 0.08392997400005697,
"count": 1,
"self": 0.08392997400005697
}
}
}
}
}
}
}