LorChak's picture
First Push
900fc3c verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.9545086026191711,
"min": 0.9391207695007324,
"max": 1.0479693412780762,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 9743.6240234375,
"min": 9086.201171875,
"max": 10697.6708984375,
"count": 20
},
"SnowballTarget.Step.mean": {
"value": 699960.0,
"min": 509992.0,
"max": 699960.0,
"count": 20
},
"SnowballTarget.Step.sum": {
"value": 699960.0,
"min": 509992.0,
"max": 699960.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
"value": 13.043752670288086,
"min": 11.944348335266113,
"max": 13.043752670288086,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2543.53173828125,
"min": 2305.25927734375,
"max": 2657.7587890625,
"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.Environment.CumulativeReward.mean": {
"value": 26.068181818181817,
"min": 24.795454545454547,
"max": 26.204545454545453,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1147.0,
"min": 1091.0,
"max": 1435.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 26.068181818181817,
"min": 24.795454545454547,
"max": 26.204545454545453,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1147.0,
"min": 1091.0,
"max": 1435.0,
"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
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.035822989675216375,
"min": 0.02571102942974903,
"max": 0.042859831821018206,
"count": 19
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.035822989675216375,
"min": 0.02571102942974903,
"max": 0.042859831821018206,
"count": 19
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.20447064662973086,
"min": 0.1857440204374374,
"max": 0.22445170631011327,
"count": 19
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.20447064662973086,
"min": 0.1857440204374374,
"max": 0.22445170631011327,
"count": 19
},
"SnowballTarget.Policy.LearningRate.mean": {
"value": 5.109569725714209e-07,
"min": 5.109569725714209e-07,
"max": 8.09932158594286e-05,
"count": 19
},
"SnowballTarget.Policy.LearningRate.sum": {
"value": 5.109569725714209e-07,
"min": 5.109569725714209e-07,
"max": 8.09932158594286e-05,
"count": 19
},
"SnowballTarget.Policy.Epsilon.mean": {
"value": 0.10017028571428567,
"min": 0.10017028571428567,
"max": 0.1269977142857143,
"count": 19
},
"SnowballTarget.Policy.Epsilon.sum": {
"value": 0.10017028571428567,
"min": 0.10017028571428567,
"max": 0.1269977142857143,
"count": 19
},
"SnowballTarget.Policy.Beta.mean": {
"value": 1.849725714285702e-05,
"min": 1.849725714285702e-05,
"max": 0.001357185942857142,
"count": 19
},
"SnowballTarget.Policy.Beta.sum": {
"value": 1.849725714285702e-05,
"min": 1.849725714285702e-05,
"max": 0.001357185942857142,
"count": 19
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1735996791",
"python_version": "3.10.12 (main, Nov 6 2024, 20:22:13) [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 --resume",
"mlagents_version": "1.2.0.dev0",
"mlagents_envs_version": "1.2.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.5.1+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1735997191"
},
"total": 399.9202619810003,
"count": 1,
"self": 0.4796982510004,
"children": {
"run_training.setup": {
"total": 0.0578861000001325,
"count": 1,
"self": 0.0578861000001325
},
"TrainerController.start_learning": {
"total": 399.38267762999976,
"count": 1,
"self": 0.3915310579748166,
"children": {
"TrainerController._reset_env": {
"total": 1.9863931160000448,
"count": 1,
"self": 1.9863931160000448
},
"TrainerController.advance": {
"total": 396.91193451302524,
"count": 18192,
"self": 0.4041940640381654,
"children": {
"env_step": {
"total": 313.65146303799315,
"count": 18192,
"self": 237.38310407998324,
"children": {
"SubprocessEnvManager._take_step": {
"total": 76.02799335198642,
"count": 18192,
"self": 1.3212031129937714,
"children": {
"TorchPolicy.evaluate": {
"total": 74.70679023899265,
"count": 18192,
"self": 74.70679023899265
}
}
},
"workers": {
"total": 0.240365606023488,
"count": 18192,
"self": 0.0,
"children": {
"worker_root": {
"total": 397.9537662330033,
"count": 18192,
"is_parallel": true,
"self": 190.60895667900672,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.002276298999959181,
"count": 1,
"is_parallel": true,
"self": 0.000686218000282679,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001590080999676502,
"count": 10,
"is_parallel": true,
"self": 0.001590080999676502
}
}
},
"UnityEnvironment.step": {
"total": 0.03597535900007642,
"count": 1,
"is_parallel": true,
"self": 0.0007059810000100697,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0004053479999583942,
"count": 1,
"is_parallel": true,
"self": 0.0004053479999583942
},
"communicator.exchange": {
"total": 0.032811723000122583,
"count": 1,
"is_parallel": true,
"self": 0.032811723000122583
},
"steps_from_proto": {
"total": 0.002052306999985376,
"count": 1,
"is_parallel": true,
"self": 0.0003964780003116175,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0016558289996737585,
"count": 10,
"is_parallel": true,
"self": 0.0016558289996737585
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 207.34480955399658,
"count": 18191,
"is_parallel": true,
"self": 10.10729122898806,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.548815729996477,
"count": 18191,
"is_parallel": true,
"self": 5.548815729996477
},
"communicator.exchange": {
"total": 158.47915548401443,
"count": 18191,
"is_parallel": true,
"self": 158.47915548401443
},
"steps_from_proto": {
"total": 33.20954711099762,
"count": 18191,
"is_parallel": true,
"self": 6.0152952949040355,
"children": {
"_process_rank_one_or_two_observation": {
"total": 27.194251816093583,
"count": 181910,
"is_parallel": true,
"self": 27.194251816093583
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 82.85627741099393,
"count": 18192,
"self": 0.43775320799977635,
"children": {
"process_trajectory": {
"total": 26.99354049599424,
"count": 18192,
"self": 26.54805537999414,
"children": {
"RLTrainer._checkpoint": {
"total": 0.4454851160000999,
"count": 4,
"self": 0.4454851160000999
}
}
},
"_update_policy": {
"total": 55.42498370699991,
"count": 19,
"self": 37.852424140002086,
"children": {
"TorchPPOOptimizer.update": {
"total": 17.572559566997825,
"count": 1155,
"self": 17.572559566997825
}
}
}
}
}
}
},
"trainer_threads": {
"total": 8.659999366500415e-07,
"count": 1,
"self": 8.659999366500415e-07
},
"TrainerController._save_models": {
"total": 0.09281807699971978,
"count": 1,
"self": 0.0011537249997672916,
"children": {
"RLTrainer._checkpoint": {
"total": 0.09166435199995249,
"count": 1,
"self": 0.09166435199995249
}
}
}
}
}
}
}