{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 2.549652099609375, "min": 2.531156063079834, "max": 3.2958154678344727, "count": 999 }, "SoccerTwos.Policy.Entropy.sum": { "value": 25047.78125, "min": 3594.928466796875, "max": 105466.078125, "count": 999 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 62.38461538461539, "min": 51.95652173913044, "max": 999.0, "count": 999 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 9732.0, "min": 6468.0, "max": 23856.0, "count": 999 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1537.1163265694297, "min": 1296.0654819099525, "max": 1548.7485052944705, "count": 986 }, "SoccerTwos.Self-play.ELO.sum": { "value": 119895.07347241552, "min": 2592.130963819905, "max": 146980.3787139268, "count": 986 }, "SoccerTwos.Step.mean": { "value": 4999985.0, "min": 4946.0, "max": 4999985.0, "count": 1000 }, "SoccerTwos.Step.sum": { "value": 4999985.0, "min": 4946.0, "max": 4999985.0, "count": 1000 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": 0.0003761997795663774, "min": -0.17155928909778595, "max": 0.17822957038879395, "count": 1000 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": 0.029343582689762115, "min": -13.553183555603027, "max": 9.980855941772461, "count": 1000 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": 0.001597140566445887, "min": -0.17013998329639435, "max": 0.17541848123073578, "count": 1000 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": 0.12457696348428726, "min": -13.441058158874512, "max": 9.84109115600586, "count": 1000 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 1000 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 1000 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": 0.01829230785369873, "min": -1.0, "max": 0.5714214284505162, "count": 1000 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": 1.426800012588501, "min": -34.70759999752045, "max": 31.999599993228912, "count": 1000 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": 0.01829230785369873, "min": -1.0, "max": 0.5714214284505162, "count": 1000 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": 1.426800012588501, "min": -34.70759999752045, "max": 31.999599993228912, "count": 1000 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 1000 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 1000 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.01634866907406831, "min": 0.008290400767691608, "max": 0.017184779205126687, "count": 121 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.01634866907406831, "min": 0.008290400767691608, "max": 0.017184779205126687, "count": 121 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.09136400073766708, "min": 0.002722801166237332, "max": 0.0995924312621355, "count": 121 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.09136400073766708, "min": 0.002722801166237332, "max": 0.0995924312621355, "count": 121 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.09407038893550634, "min": 0.002740770936361514, "max": 0.1027330020442605, "count": 121 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.09407038893550634, "min": 0.002740770936361514, "max": 0.1027330020442605, "count": 121 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0001, "min": 0.0001, "max": 0.0001, "count": 121 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0001, "min": 0.0001, "max": 0.0001, "count": 121 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.15, "min": 0.15, "max": 0.15, "count": 121 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.15, "min": 0.15, "max": 0.15, "count": 121 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.01, "min": 0.01, "max": 0.01, "count": 121 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.01, "min": 0.01, "max": 0.01, "count": 121 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1726808519", "python_version": "3.10.12 (main, Sep 11 2024, 15:47:36) [GCC 11.4.0]", "command_line_arguments": "/home/cimcon/.local/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos/SoccerTwos.x86_64 --run-id=SoccerTwos4 --no-graphics", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.2.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1726833339" }, "total": 24819.974882034003, "count": 1, "self": 0.39391662400157657, "children": { "run_training.setup": { "total": 0.04371372899913695, "count": 1, "self": 0.04371372899913695 }, "TrainerController.start_learning": { "total": 24819.537251681002, "count": 1, "self": 6.5253307148232125, "children": { "TrainerController._reset_env": { "total": 3.4250789890356828, "count": 50, "self": 3.4250789890356828 }, "TrainerController.advance": { "total": 24808.916593573143, "count": 338182, "self": 6.673431090224767, "children": { "env_step": { "total": 5454.4803859715175, "count": 338182, "self": 3846.587014699544, "children": { "SubprocessEnvManager._take_step": { "total": 1603.9386386508268, "count": 338182, "self": 44.945016948186094, "children": { "TorchPolicy.evaluate": { "total": 1558.9936217026407, "count": 635088, "self": 1558.9936217026407 } } }, "workers": { "total": 3.9547326211468317, "count": 338182, "self": 0.0, "children": { "worker_root": { "total": 24810.41101118461, "count": 338182, "is_parallel": true, "self": 21716.23323050198, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0020851630106335506, "count": 2, "is_parallel": true, "self": 0.0004955230106133968, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015896400000201538, "count": 8, "is_parallel": true, "self": 0.0015896400000201538 } } }, "UnityEnvironment.step": { "total": 0.019626065986813046, "count": 1, "is_parallel": true, "self": 0.0004625220026355237, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0003749309980776161, "count": 1, "is_parallel": true, "self": 0.0003749309980776161 }, "communicator.exchange": { "total": 0.017260993001400493, "count": 1, "is_parallel": true, "self": 0.017260993001400493 }, "steps_from_proto": { "total": 0.0015276199846994132, "count": 2, "is_parallel": true, "self": 0.0003040669980691746, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012235529866302386, "count": 8, "is_parallel": true, "self": 0.0012235529866302386 } } } } } } }, "UnityEnvironment.step": { "total": 3094.105826568659, "count": 338181, "is_parallel": true, "self": 153.45056534878677, "children": { "UnityEnvironment._generate_step_input": { "total": 113.4950077731628, "count": 338181, "is_parallel": true, "self": 113.4950077731628 }, "communicator.exchange": { "total": 2345.893377115164, "count": 338181, "is_parallel": true, "self": 2345.893377115164 }, "steps_from_proto": { "total": 481.26687633154506, "count": 676362, "is_parallel": true, "self": 95.02908025567012, "children": { "_process_rank_one_or_two_observation": { "total": 386.23779607587494, "count": 2705448, "is_parallel": true, "self": 386.23779607587494 } } } } }, "steps_from_proto": { "total": 0.07195411396969575, "count": 98, "is_parallel": true, "self": 0.014059000910492614, "children": { "_process_rank_one_or_two_observation": { "total": 0.05789511305920314, "count": 392, "is_parallel": true, "self": 0.05789511305920314 } } } } } } } } }, "trainer_advance": { "total": 19347.7627765114, "count": 338182, "self": 56.05197318458522, "children": { "process_trajectory": { "total": 2050.2861783408152, "count": 338182, "self": 2044.0442390817916, "children": { "RLTrainer._checkpoint": { "total": 6.241939259023638, "count": 10, "self": 6.241939259023638 } } }, "_update_policy": { "total": 17241.424624986, "count": 121, "self": 747.4267182948097, "children": { "TorchPOCAOptimizer.update": { "total": 16493.99790669119, "count": 4840, "self": 16493.99790669119 } } } } } } }, "trainer_threads": { "total": 6.689951987937093e-07, "count": 1, "self": 6.689951987937093e-07 }, "TrainerController._save_models": { "total": 0.6702477350045228, "count": 1, "self": 0.005346545003703795, "children": { "RLTrainer._checkpoint": { "total": 0.664901190000819, "count": 1, "self": 0.664901190000819 } } } } } } }