|
{ |
|
"name": "root", |
|
"gauges": { |
|
"SoccerTwos.Policy.Entropy.mean": { |
|
"value": 2.1297104358673096, |
|
"min": 2.1297104358673096, |
|
"max": 3.2300140857696533, |
|
"count": 480 |
|
}, |
|
"SoccerTwos.Policy.Entropy.sum": { |
|
"value": 42117.15234375, |
|
"min": 15416.599609375, |
|
"max": 118434.0546875, |
|
"count": 480 |
|
}, |
|
"SoccerTwos.Environment.EpisodeLength.mean": { |
|
"value": 55.48863636363637, |
|
"min": 43.73451327433628, |
|
"max": 999.0, |
|
"count": 480 |
|
}, |
|
"SoccerTwos.Environment.EpisodeLength.sum": { |
|
"value": 19532.0, |
|
"min": 7992.0, |
|
"max": 23976.0, |
|
"count": 480 |
|
}, |
|
"SoccerTwos.Self-play.ELO.mean": { |
|
"value": 1490.0828995925053, |
|
"min": 1189.2781594350054, |
|
"max": 1510.0009701320125, |
|
"count": 401 |
|
}, |
|
"SoccerTwos.Self-play.ELO.sum": { |
|
"value": 262254.59032828093, |
|
"min": 2378.5563188700107, |
|
"max": 339783.2031810584, |
|
"count": 401 |
|
}, |
|
"SoccerTwos.Step.mean": { |
|
"value": 4999982.0, |
|
"min": 209824.0, |
|
"max": 4999982.0, |
|
"count": 480 |
|
}, |
|
"SoccerTwos.Step.sum": { |
|
"value": 4999982.0, |
|
"min": 209824.0, |
|
"max": 4999982.0, |
|
"count": 480 |
|
}, |
|
"SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { |
|
"value": -0.08622787892818451, |
|
"min": -0.08622787892818451, |
|
"max": 0.18638771772384644, |
|
"count": 480 |
|
}, |
|
"SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { |
|
"value": -15.176106452941895, |
|
"min": -15.176106452941895, |
|
"max": 23.857627868652344, |
|
"count": 480 |
|
}, |
|
"SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { |
|
"value": -0.08692476153373718, |
|
"min": -0.08692476153373718, |
|
"max": 0.1873682141304016, |
|
"count": 480 |
|
}, |
|
"SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { |
|
"value": -15.298757553100586, |
|
"min": -15.298757553100586, |
|
"max": 23.983131408691406, |
|
"count": 480 |
|
}, |
|
"SoccerTwos.Environment.CumulativeReward.mean": { |
|
"value": 0.0, |
|
"min": 0.0, |
|
"max": 0.0, |
|
"count": 480 |
|
}, |
|
"SoccerTwos.Environment.CumulativeReward.sum": { |
|
"value": 0.0, |
|
"min": 0.0, |
|
"max": 0.0, |
|
"count": 480 |
|
}, |
|
"SoccerTwos.Policy.ExtrinsicReward.mean": { |
|
"value": -0.14138409292156046, |
|
"min": -0.5833333333333334, |
|
"max": 0.41337000131607055, |
|
"count": 480 |
|
}, |
|
"SoccerTwos.Policy.ExtrinsicReward.sum": { |
|
"value": -24.88360035419464, |
|
"min": -40.97820007801056, |
|
"max": 55.59539973735809, |
|
"count": 480 |
|
}, |
|
"SoccerTwos.Environment.GroupCumulativeReward.mean": { |
|
"value": -0.14138409292156046, |
|
"min": -0.5833333333333334, |
|
"max": 0.41337000131607055, |
|
"count": 480 |
|
}, |
|
"SoccerTwos.Environment.GroupCumulativeReward.sum": { |
|
"value": -24.88360035419464, |
|
"min": -40.97820007801056, |
|
"max": 55.59539973735809, |
|
"count": 480 |
|
}, |
|
"SoccerTwos.IsTraining.mean": { |
|
"value": 1.0, |
|
"min": 1.0, |
|
"max": 1.0, |
|
"count": 480 |
|
}, |
|
"SoccerTwos.IsTraining.sum": { |
|
"value": 1.0, |
|
"min": 1.0, |
|
"max": 1.0, |
|
"count": 480 |
|
}, |
|
"SoccerTwos.Losses.PolicyLoss.mean": { |
|
"value": 0.02225424475618638, |
|
"min": 0.01128294709584831, |
|
"max": 0.02365408402401954, |
|
"count": 227 |
|
}, |
|
"SoccerTwos.Losses.PolicyLoss.sum": { |
|
"value": 0.02225424475618638, |
|
"min": 0.01128294709584831, |
|
