{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 3.144447088241577, "min": 3.144447088241577, "max": 3.2956929206848145, "count": 355 }, "SoccerTwos.Policy.Entropy.sum": { "value": 39947.0546875, "min": 18880.01953125, "max": 121548.8125, "count": 355 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 633.875, "min": 439.1, "max": 999.0, "count": 355 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 20284.0, "min": 13968.0, "max": 26520.0, "count": 355 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1191.594047871502, "min": 1185.9035649843918, "max": 1199.5028730369677, "count": 269 }, "SoccerTwos.Self-play.ELO.sum": { "value": 14299.128574458024, "min": 2372.8095692167844, "max": 14362.900581238877, "count": 269 }, "SoccerTwos.Step.mean": { "value": 3549926.0, "min": 9276.0, "max": 3549926.0, "count": 355 }, "SoccerTwos.Step.sum": { "value": 3549926.0, "min": 9276.0, "max": 3549926.0, "count": 355 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": -0.013288138434290886, "min": -0.02144741080701351, "max": 0.05369578301906586, "count": 355 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": -0.21261021494865417, "min": -0.2960754334926605, "max": 0.8361341953277588, "count": 355 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": -0.013158649206161499, "min": -0.02067537046968937, "max": 0.053638335317373276, "count": 355 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": -0.21053838729858398, "min": -0.2881663143634796, "max": 0.8044207096099854, "count": 355 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 355 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 355 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": -0.2597000040113926, "min": -0.6363636363636364, "max": 0.28802000284194945, "count": 355 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": -4.1552000641822815, "min": -8.0, "max": 5.760400056838989, "count": 355 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": -0.2597000040113926, "min": -0.6363636363636364, "max": 0.28802000284194945, "count": 355 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": -4.1552000641822815, "min": -8.0, "max": 5.760400056838989, "count": 355 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 355 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 355 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.0211825970094651, "min": 0.011011536803622827, "max": 0.02337798193329945, "count": 165 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.0211825970094651, "min": 0.011011536803622827, "max": 0.02337798193329945, "count": 165 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.0034293286579971513, "min": 2.7304897230351345e-06, "max": 0.008026694071789582, "count": 165 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.0034293286579971513, "min": 2.7304897230351345e-06, "max": 0.008026694071789582, "count": 165 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.0034754222491756082, "min": 2.701601912728317e-06, "max": 0.008031302457675337, "count": 165 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.0034754222491756082, "min": 2.701601912728317e-06, "max": 0.008031302457675337, "count": 165 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 165 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 165 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.2, "max": 0.20000000000000007, "count": 165 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.2, "max": 0.20000000000000007, "count": 165 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005, "max": 0.005000000000000001, "count": 165 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005, "max": 0.005000000000000001, "count": 165 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1675313227", "python_version": "3.8.15 | packaged by conda-forge | (default, Nov 22 2022, 08:49:35) \n[GCC 10.4.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env=/content/ml-agents/ml-agents/mlagents/training-envs-executables/SoccerTows/SoccerTows.x86_64 --run-id=SoccerTwos --no-graphics --force", "mlagents_version": "0.31.0.dev0", "mlagents_envs_version": "0.31.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.8.1+cu102", "numpy_version": "1.21.2", "end_time_seconds": "1675321471" }, "total": 8243.666359687999, "count": 1, "self": 0.09991793500012136, "children": { "run_training.setup": { "total": 0.039593043999957445, "count": 1, "self": 0.039593043999957445 }, "TrainerController.start_learning": { "total": 8243.526848709, "count": 1, "self": 6.254733504023534, "children": { "TrainerController._reset_env": { "total": 6.327788356999008, "count": 18, "self": 6.327788356999008 }, "TrainerController.advance": { "total": 8230.402383417979, "count": 231345, "self": 6.6894588662635215, "children": { "env_step": { "total": 6651.9437016586535, "count": 231345, "self": 5202.866837339538, "children": { "SubprocessEnvManager._take_step": { "total": 1445.234483483801, "count": 231345, "self": 44.2147159702522, "children": { "TorchPolicy.evaluate": { "total": 1401.0197675135487, "count": 459344, "self": 1401.0197675135487 } } }, "workers": { "total": 3.842380835314543, "count": 231345, "self": 0.0, "children": { "worker_root": { "total": 8225.572103267688, "count": 231345, "is_parallel": true, "self": 3830.2844692186654, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0026728390002972446, "count": 2, "is_parallel": true, "self": 0.0007410939997498645, "children": { "_process_rank_one_or_two_observation": { "total": 0.0019317450005473802, "count": 8, "is_parallel": true, "self": 0.0019317450005473802 } } }, "UnityEnvironment.step": { "total": 0.07920495600001232, "count": 1, "is_parallel": true, "self": 0.001055844999882538, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0008201519999602169, "count": 1, "is_parallel": true, "self": 0.0008201519999602169 }, "communicator.exchange": { "total": 0.06653593500004717, "count": 1, "is_parallel": true, "self": 0.06653593500004717 }, "steps_from_proto": { "total": 0.010793024000122386, "count": 2, "is_parallel": true, "self": 0.0006254220011214784, "children": { "_process_rank_one_or_two_observation": { "total": 0.010167601999000908, "count": 8, "is_parallel": true, "self": 0.010167601999000908 } } } } } } }, "UnityEnvironment.step": { "total": 4395.240563849025, "count": 231344, "is_parallel": true, "self": 224.1757867290089, "children": { "UnityEnvironment._generate_step_input": { "total": 163.15691012905927, "count": 231344, "is_parallel": true, "self": 163.15691012905927 }, "communicator.exchange": { "total": 3227.778860779885, "count": 231344, "is_parallel": true, "self": 3227.778860779885 }, "steps_from_proto": { "total": 780.1290062110725, "count": 462688, "is_parallel": true, "self": 144.38221094411483, "children": { "_process_rank_one_or_two_observation": { "total": 635.7467952669576, "count": 1850752, "is_parallel": true, "self": 635.7467952669576 } } } } }, "steps_from_proto": { "total": 0.04707019999750628, "count": 34, "is_parallel": true, "self": 0.009743015996264148, "children": { "_process_rank_one_or_two_observation": { "total": 0.03732718400124213, "count": 136, "is_parallel": true, "self": 0.03732718400124213 } } } } } } } } }, "trainer_advance": { "total": 1571.7692228930614, "count": 231345, "self": 43.19121700917185, "children": { "process_trajectory": { "total": 404.1151300348952, "count": 231345, "self": 402.2769509508935, "children": { "RLTrainer._checkpoint": { "total": 1.8381790840016947, "count": 7, "self": 1.8381790840016947 } } }, "_update_policy": { "total": 1124.4628758489944, "count": 166, "self": 719.5995572830188, "children": { "TorchPOCAOptimizer.update": { "total": 404.86331856597553, "count": 4956, "self": 404.86331856597553 } } } } } } }, "trainer_threads": { "total": 1.5799996617715806e-06, "count": 1, "self": 1.5799996617715806e-06 }, "TrainerController._save_models": { "total": 0.5419418499986932, "count": 1, "self": 0.002837060997990193, "children": { "RLTrainer._checkpoint": { "total": 0.539104789000703, "count": 1, "self": 0.539104789000703 } } } } } } }