{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 3.1824750900268555, "min": 3.1547484397888184, "max": 3.2956900596618652, "count": 100 }, "SoccerTwos.Policy.Entropy.sum": { "value": 88701.9453125, "min": 23412.0703125, "max": 114764.3203125, "count": 100 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 860.5, "min": 489.9, "max": 999.0, "count": 100 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 20652.0, "min": 14644.0, "max": 27616.0, "count": 100 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1200.78991806887, "min": 1197.0440605645447, "max": 1207.1172065682176, "count": 90 }, "SoccerTwos.Self-play.ELO.sum": { "value": 4803.15967227548, "min": 2394.0881211290894, "max": 16784.708841766012, "count": 90 }, "SoccerTwos.Step.mean": { "value": 999684.0, "min": 9824.0, "max": 999684.0, "count": 100 }, "SoccerTwos.Step.sum": { "value": 999684.0, "min": 9824.0, "max": 999684.0, "count": 100 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": -0.00797598622739315, "min": -0.036553021520376205, "max": 0.05947311595082283, "count": 100 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": -0.0957118347287178, "min": -0.438421368598938, "max": 0.8325973749160767, "count": 100 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": -0.006179752293974161, "min": -0.022581540048122406, "max": 0.05948488041758537, "count": 100 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": -0.07415702939033508, "min": -0.27457916736602783, "max": 0.8327765464782715, "count": 100 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 100 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 100 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": -0.16666666666666666, "min": -0.5860000000550196, "max": 0.38087058768552895, "count": 100 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": -2.0, "min": -8.0, "max": 6.474799990653992, "count": 100 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": -0.16666666666666666, "min": -0.5860000000550196, "max": 0.38087058768552895, "count": 100 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": -2.0, "min": -8.0, "max": 6.474799990653992, "count": 100 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 100 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 100 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.012221555140179892, "min": 0.006795583742981156, "max": 0.016645218633736174, "count": 46 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.012221555140179892, "min": 0.006795583742981156, "max": 0.016645218633736174, "count": 46 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.003237667710830768, "min": 8.194062053613985e-05, "max": 0.01861500459102293, "count": 46 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.003237667710830768, "min": 8.194062053613985e-05, "max": 0.01861500459102293, "count": 46 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.00324154964958628, "min": 7.848465102142655e-05, "max": 0.009435744381820162, "count": 46 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.00324154964958628, "min": 7.848465102142655e-05, "max": 0.009435744381820162, "count": 46 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0006, "min": 0.0006, "max": 0.0006, "count": 46 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0006, "min": 0.0006, "max": 0.0006, "count": 46 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 46 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 46 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005, "min": 0.005, "max": 0.005, "count": 46 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005, "min": 0.005, "max": 0.005, "count": 46 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1697686348", "python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [GCC 11.4.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos.x86_64 --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": "2.0.1+cu118", "numpy_version": "1.23.5", "end_time_seconds": "1697688565" }, "total": 2217.164994551, "count": 1, "self": 0.4259129499996561, "children": { "run_training.setup": { "total": 0.07464664500002982, "count": 1, "self": 0.07464664500002982 }, "TrainerController.start_learning": { "total": 2216.664434956, "count": 1, "self": 1.6753877999994984, "children": { "TrainerController._reset_env": { "total": 4.416130657000224, "count": 5, "self": 4.416130657000224 }, "TrainerController.advance": { "total": 2210.3573846880004, "count": 65069, "self": 1.8022751490188966, "children": { "env_step": { "total": 1823.0047769609614, "count": 65069, "self": 1406.1171325439245, "children": { "SubprocessEnvManager._take_step": { "total": 415.8875872410355, "count": 65069, "self": 11.887741108043144, "children": { "TorchPolicy.evaluate": { "total": 403.99984613299233, "count": 129182, "self": 403.99984613299233 } } }, "workers": { "total": 1.0000571760013486, "count": 65069, "self": 0.0, "children": { "worker_root": { "total": 2212.1702933349934, "count": 65069, "is_parallel": true, "self": 1033.889048864969, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0044236590000537035, "count": 2, "is_parallel": true, "self": 0.0009960950001186575, "children": { "_process_rank_one_or_two_observation": { "total": 0.003427563999935046, "count": 8, "is_parallel": true, "self": 0.003427563999935046 } } }, "UnityEnvironment.step": { "total": 0.0418704440000397, "count": 1, "is_parallel": true, "self": 0.0012168680000286258, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0008716350000099737, "count": 1, "is_parallel": true, "self": 0.0008716350000099737 }, "communicator.exchange": { "total": 0.035724202000039895, "count": 1, "is_parallel": true, "self": 0.035724202000039895 }, "steps_from_proto": { "total": 0.004057738999961202, "count": 2, "is_parallel": true, "self": 0.0006634809998899982, "children": { "_process_rank_one_or_two_observation": { "total": 0.003394258000071204, "count": 8, "is_parallel": true, "self": 0.003394258000071204 } } } } } } }, "UnityEnvironment.step": { "total": 1178.2684012030245, "count": 65068, "is_parallel": true, "self": 75.30102161908849, "children": { "UnityEnvironment._generate_step_input": { "total": 49.89441047398384, "count": 65068, "is_parallel": true, "self": 49.89441047398384 }, "communicator.exchange": { "total": 818.6866904860156, "count": 65068, "is_parallel": true, "self": 818.6866904860156 }, "steps_from_proto": { "total": 234.38627862393668, "count": 130136, "is_parallel": true, "self": 37.99782386399312, "children": { "_process_rank_one_or_two_observation": { "total": 196.38845475994356, "count": 520544, "is_parallel": true, "self": 196.38845475994356 } } } } }, "steps_from_proto": { "total": 0.012843266999880143, "count": 8, "is_parallel": true, "self": 0.002305757999351954, "children": { "_process_rank_one_or_two_observation": { "total": 0.010537509000528189, "count": 32, "is_parallel": true, "self": 0.010537509000528189 } } } } } } } } }, "trainer_advance": { "total": 385.55033257802, "count": 65069, "self": 14.281712731008213, "children": { "process_trajectory": { "total": 109.3654763670126, "count": 65069, "self": 108.84511364601275, "children": { "RLTrainer._checkpoint": { "total": 0.5203627209998558, "count": 2, "self": 0.5203627209998558 } } }, "_update_policy": { "total": 261.9031434799992, "count": 46, "self": 161.58336632699843, "children": { "TorchPOCAOptimizer.update": { "total": 100.31977715300076, "count": 690, "self": 100.31977715300076 } } } } } } }, "trainer_threads": { "total": 1.0740000107034575e-06, "count": 1, "self": 1.0740000107034575e-06 }, "TrainerController._save_models": { "total": 0.2155307369998809, "count": 1, "self": 0.001797785000235308, "children": { "RLTrainer._checkpoint": { "total": 0.2137329519996456, "count": 1, "self": 0.2137329519996456 } } } } } } }