"max": 0.02365408402401954, |
|
"count": 227 |
|
}, |
|
"SoccerTwos.Losses.ValueLoss.mean": { |
|
"value": 0.10136176124215127, |
|
"min": 1.94872579489432e-06, |
|
"max": 0.1131344015399615, |
|
"count": 227 |
|
}, |
|
"SoccerTwos.Losses.ValueLoss.sum": { |
|
"value": 0.10136176124215127, |
|
"min": 1.94872579489432e-06, |
|
"max": 0.1131344015399615, |
|
"count": 227 |
|
}, |
|
"SoccerTwos.Losses.BaselineLoss.mean": { |
|
"value": 0.1039174164334933, |
|
"min": 1.9381466737892576e-06, |
|
"max": 0.11576234499613444, |
|
"count": 227 |
|
}, |
|
"SoccerTwos.Losses.BaselineLoss.sum": { |
|
"value": 0.1039174164334933, |
|
"min": 1.9381466737892576e-06, |
|
"max": 0.11576234499613444, |
|
"count": 227 |
|
}, |
|
"SoccerTwos.Policy.LearningRate.mean": { |
|
"value": 0.0003, |
|
"min": 0.0003, |
|
"max": 0.0003, |
|
"count": 227 |
|
}, |
|
"SoccerTwos.Policy.LearningRate.sum": { |
|
"value": 0.0003, |
|
"min": 0.0003, |
|
"max": 0.0003, |
|
"count": 227 |
|
}, |
|
"SoccerTwos.Policy.Epsilon.mean": { |
|
"value": 0.20000000000000007, |
|
"min": 0.20000000000000004, |
|
"max": 0.20000000000000007, |
|
"count": 227 |
|
}, |
|
"SoccerTwos.Policy.Epsilon.sum": { |
|
"value": 0.20000000000000007, |
|
"min": 0.20000000000000004, |
|
"max": 0.20000000000000007, |
|
"count": 227 |
|
}, |
|
"SoccerTwos.Policy.Beta.mean": { |
|
"value": 0.005000000000000001, |
|
"min": 0.005000000000000001, |
|
"max": 0.005000000000000001, |
|
"count": 227 |
|
}, |
|
"SoccerTwos.Policy.Beta.sum": { |
|
"value": 0.005000000000000001, |
|
"min": 0.005000000000000001, |
|
"max": 0.005000000000000001, |
|
"count": 227 |
|
} |
|
}, |
|
"metadata": { |
|
"timer_format_version": "0.1.0", |
|
"start_time_seconds": "1677346998", |
|
"python_version": "3.9.16 (main, Jan 11 2023, 16:05:54) \n[GCC 11.2.0]", |
|
"command_line_arguments": "/home/amkio/miniconda3/envs/rl/bin/mlagents-learn ml-agents/config/poca/SoccerTwos.yaml --env SoccerTwos/SoccerTwos.x86_64 --run-id=SoccerTwosV1 --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": "1677386528" |
|
}, |
|
"total": 39530.100510085, |
|
"count": 1, |
|
"self": 1.2977799150030478, |
|
"children": { |
|
"run_training.setup": { |
|
"total": 0.034655507000024954, |
|
"count": 1, |
|
"self": 0.034655507000024954 |
|
}, |
|
"TrainerController.start_learning": { |
|
"total": 39528.768074663, |
|
"count": 1, |
|
"self": 16.345437378433417, |
|
"children": { |
|
"TrainerController._reset_env": { |
|
"total": 4.631710846003898, |
|
"count": 25, |
|
"self": 4.631710846003898 |
|
}, |
|
"TrainerController.advance": { |
|
"total": 39507.356822843554, |
|
"count": 318461, |
|
"self": 18.833687486279814, |
|
"children": { |
|
"env_step": { |
|
"total": 13689.83521339461, |
|
"count": 318461, |
|
"self": 11043.583744051386, |
|
"children": { |
|
"SubprocessEnvManager._take_step": { |
|
"total": 2636.484040468952, |
|
"count": 318461, |
|
"self": 112.27693164064476, |
|
"children": { |
|
"TorchPolicy.evaluate": { |
|
"total": 2524.2071088283074, |
|
"count": 612392, |
|
"self": 2524.2071088283074 |
|
} |
|
} |
|
}, |
|
"workers": { |
|
"total": 9.767428874271445, |
|
"count": 318461, |
|
"self": 0.0, |
|
"children": { |
|
"worker_root": { |
|
"total": 39465.199092006376, |
|
"count": 318461, |
|
"is_parallel": true, |
|
"self": 30293.40543808885, |
|
"children": { |
|
"run_training.setup": { |
|
"total": 0.0, |
|
