{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 1.36985445022583, "min": 1.3302485942840576, "max": 3.295691967010498, "count": 5000 }, "SoccerTwos.Policy.Entropy.sum": { "value": 27177.912109375, "min": 6765.84716796875, "max": 113482.421875, "count": 5000 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 70.25714285714285, "min": 42.94117647058823, "max": 999.0, "count": 5000 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19672.0, "min": 12224.0, "max": 28348.0, "count": 5000 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1491.0628039525184, "min": 1182.548210703926, "max": 1516.7776235279837, "count": 4989 }, "SoccerTwos.Self-play.ELO.sum": { "value": 208748.79255335257, "min": 2365.096421407852, "max": 329488.51982636034, "count": 4989 }, "SoccerTwos.Step.mean": { "value": 49999978.0, "min": 9192.0, "max": 49999978.0, "count": 5000 }, "SoccerTwos.Step.sum": { "value": 49999978.0, "min": 9192.0, "max": 49999978.0, "count": 5000 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": -0.008446477353572845, "min": -0.1378321647644043, "max": 0.2507602572441101, "count": 5000 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": -1.182506799697876, "min": -22.672176361083984, "max": 32.625816345214844, "count": 5000 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": -0.008503497578203678, "min": -0.13763639330863953, "max": 0.250055193901062, "count": 5000 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": -1.190489649772644, "min": -22.192230224609375, "max": 32.972434997558594, "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": -0.1979771431003298, "min": -0.6875, "max": 0.569142861025674, "count": 5000 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": -27.716800034046173, "min": -63.01819998025894, "max": 60.70080053806305, "count": 5000 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": -0.1979771431003298, "min": -0.6875, "max": 0.569142861025674, "count": 5000 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": -27.716800034046173, "min": -63.01819998025894, "max": 60.70080053806305, "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": 0.01857423917778457, "min": 0.009236962045542895, "max": 0.02754863896795238, "count": 2423 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.01857423917778457, "min": 0.009236962045542895, "max": 0.02754863896795238, "count": 2423 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.08878144746025403, "min": 0.00019966156493561965, "max": 0.11898887902498245, "count": 2423 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.08878144746025403, "min": 0.00019966156493561965, "max": 0.11898887902498245, "count": 2423 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.0897236814101537, "min": 0.0001982558096642606, "max": 0.12116950526833534, "count": 2423 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.0897236814101537, "min": 0.0001982558096642606, "max": 0.12116950526833534, "count": 2423 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 2423 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 2423 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 2423 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 2423 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 2423 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 2423 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1741515726", "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]", "command_line_arguments": "/home/carbajal/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": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.6.0+cu124", "numpy_version": "1.23.5", "end_time_seconds": "1741603594" }, "total": 87867.567145246, "count": 1, "self": 0.2719908799917903, "children": { "run_training.setup": { "total": 0.014040420006494969, "count": 1, "self": 0.014040420006494969 }, "TrainerController.start_learning": { "total": 87867.281113946, "count": 1, "self": 70.07043651660206, "children": { "TrainerController._reset_env": { "total": 6.217110827594297, "count": 250, "self": 6.217110827594297 }, "TrainerController.advance": { "total": 87790.84123178979, "count": 3428405, "self": 63.52165870752651, "children": { "env_step": { "total": 65463.16093376643, "count": 3428405, "self": 47247.172181124944, "children": { "SubprocessEnvManager._take_step": { "total": 18172.926531222416, "count": 3428405, "self": 375.9177835499577, "children": { "TorchPolicy.evaluate": { "total": 17797.00874767246, "count": 6284006, "self": 17797.00874767246 } } }, "workers": { "total": 43.06222141906619, "count": 3428405, "self": 0.0, "children": { "worker_root": { "total": 87778.782617174, "count": 3428405, "is_parallel": true, "self": 48104.57271212834, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0019256249943282455, "count": 2, "is_parallel": true, "self": 0.00045586604392156005, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014697589504066855, "count": 8, "is_parallel": true, "self": 0.0014697589504066855 } } }, "UnityEnvironment.step": { "total": 0.03152862499700859, "count": 1, "is_parallel": true, "self": 0.000490236998302862, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0003318740054965019, "count": 1, "is_parallel": true, "self": 0.0003318740054965019 }, "communicator.exchange": { "total": 0.02909855797770433, "count": 1, "is_parallel": true, "self": 0.02909855797770433 }, "steps_from_proto": { "total": 0.0016079560155048966, "count": 2, "is_parallel": true, "self": 0.00033470705966465175, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012732489558402449, "count": 8, "is_parallel": true, "self": 0.0012732489558402449 } } } } } } }, "UnityEnvironment.step": { "total": 39673.80391099339, "count": 3428404, "is_parallel": true, "self": 1910.256119078549, "children": { "UnityEnvironment._generate_step_input": { "total": 1132.760242002434, "count": 3428404, "is_parallel": true, "self": 1132.760242002434 }, "communicator.exchange": { "total": 31082.231930095644, "count": 3428404, "is_parallel": true, "self": 31082.231930095644 }, "steps_from_proto": { "total": 5548.5556198167615, "count": 6856808, "is_parallel": true, "self": 1055.9510837357084, "children": { "_process_rank_one_or_two_observation": { "total": 4492.604536081053, "count": 27427232, "is_parallel": true, "self": 4492.604536081053 } } } } }, "steps_from_proto": { "total": 0.40599405227112584, "count": 498, "is_parallel": true, "self": 0.07375247427262366, "children": { "_process_rank_one_or_two_observation": { "total": 0.3322415779985022, "count": 1992, "is_parallel": true, "self": 0.3322415779985022 } } } } } } } } }, "trainer_advance": { "total": 22264.158639315836, "count": 3428405, "self": 447.3205651437456, "children": { "process_trajectory": { "total": 9309.08619754741, "count": 3428405, "self": 9293.06106790845, "children": { "RLTrainer._checkpoint": { "total": 16.025129638961516, "count": 100, "self": 16.025129638961516 } } }, "_update_policy": { "total": 12507.75187662468, "count": 2423, "self": 5562.759891700873, "children": { "TorchPOCAOptimizer.update": { "total": 6944.991984923807, "count": 72690, "self": 6944.991984923807 } } } } } } }, "trainer_threads": { "total": 6.300106178969145e-07, "count": 1, "self": 6.300106178969145e-07 }, "TrainerController._save_models": { "total": 0.15233418199932203, "count": 1, "self": 0.0016578139911871403, "children": { "RLTrainer._checkpoint": { "total": 0.1506763680081349, "count": 1, "self": 0.1506763680081349 } } } } } } }