WilliamADSP's picture
First Push
e2726a9
{
"name": "root",
"gauges": {
"SoccerTwos.Policy.Entropy.mean": {
"value": 1.442643404006958,
"min": 1.3646326065063477,
"max": 1.5156055688858032,
"count": 401
},
"SoccerTwos.Policy.Entropy.sum": {
"value": 29083.69140625,
"min": 964.6746826171875,
"max": 34790.27734375,
"count": 401
},
"SoccerTwos.Environment.EpisodeLength.mean": {
"value": 58.892857142857146,
"min": 16.0,
"max": 91.64150943396227,
"count": 401
},
"SoccerTwos.Environment.EpisodeLength.sum": {
"value": 19788.0,
"min": 192.0,
"max": 20676.0,
"count": 401
},
"SoccerTwos.Self-play.ELO.mean": {
"value": 1536.758699507207,
"min": 1513.376511471752,
"max": 1570.2386341842073,
"count": 401
},
"SoccerTwos.Self-play.ELO.sum": {
"value": 258175.46151721076,
"min": 9114.78279783337,
"max": 339446.648018735,
"count": 401
},
"SoccerTwos.Step.mean": {
"value": 29999984.0,
"min": 25999991.0,
"max": 29999984.0,
"count": 401
},
"SoccerTwos.Step.sum": {
"value": 29999984.0,
"min": 25999991.0,
"max": 29999984.0,
"count": 401
},
"SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": {
"value": -0.06340470910072327,
"min": -0.23134204745292664,
"max": 0.08946024626493454,
"count": 401
},
"SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": {
"value": -10.65199089050293,
"min": -21.37249755859375,
"max": 11.450911521911621,
"count": 401
},
"SoccerTwos.Policy.ExtrinsicValueEstimate.mean": {
"value": -0.0660364106297493,
"min": -0.23267503082752228,
"max": 0.09010016918182373,
"count": 401
},
"SoccerTwos.Policy.ExtrinsicValueEstimate.sum": {
"value": -11.094117164611816,
"min": -21.51323699951172,
"max": 11.532821655273438,
"count": 401
},
"SoccerTwos.Environment.CumulativeReward.mean": {
"value": 0.0,
"min": 0.0,
"max": 0.0,
"count": 401
},
"SoccerTwos.Environment.CumulativeReward.sum": {
"value": 0.0,
"min": 0.0,
"max": 0.0,
"count": 401
},
"SoccerTwos.Policy.ExtrinsicReward.mean": {
"value": -0.37794047523112523,
"min": -1.0,
"max": 0.3092654096255512,
"count": 401
},
"SoccerTwos.Policy.ExtrinsicReward.sum": {
"value": -63.49399983882904,
"min": -63.49399983882904,
"max": 49.17320013046265,
"count": 401
},
"SoccerTwos.Environment.GroupCumulativeReward.mean": {
"value": -0.37794047523112523,
"min": -1.0,
"max": 0.3092654096255512,
"count": 401
},
"SoccerTwos.Environment.GroupCumulativeReward.sum": {
"value": -63.49399983882904,
"min": -63.49399983882904,
"max": 49.17320013046265,
"count": 401
},
"SoccerTwos.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 401
},
"SoccerTwos.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 401
},
"SoccerTwos.Losses.PolicyLoss.mean": {
"value": 0.015637130175794784,
"min": 0.011390995223094554,
"max": 0.025345727618938933,
"count": 194
},
"SoccerTwos.Losses.PolicyLoss.sum": {
"value": 0.015637130175794784,
"min": 0.011390995223094554,
"max": 0.025345727618938933,
"count": 194
},
"SoccerTwos.Losses.ValueLoss.mean": {
"value": 0.10095099707444509,
"min": 0.07894389082988103,
"max": 0.11518443673849106,
"count": 194
},
"SoccerTwos.Losses.ValueLoss.sum": {
"value": 0.10095099707444509,
"min": 0.07894389082988103,
"max": 0.11518443673849106,
"count": 194
},
"SoccerTwos.Losses.BaselineLoss.mean": {
"value": 0.10293505663673083,
"min": 0.0800147719681263,
"max": 0.11697089771429697,
"count": 194
},
"SoccerTwos.Losses.BaselineLoss.sum": {
"value": 0.10293505663673083,
"min": 0.0800147719681263,
"max": 0.11697089771429697,
"count": 194
},
"SoccerTwos.Policy.LearningRate.mean": {
"value": 0.0003,
"min": 0.0003,
"max": 0.0003,
"count": 194
},
"SoccerTwos.Policy.LearningRate.sum": {
"value": 0.0003,
"min": 0.0003,
"max": 0.0003,
"count": 194
},
"SoccerTwos.Policy.Epsilon.mean": {
"value": 0.20000000000000007,
"min": 0.20000000000000007,
"max": 0.20000000000000007,
"count": 194
},
"SoccerTwos.Policy.Epsilon.sum": {
"value": 0.20000000000000007,
"min": 0.20000000000000007,
"max": 0.20000000000000007,
"count": 194
},
"SoccerTwos.Policy.Beta.mean": {
"value": 0.005000000000000001,
"min": 0.005000000000000001,
"max": 0.005000000000000001,
"count": 194
},
"SoccerTwos.Policy.Beta.sum": {
"value": 0.005000000000000001,
"min": 0.005000000000000001,
"max": 0.005000000000000001,
