{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 1.3111799955368042, "min": 1.2855664491653442, "max": 2.188783884048462, "count": 4570 }, "SoccerTwos.Policy.Entropy.sum": { "value": 23622.21875, "min": 21731.388671875, "max": 46860.515625, "count": 4570 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 62.17948717948718, "min": 38.330708661417326, "max": 96.82352941176471, "count": 4570 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19400.0, "min": 17644.0, "max": 21636.0, "count": 4570 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1370.5288981886865, "min": 1194.9149603136586, "max": 1426.1929789955975, "count": 4570 }, "SoccerTwos.Self-play.ELO.sum": { "value": 213802.5081174351, "min": 140965.7626806283, "max": 343286.631748718, "count": 4570 }, "SoccerTwos.Step.mean": { "value": 49999895.0, "min": 4309918.0, "max": 49999895.0, "count": 4570 }, "SoccerTwos.Step.sum": { "value": 49999895.0, "min": 4309918.0, "max": 49999895.0, "count": 4570 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": -0.03251473605632782, "min": -0.14258797466754913, "max": 0.10400567203760147, "count": 4570 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": -5.104813575744629, "min": -25.951011657714844, "max": 20.679386138916016, "count": 4570 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": -0.03338980674743652, "min": -0.145628422498703, "max": 0.10737495124340057, "count": 4570 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": -5.242199897766113, "min": -26.50437355041504, "max": 21.174419403076172, "count": 4570 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 4570 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 4570 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": -0.053352865064220066, "min": -0.4170310556518365, "max": 0.312821740689485, "count": 4570 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": -8.37639981508255, "min": -67.14199995994568, "max": 57.88719987869263, "count": 4570 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": -0.053352865064220066, "min": -0.4170310556518365, "max": 0.312821740689485, "count": 4570 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": -8.37639981508255, "min": -67.14199995994568, "max": 57.88719987869263, "count": 4570 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 4570 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 4570 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.01991779778036289, "min": 0.009833579595821599, "max": 0.02802308723718549, "count": 2219 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.01991779778036289, "min": 0.009833579595821599, "max": 0.02802308723718549, "count": 2219 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.10099085420370102, "min": 0.07856509958704312, "max": 0.13108116562167804, "count": 2219 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.10099085420370102, "min": 0.07856509958704312, "max": 0.13108116562167804, "count": 2219 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.102103441208601, "min": 0.07945097560683886, "max": 0.13329573770364125, "count": 2219 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.102103441208601, "min": 0.07945097560683886, "max": 0.13329573770364125, "count": 2219 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 2219 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 2219 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 2219 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 2219 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 2219 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 2219 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1721828180", "python_version": "3.10.12 | packaged by conda-forge | (main, Jun 23 2023, 22:40:32) [GCC 12.3.0]", "command_line_arguments": "/home/unlike/miniconda3/envs/ml-agents/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos/SoccerTwos.x86_64 --run-id=SoccerTwos --resume --no-graphics", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.3.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1721854131" }, "total": 25950.441492744, "count": 1, "self": 0.1669595460043638, "children": { "run_training.setup": { "total": 0.005906230999244144, "count": 1, "self": 0.005906230999244144 }, "TrainerController.start_learning": { "total": 25950.268626966998, "count": 1, "self": 23.044559067475348, "children": { "TrainerController._reset_env": { "total": 2.031587658042554, "count": 230, "self": 2.031587658042554 }, "TrainerController.advance": { "total": 25925.108505157477, "count": 3174216, "self": 22.11772064798788, "children": { "env_step": { "total": 19238.14321225281, "count": 3174216, "self": 14385.698092758597, "children": { "SubprocessEnvManager._take_step": { "total": 4837.245746559864, "count": 3174216, "self": 169.10663177945753, "children": { "TorchPolicy.evaluate": { "total": 4668.139114780406, "count": 5733790, "self": 4668.139114780406 } } }, "workers": { "total": 15.199372934348503, "count": 3174216, "self": 0.0, "children": { "worker_root": { "total": 25916.210800837714, "count": 3174216, "is_parallel": true, "self": 14072.16607910991, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0009477109997533262, "count": 2, "is_parallel": true, "self": 0.00022423200425691903, "children": { "_process_rank_one_or_two_observation": { "total": 0.0007234789954964072, "count": 8, "is_parallel": true, "self": 0.0007234789954964072 } } }, "UnityEnvironment.step": { "total": 0.010612623002089094, "count": 1, "is_parallel": true, "self": 0.00023258199871634133, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00020189900169498287, "count": 1, "is_parallel": true, "self": 0.00020189900169498287 }, "communicator.exchange": { "total": 0.009530215000268072, "count": 1, "is_parallel": true, "self": 0.009530215000268072 }, "steps_from_proto": { "total": 0.0006479270014096983, "count": 2, "is_parallel": true, "self": 0.00012458499986678362, "children": { "_process_rank_one_or_two_observation": { "total": 0.0005233420015429147, "count": 8, "is_parallel": true, "self": 0.0005233420015429147 } } } } } } }, "steps_from_proto": { "total": 0.14035587402395322, "count": 458, "is_parallel": true, "self": 0.026326446979510365, "children": { "_process_rank_one_or_two_observation": { "total": 0.11402942704444285, "count": 1832, "is_parallel": true, "self": 0.11402942704444285 } } }, "UnityEnvironment.step": { "total": 11843.904365853781, "count": 3174215, "is_parallel": true, "self": 658.2597974323216, "children": { "UnityEnvironment._generate_step_input": { "total": 379.51864914055113, "count": 3174215, "is_parallel": true, "self": 379.51864914055113 }, "communicator.exchange": { "total": 9059.325374901728, "count": 3174215, "is_parallel": true, "self": 9059.325374901728 }, "steps_from_proto": { "total": 1746.8005443791808, "count": 6348430, "is_parallel": true, "self": 318.0379855389583, "children": { "_process_rank_one_or_two_observation": { "total": 1428.7625588402225, "count": 25393720, "is_parallel": true, "self": 1428.7625588402225 } } } } } } } } } } }, "trainer_advance": { "total": 6664.84757225668, "count": 3174216, "self": 175.5509459523346, "children": { "process_trajectory": { "total": 2893.2320144626538, "count": 3174216, "self": 2886.7261530876494, "children": { "RLTrainer._checkpoint": { "total": 6.505861375004315, "count": 92, "self": 6.505861375004315 } } }, "_update_policy": { "total": 3596.0646118416917, "count": 2219, "self": 2077.9340705413124, "children": { "TorchPOCAOptimizer.update": { "total": 1518.1305413003793, "count": 66570, "self": 1518.1305413003793 } } } } } } }, "trainer_threads": { "total": 3.349996404722333e-07, "count": 1, "self": 3.349996404722333e-07 }, "TrainerController._save_models": { "total": 0.08397474900266388, "count": 1, "self": 0.0009553830022923648, "children": { "RLTrainer._checkpoint": { "total": 0.08301936600037152, "count": 1, "self": 0.08301936600037152 } } } } } } }