{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 3.1563942432403564, "min": 3.149630308151245, "max": 3.2956900596618652, "count": 50 }, "SoccerTwos.Policy.Entropy.sum": { "value": 66663.046875, "min": 25940.142578125, "max": 111828.1015625, "count": 50 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 300.6470588235294, "min": 261.3333333333333, "max": 999.0, "count": 50 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 20444.0, "min": 14672.0, "max": 28340.0, "count": 50 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1219.5692826964037, "min": 1198.0168266386224, "max": 1219.5692826964037, "count": 43 }, "SoccerTwos.Self-play.ELO.sum": { "value": 36587.07848089211, "min": 2396.033653277245, "max": 41411.70517627378, "count": 43 }, "SoccerTwos.Step.mean": { "value": 499232.0, "min": 9950.0, "max": 499232.0, "count": 50 }, "SoccerTwos.Step.sum": { "value": 499232.0, "min": 9950.0, "max": 499232.0, "count": 50 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": 0.03765362128615379, "min": -0.009388549253344536, "max": 0.04418336600065231, "count": 50 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": 1.2425694465637207, "min": -0.12511155009269714, "max": 1.458051085472107, "count": 50 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": 0.03904584422707558, "min": -0.009185528382658958, "max": 0.05486869812011719, "count": 50 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": 1.2885128259658813, "min": -0.12370288372039795, "max": 1.8106670379638672, "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": 0.48296364148457843, "min": -0.5384615384615384, "max": 0.48296364148457843, "count": 50 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": 15.937800168991089, "min": -12.301000118255615, "max": 15.937800168991089, "count": 50 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": 0.48296364148457843, "min": -0.5384615384615384, "max": 0.48296364148457843, "count": 50 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": 15.937800168991089, "min": -12.301000118255615, "max": 15.937800168991089, "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": 0.019610659056343138, "min": 0.014299746853066609, "max": 0.020620077780040446, "count": 23 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.019610659056343138, "min": 0.014299746853066609, "max": 0.020620077780040446, "count": 23 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.017787810197720924, "min": 0.0004044039160362445, "max": 0.017787810197720924, "count": 23 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.017787810197720924, "min": 0.0004044039160362445, "max": 0.017787810197720924, "count": 23 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.018563354884584746, "min": 0.0004041414142799719, "max": 0.018563354884584746, "count": 23 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.018563354884584746, "min": 0.0004041414142799719, "max": 0.018563354884584746, "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": "1701589940", "python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [GCC 11.4.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos.exe --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": "2.1.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1701591452" }, "total": 1512.5341511859988, "count": 1, "self": 0.37710676999631687, "children": { "run_training.setup": { "total": 0.05790981900281622, "count": 1, "self": 0.05790981900281622 }, "TrainerController.start_learning": { "total": 1512.0991345969996, "count": 1, "self": 1.11143703858761, "children": { "TrainerController._reset_env": { "total": 2.554106884996145, "count": 3, "self": 2.554106884996145 }, "TrainerController.advance": { "total": 1508.223750191417, "count": 32636, "self": 1.2235327585294726, "children": { "env_step": { "total": 897.9893766806708, "count": 32636, "self": 715.3867988462698, "children": { "SubprocessEnvManager._take_step": { "total": 181.87036738228198, "count": 32636, "self": 6.958218602518173, "children": { "TorchPolicy.evaluate": { "total": 174.9121487797638, "count": 64724, "self": 174.9121487797638 } } }, "workers": { "total": 0.732210452119034, "count": 32636, "self": 0.0, "children": { "worker_root": { "total": 1509.174110517837, "count": 32636, "is_parallel": true, "self": 939.3240124901131, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.003827897999144625, "count": 2, "is_parallel": true, "self": 0.001106725998397451, "children": { "_process_rank_one_or_two_observation": { "total": 0.002721172000747174, "count": 8, "is_parallel": true, "self": 0.002721172000747174 } } }, "UnityEnvironment.step": { "total": 0.03494443399904412, "count": 1, "is_parallel": true, "self": 0.0013591089918918442, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0006393720032065175, "count": 1, "is_parallel": true, "self": 0.0006393720032065175 }, "communicator.exchange": { "total": 0.02888951200293377, "count": 1, "is_parallel": true, "self": 0.02888951200293377 }, "steps_from_proto": { "total": 0.00405644100101199, "count": 2, "is_parallel": true, "self": 0.0007671239982300904, "children": { "_process_rank_one_or_two_observation": { "total": 0.0032893170027818996, "count": 8, "is_parallel": true, "self": 0.0032893170027818996 } } } } } } }, "UnityEnvironment.step": { "total": 569.845528380727, "count": 32635, "is_parallel": true, "self": 36.250143324890814, "children": { "UnityEnvironment._generate_step_input": { "total": 24.222136394961126, "count": 32635, "is_parallel": true, "self": 24.222136394961126 }, "communicator.exchange": { "total": 405.8313904701572, "count": 32635, "is_parallel": true, "self": 405.8313904701572 }, "steps_from_proto": { "total": 103.5418581907179, "count": 65270, "is_parallel": true, "self": 18.407087022293126, "children": { "_process_rank_one_or_two_observation": { "total": 85.13477116842478, "count": 261080, "is_parallel": true, "self": 85.13477116842478 } } } } }, "steps_from_proto": { "total": 0.004569646996969823, "count": 4, "is_parallel": true, "self": 0.0008489149986417033, "children": { "_process_rank_one_or_two_observation": { "total": 0.0037207319983281195, "count": 16, "is_parallel": true, "self": 0.0037207319983281195 } } } } } } } } }, "trainer_advance": { "total": 609.0108407522166, "count": 32636, "self": 9.133657020021928, "children": { "process_trajectory": { "total": 99.48270784419219, "count": 32636, "self": 99.22933577319054, "children": { "RLTrainer._checkpoint": { "total": 0.2533720710016496, "count": 1, "self": 0.2533720710016496 } } }, "_update_policy": { "total": 500.3944758880025, "count": 23, "self": 84.26536148403466, "children": { "TorchPOCAOptimizer.update": { "total": 416.12911440396783, "count": 693, "self": 416.12911440396783 } } } } } } }, "trainer_threads": { "total": 9.690011211205274e-07, "count": 1, "self": 9.690011211205274e-07 }, "TrainerController._save_models": { "total": 0.20983951299785986, "count": 1, "self": 0.0025311909994343296, "children": { "RLTrainer._checkpoint": { "total": 0.20730832199842553, "count": 1, "self": 0.20730832199842553 } } } } } } }