{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 1.5031105279922485, "min": 1.4853661060333252, "max": 3.295753240585327, "count": 600 }, "SoccerTwos.Policy.Entropy.sum": { "value": 30302.708984375, "min": 15746.2822265625, "max": 105464.1015625, "count": 600 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 44.648148148148145, "min": 38.67460317460318, "max": 999.0, "count": 600 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19288.0, "min": 7992.0, "max": 28552.0, "count": 600 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1567.3846019546936, "min": 1189.3936508408033, "max": 1583.8063739193924, "count": 593 }, "SoccerTwos.Self-play.ELO.sum": { "value": 338555.0740222138, "min": 2390.508945079749, "max": 384263.7276774414, "count": 593 }, "SoccerTwos.Step.mean": { "value": 5999832.0, "min": 9830.0, "max": 5999832.0, "count": 600 }, "SoccerTwos.Step.sum": { "value": 5999832.0, "min": 9830.0, "max": 5999832.0, "count": 600 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": -0.03408787399530411, "min": -0.10397680848836899, "max": 0.14669004082679749, "count": 600 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": -7.362980842590332, "min": -21.915634155273438, "max": 28.4429931640625, "count": 600 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": -0.03417100012302399, "min": -0.10394182801246643, "max": 0.1544579714536667, "count": 600 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": -7.3809356689453125, "min": -22.031593322753906, "max": 30.658737182617188, "count": 600 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 600 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 600 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": 0.023190740357946465, "min": -0.6257176469354069, "max": 0.5128818249160593, "count": 600 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": 5.009199917316437, "min": -61.58959984779358, "max": 63.226799964904785, "count": 600 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": 0.023190740357946465, "min": -0.6257176469354069, "max": 0.5128818249160593, "count": 600 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": 5.009199917316437, "min": -61.58959984779358, "max": 63.226799964904785, "count": 600 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 600 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 600 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.01506537000774794, "min": 0.009937849570997059, "max": 0.02400178289390169, "count": 289 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.01506537000774794, "min": 0.009937849570997059, "max": 0.02400178289390169, "count": 289 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.13020551279187204, "min": 5.6926707899644194e-05, "max": 0.13434325406948724, "count": 289 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.13020551279187204, "min": 5.6926707899644194e-05, "max": 0.13434325406948724, "count": 289 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.1305543358127276, "min": 6.166132200936166e-05, "max": 0.13478971819082897, "count": 289 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.1305543358127276, "min": 6.166132200936166e-05, "max": 0.13478971819082897, "count": 289 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 7.292997569333412e-07, "min": 7.292997569333412e-07, "max": 0.0002986438004520667, "count": 289 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 7.292997569333412e-07, "min": 7.292997569333412e-07, "max": 0.0002986438004520667, "count": 289 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.10024306666666669, "min": 0.10024306666666669, "max": 0.19954793333333332, "count": 289 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.10024306666666669, "min": 0.10024306666666669, "max": 0.19954793333333332, "count": 289 }, "SoccerTwos.Policy.Beta.mean": { "value": 2.212902666666679e-05, "min": 2.212902666666679e-05, "max": 0.004977441873333331, "count": 289 }, "SoccerTwos.Policy.Beta.sum": { "value": 2.212902666666679e-05, "min": 2.212902666666679e-05, "max": 0.004977441873333331, "count": 289 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1679178285", "python_version": "3.9.16 (main, Mar 8 2023, 14:00:05) \n[GCC 11.2.0]", "command_line_arguments": "/home/hrcesur/miniconda3/envs/rl/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos/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": "1679209314" }, "total": 31029.345825880002, "count": 1, "self": 0.47647523500199895, "children": { "run_training.setup": { "total": 0.017039080999893486, "count": 1, "self": 0.017039080999893486 }, "TrainerController.start_learning": { "total": 31028.852311564, "count": 1, "self": 11.62543190283759, "children": { "TrainerController._reset_env": { "total": 2.5118212519960252, "count": 30, "self": 2.5118212519960252 }, "TrainerController.advance": { "total": 31014.421411322168, "count": 415474, "self": 11.537319528641092, "children": { "env_step": { "total": 10265.694971100384, "count": 415474, "self": 7897.8433287695425, "children": { "SubprocessEnvManager._take_step": { "total": 2360.7215402472243, "count": 415474, "self": 80.8951467904476, "children": { "TorchPolicy.evaluate": { "total": 2279.8263934567767, "count": 754736, "self": 2279.8263934567767 } } }, "workers": { "total": 7.1301020836169755, "count": 415474, "self": 0.0, "children": { "worker_root": { "total": 31011.036387888747, "count": 415474, "is_parallel": true, "self": 24600.084445694643, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0054780430002665526, "count": 2, "is_parallel": true, "self": 0.0017358640002385073, "children": { "_process_rank_one_or_two_observation": { "total": 0.0037421790000280453, "count": 8, "is_parallel": true, "self": 0.0037421790000280453 } } }, "UnityEnvironment.step": { "total": 0.03557804899992334, "count": 1, "is_parallel": true, "self": 0.0014585970000098314, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0016622109999389068, "count": 1, "is_parallel": true, "self": 0.0016622109999389068 }, "communicator.exchange": { "total": 0.028263499999866326, "count": 1, "is_parallel": true, "self": 0.028263499999866326 }, "steps_from_proto": { "total": 0.004193741000108275, "count": 2, "is_parallel": true, "self": 0.0008658380002088961, "children": { "_process_rank_one_or_two_observation": { "total": 0.003327902999899379, "count": 8, "is_parallel": true, "self": 0.003327902999899379 } } } } } } }, "UnityEnvironment.step": { "total": 6410.838686295098, "count": 415473, "is_parallel": true, "self": 379.25663072938187, "children": { "UnityEnvironment._generate_step_input": { "total": 374.063670495638, "count": 415473, "is_parallel": true, "self": 374.063670495638 }, "communicator.exchange": { "total": 4562.090233859916, "count": 415473, "is_parallel": true, "self": 4562.090233859916 }, "steps_from_proto": { "total": 1095.4281512101627, "count": 830946, "is_parallel": true, "self": 240.53099280302786, "children": { "_process_rank_one_or_two_observation": { "total": 854.8971584071348, "count": 3323784, "is_parallel": true, "self": 854.8971584071348 } } } } }, "steps_from_proto": { "total": 0.11325589900388877, "count": 58, "is_parallel": true, "self": 0.024725750999550655, "children": { "_process_rank_one_or_two_observation": { "total": 0.08853014800433812, "count": 232, "is_parallel": true, "self": 0.08853014800433812 } } } } } } } } }, "trainer_advance": { "total": 20737.189120693143, "count": 415474, "self": 76.80797019366219, "children": { "process_trajectory": { "total": 3242.5880062994315, "count": 415474, "self": 3238.925574678427, "children": { "RLTrainer._checkpoint": { "total": 3.6624316210045436, "count": 12, "self": 3.6624316210045436 } } }, "_update_policy": { "total": 17417.793144200048, "count": 289, "self": 1486.0706528033752, "children": { "TorchPOCAOptimizer.update": { "total": 15931.722491396673, "count": 8685, "self": 15931.722491396673 } } } } } } }, "trainer_threads": { "total": 1.1779993656091392e-06, "count": 1, "self": 1.1779993656091392e-06 }, "TrainerController._save_models": { "total": 0.2936459089978598, "count": 1, "self": 0.002132837998942705, "children": { "RLTrainer._checkpoint": { "total": 0.2915130709989171, "count": 1, "self": 0.2915130709989171 } } } } } } }