| { | |
| "name": "root", | |
| "gauges": { | |
| "SoccerTwos.Policy.Entropy.mean": { | |
| "value": 3.238750696182251, | |
| "min": 3.197690486907959, | |
| "max": 3.295699119567871, | |
| "count": 50 | |
| }, | |
| "SoccerTwos.Policy.Entropy.sum": { | |
| "value": 49021.73046875, | |
| "min": 26611.60546875, | |
| "max": 105462.375, | |
| "count": 50 | |
| }, | |
| "SoccerTwos.Environment.EpisodeLength.mean": { | |
| "value": 505.0, | |
| "min": 403.54545454545456, | |
| "max": 999.0, | |
| "count": 50 | |
| }, | |
| "SoccerTwos.Environment.EpisodeLength.sum": { | |
| "value": 18180.0, | |
| "min": 13876.0, | |
| "max": 27272.0, | |
| "count": 50 | |
| }, | |
| "SoccerTwos.Self-play.ELO.mean": { | |
| "value": 1186.5069004133907, | |
| "min": 1186.5069004133907, | |
| "max": 1199.8575034417302, | |
| "count": 48 | |
| }, | |
| "SoccerTwos.Self-play.ELO.sum": { | |
| "value": 16611.09660578747, | |
| "min": 2381.7478876241566, | |
| "max": 21444.55038134982, | |
| "count": 48 | |
| }, | |
| "SoccerTwos.Step.mean": { | |
| "value": 499680.0, | |
| "min": 9652.0, | |
| "max": 499680.0, | |
| "count": 50 | |
| }, | |
| "SoccerTwos.Step.sum": { | |
| "value": 499680.0, | |
| "min": 9652.0, | |
| "max": 499680.0, | |
| "count": 50 | |
| }, | |
| "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { | |
| "value": -0.030743226408958435, | |
| "min": -0.030743226408958435, | |
| "max": 0.07228275388479233, | |
| "count": 50 | |
| }, | |
| "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { | |
| "value": -0.5841212868690491, | |
| "min": -0.5841212868690491, | |
| "max": 0.8673423528671265, | |
| "count": 50 | |
| }, | |
| "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { | |
| "value": -0.02629690431058407, | |
| "min": -0.02629690431058407, | |
| "max": 0.07229527831077576, | |
| "count": 50 | |
| }, | |
| "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { | |
| "value": -0.49964118003845215, | |
| "min": -0.49964118003845215, | |
| "max": 0.8674721717834473, | |
| "count": 50 | |
| }, | |
| "SoccerTwos.Environment.CumulativeReward.mean": { | |
| "value": 0.0, | |
| "min": 0.0, | |
| "max": 0.0, | |
| "count": 50 | |
| }, | |
| "SoccerTwos.Environment.CumulativeReward.sum": { | |
| "value": 0.0, | |
| "min": 0.0, | |
| "max": 0.0, | |
| "count": 50 | |
| }, | |
| "SoccerTwos.Policy.ExtrinsicReward.mean": { | |
| "value": -0.3532631585472508, | |
| "min": -0.5625, | |
| "max": 0.2612923016914955, | |
| "count": 50 | |
| }, | |
| "SoccerTwos.Policy.ExtrinsicReward.sum": { | |
| "value": -6.712000012397766, | |
| "min": -9.0, | |
| "max": 3.396799921989441, | |
| "count": 50 | |
| }, | |
| "SoccerTwos.Environment.GroupCumulativeReward.mean": { | |
| "value": -0.3532631585472508, | |
| "min": -0.5625, | |
| "max": 0.2612923016914955, | |
| "count": 50 | |
| }, | |
| "SoccerTwos.Environment.GroupCumulativeReward.sum": { | |
| "value": -6.712000012397766, | |
| "min": -9.0, | |
| "max": 3.396799921989441, | |
| "count": 50 | |
| }, | |
| "SoccerTwos.IsTraining.mean": { | |
| "value": 1.0, | |
| "min": 1.0, | |
| "max": 1.0, | |
| "count": 50 | |
| }, | |
| "SoccerTwos.IsTraining.sum": { | |
| "value": 1.0, | |
| "min": 1.0, | |
| "max": 1.0, | |
| "count": 50 | |
| }, | |
| "SoccerTwos.Losses.PolicyLoss.mean": { | |
| "value": 0.02084106073404352, | |
| "min": 0.01365347881995452, | |
| "max": 0.02084106073404352, | |
| "count": 23 | |
| }, | |
| "SoccerTwos.Losses.PolicyLoss.sum": { | |
| "value": 0.02084106073404352, | |
| "min": 0.01365347881995452, | |
| "max": 0.02084106073404352, | |
| "count": 23 | |
| }, | |
| "SoccerTwos.Losses.ValueLoss.mean": { | |
