{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 1.5210864543914795, "min": 1.283016324043274, "max": 1.5693892240524292, "count": 67 }, "SoccerTwos.Policy.Entropy.sum": { "value": 31346.55078125, "min": 369.5086975097656, "max": 36128.84375, "count": 67 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 73.19117647058823, "min": 7.0, "max": 88.2280701754386, "count": 67 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19908.0, "min": 28.0, "max": 22708.0, "count": 67 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1501.20479835153, "min": 1467.0070375243758, "max": 1516.5938430657802, "count": 67 }, "SoccerTwos.Self-play.ELO.sum": { "value": 204163.85257580807, "min": 2949.5553523885633, "max": 275309.6668144112, "count": 67 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 67 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 67 }, "SoccerTwos.Step.mean": { "value": 16659998.0, "min": 16009914.0, "max": 16659998.0, "count": 66 }, "SoccerTwos.Step.sum": { "value": 16659998.0, "min": 16009914.0, "max": 16659998.0, "count": 66 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": 0.006284900940954685, "min": -0.09183704853057861, "max": 0.038205210119485855, "count": 66 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": 0.8484616279602051, "min": -14.418416976928711, "max": 6.8769378662109375, "count": 66 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": 0.007226753514260054, "min": -0.08986865729093552, "max": 0.035017531365156174, "count": 66 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": 0.9756117463111877, "min": -14.109378814697266, "max": 6.280918121337891, "count": 66 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 66 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 66 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": -0.04052592604248612, "min": -0.3240030765533447, "max": 0.21911506865122546, "count": 66 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": -5.471000015735626, "min": -42.120399951934814, "max": 31.99080002307892, "count": 66 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": -0.04052592604248612, "min": -0.3240030765533447, "max": 0.21911506865122546, "count": 66 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": -5.471000015735626, "min": -42.120399951934814, "max": 31.99080002307892, "count": 66 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.01663626519633302, "min": 0.011058855353621767, "max": 0.021713046291066955, "count": 31 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.01663626519633302, "min": 0.011058855353621767, "max": 0.021713046291066955, "count": 31 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.09606809318065643, "min": 0.08164825389782587, "max": 0.10430057098468144, "count": 31 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.09606809318065643, "min": 0.08164825389782587, "max": 0.10430057098468144, "count": 31 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.09743865678707758, "min": 0.08355539763967196, "max": 0.10640152444442114, "count": 31 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.09743865678707758, "min": 0.08355539763967196, "max": 0.10640152444442114, "count": 31 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 31 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 31 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 31 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 31 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 31 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 31 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1711073054", "python_version": "3.10.13 | packaged by conda-forge | (main, Dec 23 2023, 15:36:39) [GCC 12.3.0]", "command_line_arguments": "/home/cyf/miniforge3/envs/drl/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos/SoccerTwos.x86_64 --run-id=SoccerTwos --no-graphics --resume", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.1.0+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1711073801" }, "total": 746.8805355050135, "count": 1, "self": 0.09119231591466814, "children": { "run_training.setup": { "total": 0.00963994103949517, "count": 1, "self": 0.00963994103949517 }, "TrainerController.start_learning": { "total": 746.7797032480594, "count": 1, "self": 0.45881012629251927, "children": { "TrainerController._reset_env": { "total": 0.7531929580727592, "count": 5, "self": 0.7531929580727592 }, "TrainerController.advance": { "total": 745.4924428357044, "count": 45650, "self": 0.42536425415892154, "children": { "env_step": { "total": 310.62293989537284, "count": 45650, "self": 256.1516028151382, "children": { "SubprocessEnvManager._take_step": { "total": 54.18669039616361, "count": 45650, "self": 3.173724082647823, "children": { "TorchPolicy.evaluate": { "total": 51.01296631351579, "count": 83582, "self": 51.01296631351579 } } }, "workers": { "total": 0.2846466840710491, "count": 45649, "self": 0.0, "children": { "worker_root": { "total": 746.0294992424315, "count": 45649, "is_parallel": true, "self": 539.6528549185023, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0012704589171335101, "count": 2, "is_parallel": true, "self": 0.0003078957088291645, "children": { "_process_rank_one_or_two_observation": { "total": 0.0009625632083043456, "count": 8, "is_parallel": true, "self": 0.0009625632083043456 } } }, "UnityEnvironment.step": { "total": 0.012883958988822997, "count": 1, "is_parallel": true, "self": 0.0002818070352077484, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00022728496696799994, "count": 1, "is_parallel": true, "self": 0.00022728496696799994 }, "communicator.exchange": { "total": 0.011604372062720358, "count": 1, "is_parallel": true, "self": 0.011604372062720358 }, "steps_from_proto": { "total": 0.0007704949239268899, "count": 2, "is_parallel": true, "self": 0.00016126083210110664, "children": { "_process_rank_one_or_two_observation": { "total": 0.0006092340918257833, "count": 8, "is_parallel": true, "self": 0.0006092340918257833 } } } } } } }, "steps_from_proto": { "total": 0.003091786988079548, "count": 8, "is_parallel": true, "self": 0.0005975650856271386, "children": { "_process_rank_one_or_two_observation": { "total": 0.0024942219024524093, "count": 32, "is_parallel": true, "self": 0.0024942219024524093 } } }, "UnityEnvironment.step": { "total": 206.37355253694113, "count": 45648, "is_parallel": true, "self": 11.50478288391605, "children": { "UnityEnvironment._generate_step_input": { "total": 6.720954565797001, "count": 45648, "is_parallel": true, "self": 6.720954565797001 }, "communicator.exchange": { "total": 157.76569051586557, "count": 45648, "is_parallel": true, "self": 157.76569051586557 }, "steps_from_proto": { "total": 30.38212457136251, "count": 91296, "is_parallel": true, "self": 5.6414579808479175, "children": { "_process_rank_one_or_two_observation": { "total": 24.740666590514593, "count": 365184, "is_parallel": true, "self": 24.740666590514593 } } } } } } } } } } }, "trainer_advance": { "total": 434.44413868617266, "count": 45649, "self": 4.367854901473038, "children": { "process_trajectory": { "total": 64.74150588177145, "count": 45649, "self": 64.5696170637384, "children": { "RLTrainer._checkpoint": { "total": 0.17188881803303957, "count": 2, "self": 0.17188881803303957 } } }, "_update_policy": { "total": 365.3347779029282, "count": 32, "self": 36.68577631516382, "children": { "TorchPOCAOptimizer.update": { "total": 328.64900158776436, "count": 960, "self": 328.64900158776436 } } } } } } }, "trainer_threads": { "total": 4.00003045797348e-07, "count": 1, "self": 4.00003045797348e-07 }, "TrainerController._save_models": { "total": 0.07525692798662931, "count": 1, "self": 0.0016847329679876566, "children": { "RLTrainer._checkpoint": { "total": 0.07357219501864165, "count": 1, "self": 0.07357219501864165 } } } } } } }