"count": 0, |
|
"is_parallel": true, |
|
"self": 0.0, |
|
"children": { |
|
"steps_from_proto": { |
|
"total": 0.005234613999164139, |
|
"count": 2, |
|
"is_parallel": true, |
|
"self": 0.0013125449991093774, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 0.003922069000054762, |
|
"count": 8, |
|
"is_parallel": true, |
|
"self": 0.003922069000054762 |
|
} |
|
} |
|
}, |
|
"UnityEnvironment.step": { |
|
"total": 0.08263854099959644, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0012752769998769509, |
|
"children": { |
|
"UnityEnvironment._generate_step_input": { |
|
"total": 0.001010441999824252, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.001010441999824252 |
|
}, |
|
"communicator.exchange": { |
|
"total": 0.07629772700011017, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.07629772700011017 |
|
}, |
|
"steps_from_proto": { |
|
"total": 0.004055094999785069, |
|
"count": 2, |
|
"is_parallel": true, |
|
"self": 0.0008141859993884282, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 0.003240909000396641, |
|
"count": 8, |
|
"is_parallel": true, |
|
"self": 0.003240909000396641 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"steps_from_proto": { |
|
"total": 0.08776084098599313, |
|
"count": 48, |
|
"is_parallel": true, |
|
"self": 0.01857009000968901, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 0.06919075097630412, |
|
"count": 192, |
|
"is_parallel": true, |
|
"self": 0.06919075097630412 |
|
} |
|
} |
|
}, |
|
"UnityEnvironment.step": { |
|
"total": 9171.70589307654, |
|
"count": 318460, |
|
"is_parallel": true, |
|
"self": 409.4262001349216, |
|
"children": { |
|
"UnityEnvironment._generate_step_input": { |
|
"total": 272.655203484308, |
|
"count": 318460, |
|
"is_parallel": true, |
|
"self": 272.655203484308 |
|
}, |
|
"communicator.exchange": { |
|
"total": 7256.58773626228, |
|
"count": 318460, |
|
"is_parallel": true, |
|
"self": 7256.58773626228 |
|
}, |
|
"steps_from_proto": { |
|
"total": 1233.036753195031, |
|
"count": 636920, |
|
"is_parallel": true, |
|
"self": 246.98099322673943, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 986.0557599682916, |
|
"count": 2547680, |
|
"is_parallel": true, |
|
"self": 986.0557599682916 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"trainer_advance": { |
|
"total": 25798.687921962664, |
|
"count": 318461, |
|
"self": 121.09615994189153, |
|
"children": { |
|
"process_trajectory": { |
|
"total": 3109.654138070761, |
|
"count": 318461, |
|
"self": 3104.1325823657576, |
|
"children": { |
|
"RLTrainer._checkpoint": { |
|
"total": 5.521555705003266, |
|
"count": 10, |
|
"self": 5.521555705003266 |
|
} |
|
} |
|
}, |
|
"_update_policy": { |
|
"total": 22567.937623950012, |
|
"count": 227, |
|
"self": 1672.4833105500802, |
|
"children": { |
|
"TorchPOCAOptimizer.update": { |
|
"total": 20895.454313399932, |
|
"count": 6816, |
|
"self": 20895.454313399932 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"trainer_threads": { |
|
"total": 1.6750054783187807e-06, |
|
"count": 1, |
|
"self": 1.6750054783187807e-06 |
|
}, |
|
"TrainerController._save_models": { |
|
"total": 0.43410192000010284, |
|
"count": 1, |
|
"self": 0.007690393002121709, |
|
"children": { |
|
"RLTrainer._checkpoint": { |
|
"total": 0.4264115269979811, |
|
"count": 1, |
|
"self": 0.4264115269979811 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |