poca-SoccerTwos / run_logs /timers.json
nlamot's picture
First Push
645002a
raw
history blame
12.1 kB
{
"name": "root",
"gauges": {
"SoccerTwos.Policy.Entropy.mean": {
"value": 3.2957630157470703,
"min": 3.2957630157470703,
"max": 3.2957630157470703,
"count": 1
},
"SoccerTwos.Policy.Entropy.sum": {
"value": 105464.4140625,
"min": 105464.4140625,
"max": 105464.4140625,
"count": 1
},
"SoccerTwos.Environment.EpisodeLength.mean": {
"value": 595.4444444444445,
"min": 595.4444444444445,
"max": 595.4444444444445,
"count": 1
},
"SoccerTwos.Environment.EpisodeLength.sum": {
"value": 21436.0,
"min": 21436.0,
"max": 21436.0,
"count": 1
},
"SoccerTwos.Self-play.ELO.mean": {
"value": 1200.5977600543993,
"min": 1200.5977600543993,
"max": 1200.5977600543993,
"count": 1
},
"SoccerTwos.Self-play.ELO.sum": {
"value": 19209.564160870388,
"min": 19209.564160870388,
"max": 19209.564160870388,
"count": 1
},
"SoccerTwos.Step.mean": {
"value": 9736.0,
"min": 9736.0,
"max": 9736.0,
"count": 1
},
"SoccerTwos.Step.sum": {
"value": 9736.0,
"min": 9736.0,
"max": 9736.0,
"count": 1
},
"SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": {
"value": -0.02721060812473297,
"min": -0.02721060812473297,
"max": -0.02721060812473297,
"count": 1
},
"SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": {
"value": -0.4625803530216217,
"min": -0.4625803530216217,
"max": -0.4625803530216217,
"count": 1
},
"SoccerTwos.Policy.ExtrinsicValueEstimate.mean": {
"value": -0.027218960225582123,
"min": -0.027218960225582123,
"max": -0.027218960225582123,
"count": 1
},
"SoccerTwos.Policy.ExtrinsicValueEstimate.sum": {
"value": -0.4627223312854767,
"min": -0.4627223312854767,
"max": -0.4627223312854767,
"count": 1
},
"SoccerTwos.Environment.CumulativeReward.mean": {
"value": 0.0,
"min": 0.0,
"max": 0.0,
"count": 1
},
"SoccerTwos.Environment.CumulativeReward.sum": {
"value": 0.0,
"min": 0.0,
"max": 0.0,
"count": 1
},
"SoccerTwos.Policy.ExtrinsicReward.mean": {
"value": -0.3015294075012207,
"min": -0.3015294075012207,
"max": -0.3015294075012207,
"count": 1
},
"SoccerTwos.Policy.ExtrinsicReward.sum": {
"value": -5.125999927520752,
"min": -5.125999927520752,
"max": -5.125999927520752,
"count": 1
},
"SoccerTwos.Environment.GroupCumulativeReward.mean": {
"value": -0.3015294075012207,
"min": -0.3015294075012207,
"max": -0.3015294075012207,
"count": 1
},
"SoccerTwos.Environment.GroupCumulativeReward.sum": {
"value": -5.125999927520752,
"min": -5.125999927520752,
"max": -5.125999927520752,
"count": 1
},
"SoccerTwos.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 1
},
"SoccerTwos.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 1
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1703600819",
"python_version": "3.10.12 (main, Jul 5 2023, 15:02:25) [Clang 14.0.6 ]",
"command_line_arguments": "/opt/homebrew/Caskroom/miniconda/base/envs/rl/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos.app --run-id=SoccerTwos --no-graphics --force",
"mlagents_version": "1.1.0.dev0",
"mlagents_envs_version": "1.1.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.1.2",
"numpy_version": "1.23.5",
"end_time_seconds": "1703600831"
},
"total": 12.324586292001186,
"count": 1,
"self": 0.05213245800405275,
"children": {
"run_training.setup": {
"total": 0.01152475000708364,
"count": 1,
"self": 0.01152475000708364
},
"TrainerController.start_learning": {
"total": 12.26092908399005,
"count": 1,
"self": 0.012635755498195067,
"children": {
"TrainerController._reset_env": {
"total": 1.3044151670037536,
"count": 1,
"self": 1.3044151670037536
},
"TrainerController.advance": {
"total": 10.815542661468498,
"count": 1460,
"self": 0.007870137967984192,
"children": {
"env_step": {
"total": 9.546404088527197,
"count": 1460,
"self": 8.040804349293467,
"children": {
"SubprocessEnvManager._take_step": {
"total": 1.500216540051042,
"count": 1460,
"self": 0.037277955751051195,
"children": {
"TorchPolicy.evaluate": {
"total": 1.462938584299991,
"count": 2898,
"self": 1.462938584299991
}
}
},
"workers": {
"total": 0.005383199182688259,
"count": 1460,
"self": 0.0,
"children": {
"worker_root": {
"total": 10.906700973515399,
"count": 1460,
"is_parallel": true,
"self": 4.1116495673777536,
"children": {
"steps_from_proto": {
"total": 0.0009015840041683987,
"count": 2,
"is_parallel": true,
"self": 0.00019383500330150127,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0007077490008668974,
"count": 8,
"is_parallel": true,
"self": 0.0007077490008668974
}
}
},
"UnityEnvironment.step": {
"total": 6.794149822133477,
"count": 1460,
"is_parallel": true,
"self": 0.3332863088871818,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.16045400052098557,
"count": 1460,
"is_parallel": true,
"self": 0.16045400052098557
},
"communicator.exchange": {
"total": 5.457947217655601,
"count": 1460,
"is_parallel": true,
"self": 5.457947217655601
},
"steps_from_proto": {
"total": 0.8424622950697085,
"count": 2920,
"is_parallel": true,
"self": 0.1259996038133977,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.7164626912563108,
"count": 11680,
"is_parallel": true,
"self": 0.7164626912563108
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 1.2612684349733172,
"count": 1460,
"self": 0.05883011972764507,
"children": {
"process_trajectory": {
"total": 1.2024383152456721,
"count": 1460,
"self": 1.2024383152456721
}
}
}
}
},
"trainer_threads": {
"total": 4.580069798976183e-07,
"count": 1,
"self": 4.580069798976183e-07
},
"TrainerController._save_models": {
"total": 0.12833504201262258,
"count": 1,
"self": 0.0008005840063560754,
"children": {
"RLTrainer._checkpoint": {
"total": 0.1275344580062665,
"count": 1,
"self": 0.1275344580062665
}
}
}
}
}
}
}