"count": 194
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1683274975",
"python_version": "3.9.16 (main, Apr 12 2023, 06:58:15) \n[GCC 10.2.1 20210110]",
"command_line_arguments": "/home/adsp/.local/bin/mlagents-learn /app/ml-agents/config/poca/SoccerTwos.yaml --env=/app/ml-agents/training-envs-executables/SoccerTwos/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": "1683304836"
},
"total": 21052.462681778998,
"count": 1,
"self": 1.3189635519956937,
"children": {
"run_training.setup": {
"total": 0.18352584300004082,
"count": 1,
"self": 0.18352584300004082
},
"TrainerController.start_learning": {
"total": 21050.960192384002,
"count": 1,
"self": 11.725414112748695,
"children": {
"TrainerController._reset_env": {
"total": 13.553882120002925,
"count": 21,
"self": 13.553882120002925
},
"TrainerController.advance": {
"total": 21025.28174819625,
"count": 277300,
"self": 11.90760220748416,
"children": {
"env_step": {
"total": 9961.931052763448,
"count": 277300,
"self": 8486.755533540296,
"children": {
"SubprocessEnvManager._take_step": {
"total": 1468.213213065258,
"count": 277300,
"self": 66.82326059318234,
"children": {
"TorchPolicy.evaluate": {
"total": 1401.3899524720757,
"count": 502138,
"self": 1401.3899524720757
}
}
},
"workers": {
"total": 6.962306157894261,
"count": 277300,
"self": 0.0,
"children": {
"worker_root": {
"total": 21019.985834203908,
"count": 277300,
"is_parallel": true,
"self": 13753.178573381148,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.005918918000020312,
"count": 2,
"is_parallel": true,
"self": 0.002527409999970587,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0033915080000497255,
"count": 8,
"is_parallel": true,
"self": 0.0033915080000497255
}
}
},
"UnityEnvironment.step": {
"total": 0.060281557000053,
"count": 1,
"is_parallel": true,
"self": 0.00105069500011723,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0009998699999869132,
"count": 1,
"is_parallel": true,
"self": 0.0009998699999869132
},
"communicator.exchange": {
"total": 0.05436580899998944,
"count": 1,
"is_parallel": true,
"self": 0.05436580899998944
},
"steps_from_proto": {
"total": 0.0038651829999594156,
"count": 2,
"is_parallel": true,
"self": 0.0011909479999303585,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.002674235000029057,
"count": 8,
"is_parallel": true,
"self": 0.002674235000029057
}
}
}
}
}
}
},
"steps_from_proto": {
"total": 0.052836068993315166,
"count": 40,
"is_parallel": true,
"self": 0.011889546985003108,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.04094652200831206,
"count": 160,
"is_parallel": true,
"self": 0.04094652200831206
}
}
},
"UnityEnvironment.step": {
"total": 7266.754424753766,
"count": 277299,
"is_parallel": true,
"self": 244.94494398424104,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 232.1515300788497,
"count": 277299,
"is_parallel": true,
"self": 232.1515300788497
},
"communicator.exchange": {
"total": 6062.591858620617,
"count": 277299,
"is_parallel": true,
"self": 6062.591858620617
},
"steps_from_proto": {
"total": 727.0660920700589,
"count": 554598,
"is_parallel": true,
"self": 166.1676294218787,
"children": {
"_process_rank_one_or_two_observation": {
"total": 560.8984626481802,
"count": 2218392,
"is_parallel": true,
"self": 560.8984626481802
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 11051.443093225316,
"count": 277300,
"self": 71.37279218860567,
"children": {
"process_trajectory": {
"total": 1740.5465395717101,
"count": 277300,
"self": 1735.6465254887112,
"children": {
"RLTrainer._checkpoint": {
"total": 4.900014082999007,
"count": 9,
"self": 4.900014082999007
}
}
},
"_update_policy": {
"total": 9239.523761465,
"count": 194,
"self": 1089.3161181191253,
"children": {
"TorchPOCAOptimizer.update": {
"total": 8150.207643345874,
"count": 5820,
"self": 8150.207643345874
}
}
}
}
}
}
},
"trainer_threads": {
"total": 2.9090006137266755e-06,
"count": 1,
"self": 2.9090006137266755e-06
},
"TrainerController._save_models": {
"total": 0.39914504600164946,
"count": 1,
"self": 0.09269286800190457,
"children": {
"RLTrainer._checkpoint": {
"total": 0.3064521779997449,
"count": 1,
"self": 0.3064521779997449
}
}
}
}
}
}
}