{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 1.437191128730774, "min": 1.349334478378296, "max": 3.2957637310028076, "count": 2852 }, "SoccerTwos.Policy.Entropy.sum": { "value": 27042.1875, "min": 16329.0478515625, "max": 146594.96875, "count": 2852 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 77.875, "min": 38.0234375, "max": 999.0, "count": 2852 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19936.0, "min": 7992.0, "max": 27888.0, "count": 2852 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1602.548234498047, "min": 1189.5400639831341, "max": 1646.8755676374396, "count": 2739 }, "SoccerTwos.Self-play.ELO.sum": { "value": 205126.17401575, "min": 2379.0801279662683, "max": 413202.69730698795, "count": 2739 }, "SoccerTwos.Step.mean": { "value": 28519980.0, "min": 9960.0, "max": 28519980.0, "count": 2852 }, "SoccerTwos.Step.sum": { "value": 28519980.0, "min": 9960.0, "max": 28519980.0, "count": 2852 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": -0.010000440292060375, "min": -0.16097573935985565, "max": 0.19826394319534302, "count": 2852 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": -1.270055890083313, "min": -28.170753479003906, "max": 27.114356994628906, "count": 2852 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": -0.012177404947578907, "min": -0.1611374169588089, "max": 0.19701406359672546, "count": 2852 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": -1.5465304851531982, "min": -28.199047088623047, "max": 27.293899536132812, "count": 2852 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 2852 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 2852 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": -0.10423307015201239, "min": -0.5715428593435458, "max": 0.4765513488972509, "count": 2852 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": -13.237599909305573, "min": -77.58720016479492, "max": 71.36440026760101, "count": 2852 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": -0.10423307015201239, "min": -0.5715428593435458, "max": 0.4765513488972509, "count": 2852 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": -13.237599909305573, "min": -77.58720016479492, "max": 71.36440026760101, "count": 2852 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 2852 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 2852 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.01605327334885563, "min": 0.010654802256613038, "max": 0.026289385526130596, "count": 1377 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.01605327334885563, "min": 0.010654802256613038, "max": 0.026289385526130596, "count": 1377 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.10625466605027517, "min": 6.154354205515725e-08, "max": 0.1319865792989731, "count": 1377 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.10625466605027517, "min": 6.154354205515725e-08, "max": 0.1319865792989731, "count": 1377 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.10752570629119873, "min": 6.034927236460893e-08, "max": 0.13373082454005877, "count": 1377 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.10752570629119873, "min": 6.034927236460893e-08, "max": 0.13373082454005877, "count": 1377 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 1377 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 1377 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.20000000000000004, "max": 0.20000000000000007, "count": 1377 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.20000000000000004, "max": 0.20000000000000007, "count": 1377 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 1377 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 1377 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1733842605", "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]", "command_line_arguments": "/home/robyn/.conda/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": "2.5.1+cu124", "numpy_version": "1.23.5", "end_time_seconds": "1733903217" }, "total": 60612.273349394, "count": 1, "self": 0.09502691100351512, "children": { "run_training.setup": { "total": 0.012748552995617501, "count": 1, "self": 0.012748552995617501 }, "TrainerController.start_learning": { "total": 60612.165573930004, "count": 1, "self": 42.1890174458822, "children": { "TrainerController._reset_env": { "total": 4.909925165033201, "count": 143, "self": 4.909925165033201 }, "TrainerController.advance": { "total": 60564.89003397507, "count": 1966451, "self": 36.03445463099342, "children": { "env_step": { "total": 33496.24376507336, "count": 1966451, "self": 27680.185781673194, "children": { "SubprocessEnvManager._take_step": { "total": 5792.173427216301, "count": 1966451, "self": 225.23392488567333, "children": { "TorchPolicy.evaluate": { "total": 5566.939502330628, "count": 3590447, "self": 5566.939502330628 } } }, "workers": { "total": 23.88455618386797, "count": 1966450, "self": 0.0, "children": { "worker_root": { "total": 60543.17199520669, "count": 1966450, "is_parallel": true, "self": 37235.51486229879, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.004633952004951425, "count": 2, "is_parallel": true, "self": 0.0006502600008388981, "children": { "_process_rank_one_or_two_observation": { "total": 0.003983692004112527, "count": 8, "is_parallel": true, "self": 0.003983692004112527 } } }, "UnityEnvironment.step": { "total": 0.02710346299863886, "count": 1, "is_parallel": true, "self": 0.00145738098945003, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004715830000350252, "count": 1, "is_parallel": true, "self": 0.0004715830000350252 }, "communicator.exchange": { "total": 0.021104119005030952, "count": 1, "is_parallel": true, "self": 0.021104119005030952 }, "steps_from_proto": { "total": 0.004070380004122853, "count": 2, "is_parallel": true, "self": 0.00045489899639505893, "children": { "_process_rank_one_or_two_observation": { "total": 0.0036154810077277943, "count": 8, "is_parallel": true, "self": 0.0036154810077277943 } } } } } } }, "UnityEnvironment.step": { "total": 23307.378715099912, "count": 1966449, "is_parallel": true, "self": 1405.6316182493174, "children": { "UnityEnvironment._generate_step_input": { "total": 827.3407736267836, "count": 1966449, "is_parallel": true, "self": 827.3407736267836 }, "communicator.exchange": { "total": 17187.554907894635, "count": 1966449, "is_parallel": true, "self": 17187.554907894635 }, "steps_from_proto": { "total": 3886.8514153291762, "count": 3932898, "is_parallel": true, "self": 594.6366406866873, "children": { "_process_rank_one_or_two_observation": { "total": 3292.214774642489, "count": 15731592, "is_parallel": true, "self": 3292.214774642489 } } } } }, "steps_from_proto": { "total": 0.2784178079891717, "count": 284, "is_parallel": true, "self": 0.04262958392791916, "children": { "_process_rank_one_or_two_observation": { "total": 0.23578822406125255, "count": 1136, "is_parallel": true, "self": 0.23578822406125255 } } } } } } } } }, "trainer_advance": { "total": 27032.611814270713, "count": 1966450, "self": 299.95488934505556, "children": { "process_trajectory": { "total": 5330.9567592090025, "count": 1966450, "self": 5323.221373201086, "children": { "RLTrainer._checkpoint": { "total": 7.7353860079165315, "count": 57, "self": 7.7353860079165315 } } }, "_update_policy": { "total": 21401.700165716655, "count": 1377, "self": 2962.4580578382593, "children": { "TorchPOCAOptimizer.update": { "total": 18439.242107878395, "count": 41319, "self": 18439.242107878395 } } } } } } }, "trainer_threads": { "total": 1.2420059647411108e-06, "count": 1, "self": 1.2420059647411108e-06 }, "TrainerController._save_models": { "total": 0.17659610201371834, "count": 1, "self": 0.001182057021651417, "children": { "RLTrainer._checkpoint": { "total": 0.17541404499206692, "count": 1, "self": 0.17541404499206692 } } } } } } }