| "value": 0.0033301054034382107, | |
| "min": 0.0008956896490417421, | |
| "max": 0.008444473100826144, | |
| "count": 23 | |
| }, | |
| "SoccerTwos.Losses.ValueLoss.sum": { | |
| "value": 0.0033301054034382107, | |
| "min": 0.0008956896490417421, | |
| "max": 0.008444473100826144, | |
| "count": 23 | |
| }, | |
| "SoccerTwos.Losses.BaselineLoss.mean": { | |
| "value": 0.003351145746031155, | |
| "min": 0.000905891958885177, | |
| "max": 0.008915761734048526, | |
| "count": 23 | |
| }, | |
| "SoccerTwos.Losses.BaselineLoss.sum": { | |
| "value": 0.003351145746031155, | |
| "min": 0.000905891958885177, | |
| "max": 0.008915761734048526, | |
| "count": 23 | |
| }, | |
| "SoccerTwos.Policy.LearningRate.mean": { | |
| "value": 0.0003, | |
| "min": 0.0003, | |
| "max": 0.0003, | |
| "count": 23 | |
| }, | |
| "SoccerTwos.Policy.LearningRate.sum": { | |
| "value": 0.0003, | |
| "min": 0.0003, | |
| "max": 0.0003, | |
| "count": 23 | |
| }, | |
| "SoccerTwos.Policy.Epsilon.mean": { | |
| "value": 0.20000000000000007, | |
| "min": 0.2, | |
| "max": 0.20000000000000007, | |
| "count": 23 | |
| }, | |
| "SoccerTwos.Policy.Epsilon.sum": { | |
| "value": 0.20000000000000007, | |
| "min": 0.2, | |
| "max": 0.20000000000000007, | |
| "count": 23 | |
| }, | |
| "SoccerTwos.Policy.Beta.mean": { | |
| "value": 0.005000000000000001, | |
| "min": 0.005, | |
| "max": 0.005000000000000001, | |
| "count": 23 | |
| }, | |
| "SoccerTwos.Policy.Beta.sum": { | |
| "value": 0.005000000000000001, | |
| "min": 0.005, | |
| "max": 0.005000000000000001, | |
| "count": 23 | |
| } | |
| }, | |
| "metadata": { | |
| "timer_format_version": "0.1.0", | |
| "start_time_seconds": "1680199306", | |
| "python_version": "3.9.16 (main, Mar 8 2023, 14:00:05) \n[GCC 11.2.0]", | |
| "command_line_arguments": "/home/tiger/anaconda3/envs/rl/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos.x86_64 --run-id=SoccerTwos --no-graphics --force", | |
| "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": "1680200710" | |
| }, | |
| "total": 1404.1848277151585, | |
| "count": 1, | |
| "self": 0.32136988639831543, | |
| "children": { | |
| "run_training.setup": { | |
| "total": 0.011325091123580933, | |
| "count": 1, | |
| "self": 0.011325091123580933 | |
| }, | |
| "TrainerController.start_learning": { | |
| "total": 1403.8521327376366, | |
| "count": 1, | |
| "self": 0.7886237502098083, | |
| "children": { | |
| "TrainerController._reset_env": { | |
| "total": 0.9542036354541779, | |
| "count": 3, | |
| "self": 0.9542036354541779 | |
| }, | |
| "TrainerController.advance": { | |
| "total": 1401.8916592299938, | |
| "count": 32550, | |
| "self": 0.7980107665061951, | |
| "children": { | |
| "env_step": { | |
| "total": 655.1693503260612, | |
| "count": 32550, | |
| "self": 500.6206337213516, | |
| "children": { | |
| "SubprocessEnvManager._take_step": { | |
| "total": 154.03513684868813, | |
| "count": 32550, | |
| "self": 5.152135759592056, | |
| "children": { | |
| "TorchPolicy.evaluate": { | |
| "total": 148.88300108909607, | |
| "count": 64622, | |
| "self": 148.88300108909607 | |
| } | |
| } | |
| }, | |
| "workers": { | |
| "total": 0.5135797560214996, | |
| "count": 32550, | |
| "self": 0.0, | |
| "children": { | |
| "worker_root": { | |
| "total": 1401.7815813720226, | |
| "count": 32550, | |
| "is_parallel": true, | |
| "self": 996.6275491714478, | |
| "children": { | |
| "run_training.setup": { | |
| "total": 0.0, | |
| "count": 0, | |
| "is_parallel": true, | |
| "self": 0.0, | |
| "children": { | |
| "steps_from_proto": { | |
| "total": 0.002947598695755005, | |
| "count": 2, | |
