{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 1.2792309522628784, "min": 1.2348917722702026, "max": 3.295727252960205, "count": 5000 }, "SoccerTwos.Policy.Entropy.sum": { "value": 25216.201171875, "min": 11426.8828125, "max": 134543.75, "count": 5000 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 59.75949367088607, "min": 40.388429752066116, "max": 999.0, "count": 5000 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 18884.0, "min": 14500.0, "max": 24340.0, "count": 5000 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1767.9656107546107, "min": 1191.9382821023419, "max": 1782.8306777461685, "count": 4982 }, "SoccerTwos.Self-play.ELO.sum": { "value": 279338.5664992285, "min": 2384.4752223632195, "max": 405713.0592094655, "count": 4982 }, "SoccerTwos.Step.mean": { "value": 49999956.0, "min": 9186.0, "max": 49999956.0, "count": 5000 }, "SoccerTwos.Step.sum": { "value": 49999956.0, "min": 9186.0, "max": 49999956.0, "count": 5000 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": -0.015709569677710533, "min": -0.13414104282855988, "max": 0.14972151815891266, "count": 5000 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": -2.482111930847168, "min": -22.539691925048828, "max": 26.333171844482422, "count": 5000 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": -0.018381375819444656, "min": -0.13297967612743378, "max": 0.1550787091255188, "count": 5000 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": -2.904257297515869, "min": -23.7386474609375, "max": 26.646390914916992, "count": 5000 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 5000 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 5000 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": -0.09320759848703312, "min": -0.45454545454545453, "max": 0.7292054118336858, "count": 5000 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": -14.726800560951233, "min": -75.5279997587204, "max": 64.1581996679306, "count": 5000 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": -0.09320759848703312, "min": -0.45454545454545453, "max": 0.7292054118336858, "count": 5000 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": -14.726800560951233, "min": -75.5279997587204, "max": 64.1581996679306, "count": 5000 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 5000 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 5000 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.017915759057117005, "min": 0.010427622961772916, "max": 0.02776472925907001, "count": 2424 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.017915759057117005, "min": 0.010427622961772916, "max": 0.02776472925907001, "count": 2424 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.09312237774332364, "min": 3.7741704318250412e-06, "max": 0.12538409580787022, "count": 2424 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.09312237774332364, "min": 3.7741704318250412e-06, "max": 0.12538409580787022, "count": 2424 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.09427823250492413, "min": 3.757458853215212e-06, "max": 0.12788692712783814, "count": 2424 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.09427823250492413, "min": 3.757458853215212e-06, "max": 0.12788692712783814, "count": 2424 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 2424 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 2424 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 2424 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 2424 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 2424 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 2424 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1696857307", "python_version": "3.10.12 | packaged by conda-forge | (main, Jun 23 2023, 22:41:52) [Clang 15.0.7 ]", "command_line_arguments": "/Users/alperenunlu/miniconda3/envs/hfrl/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos.app --run-id=SoccerTwos --no-graphics", "mlagents_version": "0.31.0.dev0", "mlagents_envs_version": "0.31.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.1.0", "numpy_version": "1.21.6", "end_time_seconds": "1696926855" }, "total": 69547.96126275, "count": 1, "self": 0.1924785840092227, "children": { "run_training.setup": { "total": 0.01784787500037055, "count": 1, "self": 0.01784787500037055 }, "TrainerController.start_learning": { "total": 69547.75093629099, "count": 1, "self": 33.873271768694394, "children": { "TrainerController._reset_env": { "total": 4.566003870908389, "count": 250, "self": 4.566003870908389 }, "TrainerController.advance": { "total": 69509.12868431839, "count": 3445248, "self": 34.666333544562804, "children": { "env_step": { "total": 31228.314172267033, "count": 3445248, "self": 25826.774199176496, "children": { "SubprocessEnvManager._take_step": { "total": 5378.584716483001, "count": 3445248, "self": 173.74828816894842, "children": { "TorchPolicy.evaluate": { "total": 5204.836428314053, "count": 6282496, "self": 5204.836428314053 } } }, "workers": { "total": 22.955256607536285, "count": 3445248, "self": 0.0, "children": { "worker_root": { "total": 69495.22190905761, "count": 3445248, "is_parallel": true, "self": 47919.383802495104, "children": { "steps_from_proto": { "total": 0.22924178894209035, "count": 500, "is_parallel": true, "self": 0.03909412305984006, "children": { "_process_rank_one_or_two_observation": { "total": 0.1901476658822503, "count": 2000, "is_parallel": true, "self": 0.1901476658822503 } } }, "UnityEnvironment.step": { "total": 21575.608864773563, "count": 3445248, "is_parallel": true, "self": 1004.7523217016242, "children": { "UnityEnvironment._generate_step_input": { "total": 538.3339753676428, "count": 3445248, "is_parallel": true, "self": 538.3339753676428 }, "communicator.exchange": { "total": 17077.4096530072, "count": 3445248, "is_parallel": true, "self": 17077.4096530072 }, "steps_from_proto": { "total": 2955.1129146970998, "count": 6890496, "is_parallel": true, "self": 493.39010991019677, "children": { "_process_rank_one_or_two_observation": { "total": 2461.722804786903, "count": 27561984, "is_parallel": true, "self": 2461.722804786903 } } } } } } } } } } }, "trainer_advance": { "total": 38246.14817850679, "count": 3445248, "self": 300.6736709216493, "children": { "process_trajectory": { "total": 8356.710882550342, "count": 3445248, "self": 8337.45565305235, "children": { "RLTrainer._checkpoint": { "total": 19.25522949799233, "count": 100, "self": 19.25522949799233 } } }, "_update_policy": { "total": 29588.763625034797, "count": 2424, "self": 4328.309902221739, "children": { "TorchPOCAOptimizer.update": { "total": 25260.453722813058, "count": 72720, "self": 25260.453722813058 } } } } } } }, "trainer_threads": { "total": 4.169996827840805e-07, "count": 1, "self": 4.169996827840805e-07 }, "TrainerController._save_models": { "total": 0.18297591600276064, "count": 1, "self": 0.0008541249990230426, "children": { "RLTrainer._checkpoint": { "total": 0.1821217910037376, "count": 1, "self": 0.1821217910037376 } } } } } } }