{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 3.170182943344116, "min": 3.170182943344116, "max": 3.2958176136016846, "count": 100 }, "SoccerTwos.Policy.Entropy.sum": { "value": 64012.3359375, "min": 17641.58203125, "max": 135147.03125, "count": 100 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 817.1666666666666, "min": 423.46153846153845, "max": 999.0, "count": 100 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19612.0, "min": 17172.0, "max": 23660.0, "count": 100 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1194.8855109726805, "min": 1193.806378469, "max": 1206.0646079271496, "count": 87 }, "SoccerTwos.Self-play.ELO.sum": { "value": 7169.313065836083, "min": 2388.2289121141957, "max": 14467.359649704407, "count": 87 }, "SoccerTwos.Step.mean": { "value": 999182.0, "min": 9440.0, "max": 999182.0, "count": 100 }, "SoccerTwos.Step.sum": { "value": 999182.0, "min": 9440.0, "max": 999182.0, "count": 100 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": -0.006761973258107901, "min": -0.04099714010953903, "max": 0.009562848135828972, "count": 100 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": -0.08114367723464966, "min": -0.6559542417526245, "max": 0.14447684586048126, "count": 100 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": -0.006709132809191942, "min": -0.040997378528118134, "max": 0.010130513459444046, "count": 100 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": -0.08050959557294846, "min": -0.6559580564498901, "max": 0.14307253062725067, "count": 100 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 100 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 100 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": 0.1818333293000857, "min": -0.5, "max": 0.2226461538901696, "count": 100 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": 2.1819999516010284, "min": -7.0, "max": 2.8944000005722046, "count": 100 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": 0.1818333293000857, "min": -0.5, "max": 0.2226461538901696, "count": 100 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": 2.1819999516010284, "min": -7.0, "max": 2.8944000005722046, "count": 100 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 100 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 100 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.018752827732047686, "min": 0.01134999077427589, "max": 0.021953440748620778, "count": 46 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.018752827732047686, "min": 0.01134999077427589, "max": 0.021953440748620778, "count": 46 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.0024301567793979, "min": 5.95106634136755e-05, "max": 0.005486274394206703, "count": 46 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.0024301567793979, "min": 5.95106634136755e-05, "max": 0.005486274394206703, "count": 46 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.0024303701531607656, "min": 6.624901361647062e-05, "max": 0.005486366401116053, "count": 46 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.0024303701531607656, "min": 6.624901361647062e-05, "max": 0.005486366401116053, "count": 46 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0005000000000000001, "min": 0.0005000000000000001, "max": 0.0005000000000000001, "count": 46 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0005000000000000001, "min": 0.0005000000000000001, "max": 0.0005000000000000001, "count": 46 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 46 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 46 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 46 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 46 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1704721146", "python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [GCC 11.4.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn ./ml-agents/config/poca/SoccerTwos.yaml --env=./ml-agents/training-envs-executables/SoccerTwos/SoccerTwos.x86_64 --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": "2.1.2+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1704723438" }, "total": 2291.444360724, "count": 1, "self": 0.4792369910001071, "children": { "run_training.setup": { "total": 0.04848877499989612, "count": 1, "self": 0.04848877499989612 }, "TrainerController.start_learning": { "total": 2290.916634958, "count": 1, "self": 1.6784743159787467, "children": { "TrainerController._reset_env": { "total": 4.280896093000592, "count": 10, "self": 4.280896093000592 }, "TrainerController.advance": { "total": 2284.64563900802, "count": 67111, "self": 1.9494308781358995, "children": { "env_step": { "total": 1888.2633872079714, "count": 67111, "self": 1457.6353917481583, "children": { "SubprocessEnvManager._take_step": { "total": 429.5588821019337, "count": 67111, "self": 11.4154689957968, "children": { "TorchPolicy.evaluate": { "total": 418.1434131061369, "count": 133204, "self": 418.1434131061369 } } }, "workers": { "total": 1.0691133578793597, "count": 67111, "self": 0.0, "children": { "worker_root": { "total": 2285.749601622094, "count": 67111, "is_parallel": true, "self": 1065.9562845331511, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005999207000968454, "count": 2, "is_parallel": true, "self": 0.0037823230031790445, "children": { "_process_rank_one_or_two_observation": { "total": 0.0022168839977894095, "count": 8, "is_parallel": true, "self": 0.0022168839977894095 } } }, "UnityEnvironment.step": { "total": 0.03851795100035815, "count": 1, "is_parallel": true, "self": 0.0011877570004799054, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0007927799997560214, "count": 1, "is_parallel": true, "self": 0.0007927799997560214 }, "communicator.exchange": { "total": 0.033154147999994166, "count": 1, "is_parallel": true, "self": 0.033154147999994166 }, "steps_from_proto": { "total": 0.00338326600012806, "count": 2, "is_parallel": true, "self": 0.0005995870005790493, "children": { "_process_rank_one_or_two_observation": { "total": 0.0027836789995490108, "count": 8, "is_parallel": true, "self": 0.0027836789995490108 } } } } } } }, "UnityEnvironment.step": { "total": 1219.770863046946, "count": 67110, "is_parallel": true, "self": 77.87443116795475, "children": { "UnityEnvironment._generate_step_input": { "total": 48.501318270026786, "count": 67110, "is_parallel": true, "self": 48.501318270026786 }, "communicator.exchange": { "total": 855.0789163280015, "count": 67110, "is_parallel": true, "self": 855.0789163280015 }, "steps_from_proto": { "total": 238.31619728096302, "count": 134220, "is_parallel": true, "self": 38.271710797398555, "children": { "_process_rank_one_or_two_observation": { "total": 200.04448648356447, "count": 536880, "is_parallel": true, "self": 200.04448648356447 } } } } }, "steps_from_proto": { "total": 0.022454041996752494, "count": 18, "is_parallel": true, "self": 0.004325938996771583, "children": { "_process_rank_one_or_two_observation": { "total": 0.01812810299998091, "count": 72, "is_parallel": true, "self": 0.01812810299998091 } } } } } } } } }, "trainer_advance": { "total": 394.43282092191293, "count": 67111, "self": 14.495314420915747, "children": { "process_trajectory": { "total": 111.31495865599209, "count": 67111, "self": 110.69357632599167, "children": { "RLTrainer._checkpoint": { "total": 0.6213823300004151, "count": 2, "self": 0.6213823300004151 } } }, "_update_policy": { "total": 268.6225478450051, "count": 46, "self": 158.10835126400798, "children": { "TorchPOCAOptimizer.update": { "total": 110.51419658099712, "count": 1380, "self": 110.51419658099712 } } } } } } }, "trainer_threads": { "total": 9.96999915514607e-07, "count": 1, "self": 9.96999915514607e-07 }, "TrainerController._save_models": { "total": 0.3116245440005514, "count": 1, "self": 0.0067838909999409225, "children": { "RLTrainer._checkpoint": { "total": 0.3048406530006105, "count": 1, "self": 0.3048406530006105 } } } } } } }