{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 3.1753852367401123, "min": 3.124070167541504, "max": 3.295760154724121, "count": 200 }, "SoccerTwos.Policy.Entropy.sum": { "value": 62186.7421875, "min": 6395.45703125, "max": 125993.9765625, "count": 200 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 999.0, "min": 376.0, "max": 999.0, "count": 200 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19980.0, "min": 7096.0, "max": 27784.0, "count": 200 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1210.76825350818, "min": 1198.995732238514, "max": 1217.7148831130346, "count": 160 }, "SoccerTwos.Self-play.ELO.sum": { "value": 9686.14602806544, "min": 2403.982894094307, "max": 16937.35401906041, "count": 160 }, "SoccerTwos.Step.mean": { "value": 1999810.0, "min": 9908.0, "max": 1999810.0, "count": 200 }, "SoccerTwos.Step.sum": { "value": 1999810.0, "min": 9908.0, "max": 1999810.0, "count": 200 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": -0.005106488708406687, "min": -0.04636257141828537, "max": 0.009470287710428238, "count": 200 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": -0.05106488615274429, "min": -0.7037259936332703, "max": 0.11364345252513885, "count": 200 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": -0.004664062522351742, "min": -0.04432212561368942, "max": 0.00714792450889945, "count": 200 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": -0.04664062336087227, "min": -0.7069289684295654, "max": 0.08577509224414825, "count": 200 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 200 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 200 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": 0.0, "min": -0.6153846153846154, "max": 0.2777714303561619, "count": 200 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": 0.0, "min": -8.0, "max": 3.888800024986267, "count": 200 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": 0.0, "min": -0.6153846153846154, "max": 0.2777714303561619, "count": 200 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": 0.0, "min": -8.0, "max": 3.888800024986267, "count": 200 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 200 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 200 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.016594474228137795, "min": 0.012508376075614554, "max": 0.023593630608714496, "count": 93 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.016594474228137795, "min": 0.012508376075614554, "max": 0.023593630608714496, "count": 93 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.003200472751632333, "min": 2.550808407401443e-06, "max": 0.004651585803367197, "count": 93 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.003200472751632333, "min": 2.550808407401443e-06, "max": 0.004651585803367197, "count": 93 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.003201262870182594, "min": 2.5332763167777253e-06, "max": 0.004683688228639463, "count": 93 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.003201262870182594, "min": 2.5332763167777253e-06, "max": 0.004683688228639463, "count": 93 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 93 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 93 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.20000000000000004, "max": 0.20000000000000007, "count": 93 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.20000000000000004, "max": 0.20000000000000007, "count": 93 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 93 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 93 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1733390944", "python_version": "3.10.1 | packaged by conda-forge | (main, Dec 22 2021, 01:39:07) [Clang 11.1.0 ]", "command_line_arguments": "/opt/anaconda3/envs/hf-rl-course/bin/mlagents-learn ./ml-agents/config/poca/SoccerTwos.yaml --env=./ml-agents/training-envs-executables/SoccerTwos/SoccerTwos.app --run-id=SoccerTwos-2 --no-graphics", "mlagents_version": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.5.1", "numpy_version": "1.23.5", "end_time_seconds": "1733397444" }, "total": 6500.227486415999, "count": 1, "self": 0.17503141600172967, "children": { "run_training.setup": { "total": 0.014256874972488731, "count": 1, "self": 0.014256874972488731 }, "TrainerController.start_learning": { "total": 6500.038198125025, "count": 1, "self": 1.1946516065509059, "children": { "TrainerController._reset_env": { "total": 2.4832318329135887, "count": 10, "self": 2.4832318329135887 }, "TrainerController.advance": { "total": 6496.281524476595, "count": 130538, "self": 1.1281268410966732, "children": { "env_step": { "total": 5425.526924707112, "count": 130538, "self": 5244.52196714154, "children": { "SubprocessEnvManager._take_step": { "total": 180.20163135998882, "count": 130538, "self": 5.278902637772262, "children": { "TorchPolicy.evaluate": { "total": 174.92272872221656, "count": 259126, "self": 174.92272872221656 } } }, "workers": { "total": 0.8033262055832893, "count": 130538, "self": 0.0, "children": { "worker_root": { "total": 6495.968970293063, "count": 130538, "is_parallel": true, "self": 1445.0736605353886, "children": { "steps_from_proto": { "total": 0.013292915828060359, "count": 20, "is_parallel": true, "self": 0.0017947120359167457, "children": { "_process_rank_one_or_two_observation": { "total": 0.011498203792143613, "count": 80, "is_parallel": true, "self": 0.011498203792143613 } } }, "UnityEnvironment.step": { "total": 5050.882016841846, "count": 130538, "is_parallel": true, "self": 12.226883286319207, "children": { "UnityEnvironment._generate_step_input": { "total": 86.68823079677531, "count": 130538, "is_parallel": true, "self": 86.68823079677531 }, "communicator.exchange": { "total": 4785.622075497755, "count": 130538, "is_parallel": true, "self": 4785.622075497755 }, "steps_from_proto": { "total": 166.34482726099668, "count": 261076, "is_parallel": true, "self": 19.653808775998186, "children": { "_process_rank_one_or_two_observation": { "total": 146.6910184849985, "count": 1044304, "is_parallel": true, "self": 146.6910184849985 } } } } } } } } } } }, "trainer_advance": { "total": 1069.6264729283866, "count": 130538, "self": 11.428957007476129, "children": { "process_trajectory": { "total": 170.9214817569591, "count": 130538, "self": 170.5529237979208, "children": { "RLTrainer._checkpoint": { "total": 0.3685579590382986, "count": 4, "self": 0.3685579590382986 } } }, "_update_policy": { "total": 887.2760341639514, "count": 93, "self": 117.34854670194909, "children": { "TorchPOCAOptimizer.update": { "total": 769.9274874620023, "count": 2799, "self": 769.9274874620023 } } } } } } }, "trainer_threads": { "total": 3.33995558321476e-07, "count": 1, "self": 3.33995558321476e-07 }, "TrainerController._save_models": { "total": 0.07878987496951595, "count": 1, "self": 0.0005459159729070961, "children": { "RLTrainer._checkpoint": { "total": 0.07824395899660885, "count": 1, "self": 0.07824395899660885 } } } } } } }