{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 1.4295754432678223, "min": 1.4295754432678223, "max": 3.2956483364105225, "count": 2204 }, "SoccerTwos.Policy.Entropy.sum": { "value": 27722.328125, "min": 18316.36328125, "max": 120985.15625, "count": 2204 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 50.04210526315789, "min": 37.689922480620154, "max": 999.0, "count": 2204 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19016.0, "min": 4676.0, "max": 30216.0, "count": 2204 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1670.8702607693115, "min": 1200.2269656552999, "max": 1670.8702607693115, "count": 2202 }, "SoccerTwos.Self-play.ELO.sum": { "value": 317465.34954616916, "min": 2401.4985608882907, "max": 409782.57697789, "count": 2202 }, "SoccerTwos.Step.mean": { "value": 22039986.0, "min": 9348.0, "max": 22039986.0, "count": 2204 }, "SoccerTwos.Step.sum": { "value": 22039986.0, "min": 9348.0, "max": 22039986.0, "count": 2204 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": 0.03447429835796356, "min": -0.14727379381656647, "max": 0.15868721902370453, "count": 2204 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": 6.584590911865234, "min": -26.709228515625, "max": 31.771392822265625, "count": 2204 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": 0.03542308136820793, "min": -0.14488007128238678, "max": 0.16164880990982056, "count": 2204 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": 6.765808582305908, "min": -26.293500900268555, "max": 30.984846115112305, "count": 2204 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 2204 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 2204 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": 0.09918952799592343, "min": -0.676254543391141, "max": 0.44998596425642046, "count": 2204 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": 18.945199847221375, "min": -67.1159999370575, "max": 58.53219944238663, "count": 2204 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": 0.09918952799592343, "min": -0.676254543391141, "max": 0.44998596425642046, "count": 2204 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": 18.945199847221375, "min": -67.1159999370575, "max": 58.53219944238663, "count": 2204 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 2204 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 2204 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.017875805279860893, "min": 0.010085510737068641, "max": 0.025645279930904506, "count": 1068 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.017875805279860893, "min": 0.010085510737068641, "max": 0.025645279930904506, "count": 1068 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.10840815007686615, "min": 0.0006131869527356078, "max": 0.1383328417936961, "count": 1068 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.10840815007686615, "min": 0.0006131869527356078, "max": 0.1383328417936961, "count": 1068 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.10949653362234434, "min": 0.000615147494439346, "max": 0.14097957462072372, "count": 1068 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.10949653362234434, "min": 0.000615147494439346, "max": 0.14097957462072372, "count": 1068 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 1068 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 1068 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.19999999999999996, "max": 0.20000000000000007, "count": 1068 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.19999999999999996, "max": 0.20000000000000007, "count": 1068 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005, "max": 0.005000000000000001, "count": 1068 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005, "max": 0.005000000000000001, "count": 1068 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1696966922", "python_version": "3.9.18 (main, Sep 11 2023, 13:41:44) \n[GCC 11.2.0]", "command_line_arguments": "/home/andre/miniconda3/envs/rl/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos.x86_64 --run-id=SoccerTwos3 --no-graphics", "mlagents_version": "0.30.0", "mlagents_envs_version": "0.30.0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.11.0+cu102", "numpy_version": "1.21.2", "end_time_seconds": "1697031305" }, "total": 64383.68118217809, "count": 1, "self": 1.2398065680172294, "children": { "run_training.setup": { "total": 0.016844510100781918, "count": 1, "self": 0.016844510100781918 }, "TrainerController.start_learning": { "total": 64382.42453109997, "count": 1, "self": 38.92193431360647, "children": { "TrainerController._reset_env": { "total": 3.307890849071555, "count": 111, "self": 3.307890849071555 }, "TrainerController.advance": { "total": 64339.5550213462, "count": 1520423, "self": 40.8708538900828, "children": { "env_step": { "total": 36604.495503323735, "count": 1520423, "self": 32750.119099378004, "children": { "SubprocessEnvManager._take_step": { "total": 3830.9975482781883, "count": 1520423, "self": 196.1993643681053, "children": { "TorchPolicy.evaluate": { "total": 3634.798183910083, "count": 2768644, "self": 3634.798183910083 } } }, "workers": { "total": 23.378855667542666, "count": 1520423, "self": 0.0, "children": { "worker_root": { "total": 64228.85714706173, "count": 1520423, "is_parallel": true, "self": 35179.90832429123, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0028462449554353952, "count": 2, "is_parallel": true, "self": 0.0007436119485646486, "children": { "_process_rank_one_or_two_observation": { "total": 0.0021026330068707466, "count": 8, "is_parallel": true, "self": 0.0021026330068707466 } } }, "UnityEnvironment.step": { "total": 0.03850793093442917, "count": 1, "is_parallel": true, "self": 0.0005843029357492924, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005270749097689986, "count": 1, "is_parallel": true, "self": 0.0005270749097689986 }, "communicator.exchange": { "total": 0.0357780740596354, "count": 1, "is_parallel": true, "self": 0.0357780740596354 }, "steps_from_proto": { "total": 0.001618479029275477, "count": 2, "is_parallel": true, "self": 0.00032234378159046173, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012961352476850152, "count": 8, "is_parallel": true, "self": 0.0012961352476850152 } } } } } } }, "UnityEnvironment.step": { "total": 29048.779247753904, "count": 1520422, "is_parallel": true, "self": 830.8873350732028, "children": { "UnityEnvironment._generate_step_input": { "total": 528.2550250960048, "count": 1520422, "is_parallel": true, "self": 528.2550250960048 }, "communicator.exchange": { "total": 25503.690678836778, "count": 1520422, "is_parallel": true, "self": 25503.690678836778 }, "steps_from_proto": { "total": 2185.9462087479187, "count": 3040844, "is_parallel": true, "self": 424.74704040167853, "children": { "_process_rank_one_or_two_observation": { "total": 1761.1991683462402, "count": 12163376, "is_parallel": true, "self": 1761.1991683462402 } } } } }, "steps_from_proto": { "total": 0.16957501659635454, "count": 220, "is_parallel": true, "self": 0.03266283276025206, "children": { "_process_rank_one_or_two_observation": { "total": 0.13691218383610249, "count": 880, "is_parallel": true, "self": 0.13691218383610249 } } } } } } } } }, "trainer_advance": { "total": 27694.18866413238, "count": 1520423, "self": 236.6728832940571, "children": { "process_trajectory": { "total": 4355.0125788023, "count": 1520423, "self": 4347.310795673635, "children": { "RLTrainer._checkpoint": { "total": 7.701783128664829, "count": 44, "self": 7.701783128664829 } } }, "_update_policy": { "total": 23102.503202036023, "count": 1069, "self": 2478.9786384809995, "children": { "TorchPOCAOptimizer.update": { "total": 20623.524563555024, "count": 32083, "self": 20623.524563555024 } } } } } } }, "trainer_threads": { "total": 5.912035703659058e-06, "count": 1, "self": 5.912035703659058e-06 }, "TrainerController._save_models": { "total": 0.639678679057397, "count": 1, "self": 0.010856325970962644, "children": { "RLTrainer._checkpoint": { "total": 0.6288223530864343, "count": 1, "self": 0.6288223530864343 } } } } } } }