{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 3.2715375423431396, "min": 3.2599244117736816, "max": 3.295760154724121, "count": 10 }, "SoccerTwos.Policy.Entropy.sum": { "value": 69094.875, "min": 41629.0546875, "max": 105464.328125, "count": 10 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 757.1428571428571, "min": 581.375, "max": 872.3333333333334, "count": 10 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 21200.0, "min": 15660.0, "max": 25212.0, "count": 10 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1204.8392342810741, "min": 1198.270734146438, "max": 1204.8392342810741, "count": 10 }, "SoccerTwos.Self-play.ELO.sum": { "value": 4819.356937124297, "min": 4804.197331701617, "max": 12034.551733414275, "count": 10 }, "SoccerTwos.Step.mean": { "value": 99198.0, "min": 9626.0, "max": 99198.0, "count": 10 }, "SoccerTwos.Step.sum": { "value": 99198.0, "min": 9626.0, "max": 99198.0, "count": 10 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": 0.05059700086712837, "min": 0.05059700086712837, "max": 0.10302615910768509, "count": 10 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": 0.7083579897880554, "min": 0.6413058638572693, "max": 1.7514102458953857, "count": 10 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": 0.04834681749343872, "min": 0.04834681749343872, "max": 0.10301734507083893, "count": 10 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": 0.6768554449081421, "min": 0.6048709154129028, "max": 1.7512948513031006, "count": 10 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 10 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 10 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": 0.028542854956218174, "min": -0.6043384613899084, "max": 0.17014117801890655, "count": 10 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": 0.39959996938705444, "min": -7.8563999980688095, "max": 2.892400026321411, "count": 10 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": 0.028542854956218174, "min": -0.6043384613899084, "max": 0.17014117801890655, "count": 10 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": 0.39959996938705444, "min": -7.8563999980688095, "max": 2.892400026321411, "count": 10 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 10 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 10 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.015819103210621202, "min": 0.014563547916865597, "max": 0.018268799929258724, "count": 4 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.015819103210621202, "min": 0.014563547916865597, "max": 0.018268799929258724, "count": 4 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.003761661254490415, "min": 0.003761661254490415, "max": 0.006663544305289785, "count": 4 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.003761661254490415, "min": 0.003761661254490415, "max": 0.006663544305289785, "count": 4 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.00379874191324537, "min": 0.00379874191324537, "max": 0.0061240348033607004, "count": 4 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.00379874191324537, "min": 0.00379874191324537, "max": 0.0061240348033607004, "count": 4 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 4 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 4 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 4 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 4 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 4 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 4 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1688421052", "python_version": "3.9.16 (main, May 15 2023, 23:46:34) \n[GCC 11.2.0]", "command_line_arguments": "/home/octadesh/anaconda3/envs/rl/bin/mlagents-learn ./training-envs-executables/SoccerTwos/config.yaml --env=./training-envs-executables/SoccerTwos/SoccerTwos.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": "1.11.0+cu102", "numpy_version": "1.21.2", "end_time_seconds": "1688421314" }, "total": 262.4532150719999, "count": 1, "self": 0.22352481099994748, "children": { "run_training.setup": { "total": 0.010035459999926388, "count": 1, "self": 0.010035459999926388 }, "TrainerController.start_learning": { "total": 262.21965480100005, "count": 1, "self": 0.1333598250087107, "children": { "TrainerController._reset_env": { "total": 0.8965802019999956, "count": 2, "self": 0.8965802019999956 }, "TrainerController.advance": { "total": 260.9802785329914, "count": 6768, "self": 0.11742586798732191, "children": { "env_step": { "total": 84.55074408300607, "count": 6768, "self": 67.7741551900042, "children": { "SubprocessEnvManager._take_step": { "total": 16.696960543003115, "count": 6768, "self": 0.5586619820021497, "children": { "TorchPolicy.evaluate": { "total": 16.138298561000965, "count": 13432, "self": 16.138298561000965 } } }, "workers": { "total": 0.07962834999875668, "count": 6768, "self": 0.0, "children": { "worker_root": { "total": 261.37585360900323, "count": 6768, "is_parallel": true, "self": 207.63039509000726, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0029241700000284254, "count": 2, "is_parallel": true, "self": 0.0009252909999304393, "children": { "_process_rank_one_or_two_observation": { "total": 0.001998879000097986, "count": 8, "is_parallel": true, "self": 0.001998879000097986 } } }, "UnityEnvironment.step": { "total": 0.02075566799999251, "count": 1, "is_parallel": true, "self": 0.00042800400001397065, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005715810000310739, "count": 1, "is_parallel": true, "self": 0.0005715810000310739 }, "communicator.exchange": { "total": 0.018465358999947057, "count": 1, "is_parallel": true, "self": 0.018465358999947057 }, "steps_from_proto": { "total": 0.0012907240000004094, "count": 2, "is_parallel": true, "self": 0.0002814209999542072, "children": { "_process_rank_one_or_two_observation": { "total": 0.0010093030000462022, "count": 8, "is_parallel": true, "self": 0.0010093030000462022 } } } } } } }, "UnityEnvironment.step": { "total": 53.745458518995974, "count": 6767, "is_parallel": true, "self": 2.9883827400004748, "children": { "UnityEnvironment._generate_step_input": { "total": 2.367578988003288, "count": 6767, "is_parallel": true, "self": 2.367578988003288 }, "communicator.exchange": { "total": 39.47945499299624, "count": 6767, "is_parallel": true, "self": 39.47945499299624 }, "steps_from_proto": { "total": 8.910041797995973, "count": 13534, "is_parallel": true, "self": 1.7090663739994625, "children": { "_process_rank_one_or_two_observation": { "total": 7.2009754239965105, "count": 54136, "is_parallel": true, "self": 7.2009754239965105 } } } } } } } } } } }, "trainer_advance": { "total": 176.31210858199802, "count": 6768, "self": 1.1104138319963113, "children": { "process_trajectory": { "total": 21.492238054001632, "count": 6768, "self": 21.492238054001632 }, "_update_policy": { "total": 153.70945669600007, "count": 4, "self": 8.936217062000651, "children": { "TorchPOCAOptimizer.update": { "total": 144.77323963399942, "count": 120, "self": 144.77323963399942 } } } } } } }, "trainer_threads": { "total": 2.033999976447376e-06, "count": 1, "self": 2.033999976447376e-06 }, "TrainerController._save_models": { "total": 0.2094342069999584, "count": 1, "self": 0.0019023749999860229, "children": { "RLTrainer._checkpoint": { "total": 0.20753183199997238, "count": 1, "self": 0.20753183199997238 } } } } } } }