| "is_parallel": true, | |
| "self": 0.0007066130638122559, | |
| "children": { | |
| "_process_rank_one_or_two_observation": { | |
| "total": 0.002240985631942749, | |
| "count": 8, | |
| "is_parallel": true, | |
| "self": 0.002240985631942749 | |
| } | |
| } | |
| }, | |
| "UnityEnvironment.step": { | |
| "total": 0.032321780920028687, | |
| "count": 1, | |
| "is_parallel": true, | |
| "self": 0.0007331967353820801, | |
| "children": { | |
| "UnityEnvironment._generate_step_input": { | |
| "total": 0.0005863308906555176, | |
| "count": 1, | |
| "is_parallel": true, | |
| "self": 0.0005863308906555176 | |
| }, | |
| "communicator.exchange": { | |
| "total": 0.028720557689666748, | |
| "count": 1, | |
| "is_parallel": true, | |
| "self": 0.028720557689666748 | |
| }, | |
| "steps_from_proto": { | |
| "total": 0.002281695604324341, | |
| "count": 2, | |
| "is_parallel": true, | |
| "self": 0.0005029737949371338, | |
| "children": { | |
| "_process_rank_one_or_two_observation": { | |
| "total": 0.001778721809387207, | |
| "count": 8, | |
| "is_parallel": true, | |
| "self": 0.001778721809387207 | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| }, | |
| "UnityEnvironment.step": { | |
| "total": 405.1495250761509, | |
| "count": 32549, | |
| "is_parallel": true, | |
| "self": 22.349061518907547, | |
| "children": { | |
| "UnityEnvironment._generate_step_input": { | |
| "total": 14.447331070899963, | |
| "count": 32549, | |
| "is_parallel": true, | |
| "self": 14.447331070899963 | |
| }, | |
| "communicator.exchange": { | |
| "total": 300.657431602478, | |
| "count": 32549, | |
| "is_parallel": true, | |
| "self": 300.657431602478 | |
| }, | |
| "steps_from_proto": { | |
| "total": 67.69570088386536, | |
| "count": 65098, | |
| "is_parallel": true, | |
| "self": 13.194623231887817, | |
| "children": { | |
| "_process_rank_one_or_two_observation": { | |
| "total": 54.50107765197754, | |
| "count": 260392, | |
| "is_parallel": true, | |
| "self": 54.50107765197754 | |
| } | |
| } | |
| } | |
| } | |
| }, | |
| "steps_from_proto": { | |
| "total": 0.004507124423980713, | |
| "count": 4, | |
| "is_parallel": true, | |
| "self": 0.0009228885173797607, | |
| "children": { | |
| "_process_rank_one_or_two_observation": { | |
| "total": 0.003584235906600952, | |
| "count": 16, | |
| "is_parallel": true, | |
| "self": 0.003584235906600952 | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| }, | |
| "trainer_advance": { | |
| "total": 745.9242981374264, | |
| "count": 32550, | |
| "self": 7.037723183631897, | |
| "children": { | |
| "process_trajectory": { | |
| "total": 95.91130197048187, | |
| "count": 32550, | |
| "self": 95.68010273575783, | |
| "children": { | |
| "RLTrainer._checkpoint": { | |
| "total": 0.2311992347240448, | |
| "count": 1, | |
| "self": 0.2311992347240448 | |
| } | |
| } | |
| }, | |
| "_update_policy": { | |
| "total": 642.9752729833126, | |
| "count": 23, | |
| "self": 96.8378726541996, | |
| "children": { | |
| "TorchPOCAOptimizer.update": { | |
| "total": 546.137400329113, | |
| "count": 693, | |
| "self": 546.137400329113 | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| }, | |
| "trainer_threads": { | |
| "total": 1.043081283569336e-06, | |
| "count": 1, | |
| "self": 1.043081283569336e-06 | |
| }, | |
| "TrainerController._save_models": { | |
| "total": 0.2176450788974762, | |
| "count": 1, | |
| "self": 0.0016064941883087158, | |
| "children": { | |
| "RLTrainer._checkpoint": { | |
| "total": 0.21603858470916748, | |
| "count": 1, | |
| "self": 0.21603858470916748 | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } |