{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 3.1578032970428467, "min": 3.0943503379821777, "max": 3.2957470417022705, "count": 533 }, "SoccerTwos.Policy.Entropy.sum": { "value": 68814.8515625, "min": 9006.1396484375, "max": 133231.34375, "count": 533 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 920.4, "min": 409.1666666666667, "max": 999.0, "count": 533 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 18408.0, "min": 16344.0, "max": 23780.0, "count": 533 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1211.0140709225593, "min": 1184.7310891700515, "max": 1211.652420415645, "count": 390 }, "SoccerTwos.Self-play.ELO.sum": { "value": 4844.056283690237, "min": 2370.4452805059636, "max": 21534.521166968163, "count": 390 }, "SoccerTwos.Step.mean": { "value": 5329634.0, "min": 9328.0, "max": 5329634.0, "count": 533 }, "SoccerTwos.Step.sum": { "value": 5329634.0, "min": 9328.0, "max": 5329634.0, "count": 533 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": -0.00663940142840147, "min": -0.04170246422290802, "max": 0.005158791318535805, "count": 533 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": -0.0730334147810936, "min": -0.5421320199966431, "max": 0.05741597339510918, "count": 533 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": -0.006606684532016516, "min": -0.037998493760824203, "max": 0.004716083873063326, "count": 533 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": -0.07267352938652039, "min": -0.5038904547691345, "max": 0.05187692493200302, "count": 533 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 533 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 533 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": -0.16701818189837717, "min": -0.6666666666666666, "max": 0.36900000274181366, "count": 533 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": -1.8372000008821487, "min": -10.0, "max": 5.9040000438690186, "count": 533 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": -0.16701818189837717, "min": -0.6666666666666666, "max": 0.36900000274181366, "count": 533 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": -1.8372000008821487, "min": -10.0, "max": 5.9040000438690186, "count": 533 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 533 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 533 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.01781173248697693, "min": 0.011581762720985959, "max": 0.022112421380976837, "count": 248 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.01781173248697693, "min": 0.011581762720985959, "max": 0.022112421380976837, "count": 248 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 6.619557328425192e-05, "min": 1.2819827558037862e-07, "max": 0.007151341903954745, "count": 248 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 6.619557328425192e-05, "min": 1.2819827558037862e-07, "max": 0.007151341903954745, "count": 248 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 6.617105118493783e-05, "min": 1.288317937072255e-07, "max": 0.007147595100104809, "count": 248 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 6.617105118493783e-05, "min": 1.288317937072255e-07, "max": 0.007147595100104809, "count": 248 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 248 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 248 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 248 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 248 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 248 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 248 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1690974671", "python_version": "3.9.17 (main, Jul 5 2023, 20:41:20) \n[GCC 11.2.0]", "command_line_arguments": "/home/jh/anaconda3/envs/rl/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos.exe --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+cpu", "numpy_version": "1.21.2", "end_time_seconds": "1690987967" }, "total": 13295.112351631, "count": 1, "self": 0.5330448329987121, "children": { "run_training.setup": { "total": 0.009768414000063785, "count": 1, "self": 0.009768414000063785 }, "TrainerController.start_learning": { "total": 13294.569538384001, "count": 1, "self": 5.719322810129597, "children": { "TrainerController._reset_env": { "total": 1.9886303630009934, "count": 27, "self": 1.9886303630009934 }, "TrainerController.advance": { "total": 13286.64480745987, "count": 346829, "self": 5.669291412561506, "children": { "env_step": { "total": 5226.643601603117, "count": 346829, "self": 4467.314352221897, "children": { "SubprocessEnvManager._take_step": { "total": 755.8678143183806, "count": 346829, "self": 31.81169897282598, "children": { "TorchPolicy.evaluate": { "total": 724.0561153455546, "count": 688772, "self": 724.0561153455546 } } }, "workers": { "total": 3.461435062838973, "count": 346829, "self": 0.0, "children": { "worker_root": { "total": 13264.300721925229, "count": 346829, "is_parallel": true, "self": 9421.340694249127, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0019402400012040744, "count": 2, "is_parallel": true, "self": 0.00047446000007767, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014657800011264044, "count": 8, "is_parallel": true, "self": 0.0014657800011264044 } } }, "UnityEnvironment.step": { "total": 0.020414718000210996, "count": 1, "is_parallel": true, "self": 0.00042586900053720456, "children": { "UnityEnvironment._generate_step_input": { "total": 0.000597819000176969, "count": 1, "is_parallel": true, "self": 0.000597819000176969 }, "communicator.exchange": { "total": 0.018284440000570612, "count": 1, "is_parallel": true, "self": 0.018284440000570612 }, "steps_from_proto": { "total": 0.0011065899989262107, "count": 2, "is_parallel": true, "self": 0.0002242499995190883, "children": { "_process_rank_one_or_two_observation": { "total": 0.0008823399994071224, "count": 8, "is_parallel": true, "self": 0.0008823399994071224 } } } } } } }, "UnityEnvironment.step": { "total": 3842.9299300630946, "count": 346828, "is_parallel": true, "self": 134.541852679753, "children": { "UnityEnvironment._generate_step_input": { "total": 103.81118051082103, "count": 346828, "is_parallel": true, "self": 103.81118051082103 }, "communicator.exchange": { "total": 3212.3851369052054, "count": 346828, "is_parallel": true, "self": 3212.3851369052054 }, "steps_from_proto": { "total": 392.1917599673152, "count": 693656, "is_parallel": true, "self": 77.209227386169, "children": { "_process_rank_one_or_two_observation": { "total": 314.9825325811462, "count": 2774624, "is_parallel": true, "self": 314.9825325811462 } } } } }, "steps_from_proto": { "total": 0.03009761300563696, "count": 52, "is_parallel": true, "self": 0.005883859999812557, "children": { "_process_rank_one_or_two_observation": { "total": 0.0242137530058244, "count": 208, "is_parallel": true, "self": 0.0242137530058244 } } } } } } } } }, "trainer_advance": { "total": 8054.331914444192, "count": 346829, "self": 47.68821373466926, "children": { "process_trajectory": { "total": 942.3445540715256, "count": 346829, "self": 940.025219979525, "children": { "RLTrainer._checkpoint": { "total": 2.319334092000645, "count": 10, "self": 2.319334092000645 } } }, "_update_policy": { "total": 7064.299146637997, "count": 249, "self": 502.3294806941003, "children": { "TorchPOCAOptimizer.update": { "total": 6561.969665943897, "count": 7459, "self": 6561.969665943897 } } } } } } }, "trainer_threads": { "total": 6.599984772037715e-07, "count": 1, "self": 6.599984772037715e-07 }, "TrainerController._save_models": { "total": 0.21677709100185893, "count": 1, "self": 0.023412786002154462, "children": { "RLTrainer._checkpoint": { "total": 0.19336430499970447, "count": 1, "self": 0.19336430499970447 } } } } } } }