{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 1.2069785594940186, "min": 1.1519638299942017, "max": 3.2957663536071777, "count": 8999 }, "SoccerTwos.Policy.Entropy.sum": { "value": 23444.3515625, "min": 20343.66796875, "max": 147094.890625, "count": 8999 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 79.6774193548387, "min": 39.185483870967744, "max": 999.0, "count": 8999 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19760.0, "min": 8864.0, "max": 31396.0, "count": 8999 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1637.9723568246582, "min": 1200.645224070351, "max": 1767.4417653790651, "count": 8948 }, "SoccerTwos.Self-play.ELO.sum": { "value": 203108.57224625762, "min": 2401.4985608882907, "max": 416689.551365559, "count": 8948 }, "SoccerTwos.Step.mean": { "value": 89999950.0, "min": 9614.0, "max": 89999950.0, "count": 9000 }, "SoccerTwos.Step.sum": { "value": 89999950.0, "min": 9614.0, "max": 89999950.0, "count": 9000 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": -0.04528549686074257, "min": -0.14936614036560059, "max": 0.1762223243713379, "count": 9000 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": -5.615401744842529, "min": -26.587173461914062, "max": 22.4957275390625, "count": 9000 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": -0.04430653154850006, "min": -0.15035443007946014, "max": 0.17547571659088135, "count": 9000 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": -5.494009971618652, "min": -26.76308822631836, "max": 21.601240158081055, "count": 9000 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 9000 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 9000 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": -0.06870322554342208, "min": -0.6929217369660087, "max": 0.588721049459357, "count": 9000 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": -8.519199967384338, "min": -81.41719990968704, "max": 60.69200003147125, "count": 9000 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": -0.06870322554342208, "min": -0.6929217369660087, "max": 0.588721049459357, "count": 9000 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": -8.519199967384338, "min": -81.41719990968704, "max": 60.69200003147125, "count": 9000 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 9000 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 9000 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.01696835795204, "min": 0.010225175912880028, "max": 0.02756322702431741, "count": 4362 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.01696835795204, "min": 0.010225175912880028, "max": 0.02756322702431741, "count": 4362 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.09537215183178584, "min": 3.76701187102905e-07, "max": 0.1309762547413508, "count": 4362 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.09537215183178584, "min": 3.76701187102905e-07, "max": 0.1309762547413508, "count": 4362 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.095896864682436, "min": 3.402811742603262e-07, "max": 0.1331341601908207, "count": 4362 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.095896864682436, "min": 3.402811742603262e-07, "max": 0.1331341601908207, "count": 4362 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 4362 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 4362 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.19999999999999996, "max": 0.20000000000000007, "count": 4362 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.19999999999999996, "max": 0.20000000000000007, "count": 4362 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005, "max": 0.005000000000000001, "count": 4362 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005, "max": 0.005000000000000001, "count": 4362 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1680302834", "python_version": "3.9.16 (main, Mar 8 2023, 14:00:05) \n[GCC 11.2.0]", "command_line_arguments": "/home/jan/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": "1680724447" }, "total": 421613.31471759605, "count": 1, "self": 1.4359463970758952, "children": { "run_training.setup": { "total": 0.0049585169999772916, "count": 1, "self": 0.0049585169999772916 }, "TrainerController.start_learning": { "total": 421611.873812682, "count": 1, "self": 95.89959785336396, "children": { "TrainerController._reset_env": { "total": 28.345651683729102, "count": 450, "self": 28.345651683729102 }, "TrainerController.advance": { "total": 421487.4963761159, "count": 6198247, "self": 92.75453607260715, "children": { "env_step": { "total": 256137.87799469387, "count": 6198247, "self": 247140.52757368324, "children": { "SubprocessEnvManager._take_step": { "total": 8939.566539897594, "count": 6198247, "self": 420.96175613394007, "children": { "TorchPolicy.evaluate": { "total": 8518.604783763654, "count": 11309388, "self": 8518.604783763654 } } }, "workers": { "total": 57.78388111305094, "count": 6198247, "self": 0.0, "children": { "worker_root": { "total": 421433.10110786615, "count": 6198247, "is_parallel": true, "self": 184609.6922954054, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0015856539998821972, "count": 2, "is_parallel": true, "self": 0.000342001000262826, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012436529996193713, "count": 8, "is_parallel": true, "self": 0.0012436529996193713 } } }, "UnityEnvironment.step": { "total": 0.04110677200014834, "count": 1, "is_parallel": true, "self": 0.00010277500041411258, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0017358219997731794, "count": 1, "is_parallel": true, "self": 0.0017358219997731794 }, "communicator.exchange": { "total": 0.03807699399976627, "count": 1, "is_parallel": true, "self": 0.03807699399976627 }, "steps_from_proto": { "total": 0.0011911810001947742, "count": 2, "is_parallel": true, "self": 0.00017413800105714472, "children": { "_process_rank_one_or_two_observation": { "total": 0.0010170429991376295, "count": 8, "is_parallel": true, "self": 0.0010170429991376295 } } } } } } }, "UnityEnvironment.step": { "total": 236822.3473638677, "count": 6198246, "is_parallel": true, "self": 627.3452969472273, "children": { "UnityEnvironment._generate_step_input": { "total": 4681.217732870498, "count": 6198246, "is_parallel": true, "self": 4681.217732870498 }, "communicator.exchange": { "total": 223759.92125021463, "count": 6198246, "is_parallel": true, "self": 223759.92125021463 }, "steps_from_proto": { "total": 7753.8630838353765, "count": 12396492, "is_parallel": true, "self": 1104.3048718534046, "children": { "_process_rank_one_or_two_observation": { "total": 6649.558211981972, "count": 49585968, "is_parallel": true, "self": 6649.558211981972 } } } } }, "steps_from_proto": { "total": 1.0614485930459523, "count": 898, "is_parallel": true, "self": 0.16432144990039887, "children": { "_process_rank_one_or_two_observation": { "total": 0.8971271431455534, "count": 3592, "is_parallel": true, "self": 0.8971271431455534 } } } } } } } } }, "trainer_advance": { "total": 165256.8638453494, "count": 6198247, "self": 658.7463159288454, "children": { "process_trajectory": { "total": 10689.392428211484, "count": 6198247, "self": 10658.611134363322, "children": { "RLTrainer._checkpoint": { "total": 30.781293848162022, "count": 180, "self": 30.781293848162022 } } }, "_update_policy": { "total": 153908.72510120907, "count": 4362, "self": 7189.026425535325, "children": { "TorchPOCAOptimizer.update": { "total": 146719.69867567375, "count": 130872, "self": 146719.69867567375 } } } } } } }, "trainer_threads": { "total": 7.200287654995918e-07, "count": 1, "self": 7.200287654995918e-07 }, "TrainerController._save_models": { "total": 0.13218630896881223, "count": 1, "self": 0.04532258596736938, "children": { "RLTrainer._checkpoint": { "total": 0.08686372300144285, "count": 1, "self": 0.08686372300144285 } } } } } } }