{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 1.3963068723678589, "min": 1.2771546840667725, "max": 3.2957348823547363, "count": 5000 }, "SoccerTwos.Policy.Entropy.sum": { "value": 26719.728515625, "min": 21484.294921875, "max": 114449.0390625, "count": 5000 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 80.16129032258064, "min": 38.19047619047619, "max": 999.0, "count": 5000 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19880.0, "min": 7992.0, "max": 28572.0, "count": 5000 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1817.8026334566646, "min": 1189.120637053404, "max": 1840.0856784175528, "count": 4981 }, "SoccerTwos.Self-play.ELO.sum": { "value": 225407.5265486264, "min": 2380.356215929806, "max": 412380.5304736879, "count": 4981 }, "SoccerTwos.Step.mean": { "value": 49999909.0, "min": 9602.0, "max": 49999909.0, "count": 5000 }, "SoccerTwos.Step.sum": { "value": 49999909.0, "min": 9602.0, "max": 49999909.0, "count": 5000 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": -0.00014881965762469918, "min": -0.12605445086956024, "max": 0.22231441736221313, "count": 5000 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": -0.018602456897497177, "min": -25.887331008911133, "max": 31.45751953125, "count": 5000 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": 0.0018781083635985851, "min": -0.1272134780883789, "max": 0.22259974479675293, "count": 5000 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": 0.23476354777812958, "min": -26.17746353149414, "max": 31.11681365966797, "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": -0.010470398902893066, "min": -0.6015478268913601, "max": 0.5490851508508815, "count": 5000 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": -1.3087998628616333, "min": -85.99719989299774, "max": 64.7364000082016, "count": 5000 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": -0.010470398902893066, "min": -0.6015478268913601, "max": 0.5490851508508815, "count": 5000 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": -1.3087998628616333, "min": -85.99719989299774, "max": 64.7364000082016, "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": 0.019048903541018566, "min": 0.010582155667361804, "max": 0.02676383561338298, "count": 2424 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.019048903541018566, "min": 0.010582155667361804, "max": 0.02676383561338298, "count": 2424 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.06459157392382622, "min": 0.00014100979866877122, "max": 0.10479331935445467, "count": 2424 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.06459157392382622, "min": 0.00014100979866877122, "max": 0.10479331935445467, "count": 2424 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.06549756055076918, "min": 0.00014164091359513502, "max": 0.10648134301106135, "count": 2424 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.06549756055076918, "min": 0.00014164091359513502, "max": 0.10648134301106135, "count": 2424 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 2424 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 2424 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.20000000000000004, "max": 0.20000000000000007, "count": 2424 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.20000000000000004, "max": 0.20000000000000007, "count": 2424 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 2424 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 2424 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1675684775", "python_version": "3.9.16 | packaged by conda-forge | (main, Feb 1 2023, 21:38:11) \n[Clang 14.0.6 ]", "command_line_arguments": "/opt/homebrew/anaconda3/envs/rl/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos/SoccerTwos.app --run-id=SoccerTwos --no-graphics", "mlagents_version": "0.31.0.dev0", "mlagents_envs_version": "0.31.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.11.0", "numpy_version": "1.21.2", "end_time_seconds": "1675907257" }, "total": 206448.191836084, "count": 1, "self": 0.36805245900177397, "children": { "run_training.setup": { "total": 0.014650083000000036, "count": 1, "self": 0.014650083000000036 }, "TrainerController.start_learning": { "total": 206447.809133542, "count": 1, "self": 43.24963995110011, "children": { "TrainerController._reset_env": { "total": 12.661075918946864, "count": 250, "self": 12.661075918946864 }, "TrainerController.advance": { "total": 206391.81318413094, "count": 3456911, "self": 39.66936604527291, "children": { "env_step": { "total": 169108.43224207006, "count": 3456911, "self": 163435.63346323566, "children": { "SubprocessEnvManager._take_step": { "total": 5646.28606319312, "count": 3456911, "self": 160.03624858593048, "children": { "TorchPolicy.evaluate": { "total": 5486.249814607189, "count": 6279810, "self": 5486.249814607189 } } }, "workers": { "total": 26.51271564129007, "count": 3456911, "self": 0.0, "children": { "worker_root": { "total": 206375.7414340783, "count": 3456911, "is_parallel": true, "self": 47894.350554134435, "children": { "steps_from_proto": { "total": 0.4054131268480161, "count": 500, "is_parallel": true, "self": 0.045059887441389224, "children": { "_process_rank_one_or_two_observation": { "total": 0.3603532394066269, "count": 2000, "is_parallel": true, "self": 0.3603532394066269 } } }, "UnityEnvironment.step": { "total": 158480.98546681704, "count": 3456911, "is_parallel": true, "self": 398.3425379449618, "children": { "UnityEnvironment._generate_step_input": { "total": 2791.330253883385, "count": 3456911, "is_parallel": true, "self": 2791.330253883385 }, "communicator.exchange": { "total": 149546.40026178435, "count": 3456911, "is_parallel": true, "self": 149546.40026178435 }, "steps_from_proto": { "total": 5744.912413204353, "count": 6913822, "is_parallel": true, "self": 635.4814637829531, "children": { "_process_rank_one_or_two_observation": { "total": 5109.430949421399, "count": 27655288, "is_parallel": true, "self": 5109.430949421399 } } } } } } } } } } }, "trainer_advance": { "total": 37243.71157601559, "count": 3456911, "self": 306.24156623405725, "children": { "process_trajectory": { "total": 8898.072100938387, "count": 3456911, "self": 8889.174947892418, "children": { "RLTrainer._checkpoint": { "total": 8.897153045969844, "count": 100, "self": 8.897153045969844 } } }, "_update_policy": { "total": 28039.397908843144, "count": 2424, "self": 4279.4441373179, "children": { "TorchPOCAOptimizer.update": { "total": 23759.953771525245, "count": 72735, "self": 23759.953771525245 } } } } } } }, "trainer_threads": { "total": 3.3300602808594704e-07, "count": 1, "self": 3.3300602808594704e-07 }, "TrainerController._save_models": { "total": 0.08523320802487433, "count": 1, "self": 0.0028838740254286677, "children": { "RLTrainer._checkpoint": { "total": 0.08234933399944566, "count": 1, "self": 0.08234933399944566 } } } } } } }