{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 2.732017993927002, "min": 1.4310749769210815, "max": 3.295657157897949, "count": 5000 }, "SoccerTwos.Policy.Entropy.sum": { "value": 46859.57421875, "min": 17607.2578125, "max": 139971.84375, "count": 5000 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 88.23214285714286, "min": 49.295918367346935, "max": 999.0, "count": 5000 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19764.0, "min": 13172.0, "max": 27080.0, "count": 5000 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1328.9875677323002, "min": 1067.6681513782962, "max": 1425.1669090363382, "count": 4978 }, "SoccerTwos.Self-play.ELO.sum": { "value": 148846.60758601764, "min": 2371.5191713258605, "max": 241218.86328195722, "count": 4978 }, "SoccerTwos.Step.mean": { "value": 49999973.0, "min": 9236.0, "max": 49999973.0, "count": 5000 }, "SoccerTwos.Step.sum": { "value": 49999973.0, "min": 9236.0, "max": 49999973.0, "count": 5000 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": 0.002145185600966215, "min": -0.35611632466316223, "max": 1.1934101581573486, "count": 5000 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": 0.2402607798576355, "min": -49.1440544128418, "max": 134.99392700195312, "count": 5000 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": 0.006087425164878368, "min": -0.3684330880641937, "max": 1.1617356538772583, "count": 5000 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": 0.6817916035652161, "min": -50.84376525878906, "max": 131.594482421875, "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": -0.16895714508635656, "min": -0.6427789487336811, "max": 0.46163683816006307, "count": 5000 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": -18.923200249671936, "min": -56.69440001249313, "max": 50.39880013465881, "count": 5000 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": -0.16895714508635656, "min": -0.6427789487336811, "max": 0.46163683816006307, "count": 5000 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": -18.923200249671936, "min": -56.69440001249313, "max": 50.39880013465881, "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": 0.01943461374224474, "min": 0.011112430859551143, "max": 0.03933954979875125, "count": 2412 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.01943461374224474, "min": 0.011112430859551143, "max": 0.03933954979875125, "count": 2412 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.058215494453907016, "min": 5.623583623067437e-06, "max": 17.72092866244105, "count": 2412 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.058215494453907016, "min": 5.623583623067437e-06, "max": 17.72092866244105, "count": 2412 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.059470121189951895, "min": 1.4972809033982533e-05, "max": 20.085067470418288, "count": 2412 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.059470121189951895, "min": 1.4972809033982533e-05, "max": 20.085067470418288, "count": 2412 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.003000000000000001, "min": 0.003000000000000001, "max": 0.003000000000000001, "count": 2412 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.003000000000000001, "min": 0.003000000000000001, "max": 0.003000000000000001, "count": 2412 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 2412 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 2412 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 2412 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 2412 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1685605326", "python_version": "3.9.16 (main, Mar 8 2023, 14:00:05) \n[GCC 11.2.0]", "command_line_arguments": "/home/wyt/anaconda3/envs/rl/bin/mlagents-learn ./config/poca/SoccerTwos.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": "1685658486" }, "total": 53160.56620799401, "count": 1, "self": 0.21856565307825804, "children": { "run_training.setup": { "total": 0.006621055072173476, "count": 1, "self": 0.006621055072173476 }, "TrainerController.start_learning": { "total": 53160.34102128586, "count": 1, "self": 60.36968820123002, "children": { "TrainerController._reset_env": { "total": 21.765231831697747, "count": 995, "self": 21.765231831697747 }, "TrainerController.advance": { "total": 53078.05931469775, "count": 3451096, "self": 56.15520123485476, "children": { "env_step": { "total": 39740.48723199195, "count": 3451096, "self": 29044.75445716479, "children": { "SubprocessEnvManager._take_step": { "total": 10660.52838735492, "count": 3451096, "self": 288.1409287536517, "children": { "TorchPolicy.evaluate": { "total": 10372.387458601268, "count": 6469632, "self": 10372.387458601268 } } }, "workers": { "total": 35.20438747224398, "count": 3451096, "self": 0.0, "children": { "worker_root": { "total": 53080.893450592645, "count": 3451096, "is_parallel": true, "self": 30041.395939050708, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.001561193959787488, "count": 2, "is_parallel": true, "self": 0.0003742906264960766, "children": { "_process_rank_one_or_two_observation": { "total": 0.0011869033332914114, "count": 8, "is_parallel": true, "self": 0.0011869033332914114 } } }, "UnityEnvironment.step": { "total": 0.016142722917720675, "count": 1, "is_parallel": true, "self": 0.0003737660590559244, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0003036879934370518, "count": 1, "is_parallel": true, "self": 0.0003036879934370518 }, "communicator.exchange": { "total": 0.01421576295979321, "count": 1, "is_parallel": true, "self": 0.01421576295979321 }, "steps_from_proto": { "total": 0.0012495059054344893, "count": 2, "is_parallel": true, "self": 0.00025913421995937824, "children": { "_process_rank_one_or_two_observation": { "total": 0.000990371685475111, "count": 8, "is_parallel": true, "self": 0.000990371685475111 } } } } } } }, "UnityEnvironment.step": { "total": 23038.307036999613, "count": 3451095, "is_parallel": true, "self": 1248.8022941302042, "children": { "UnityEnvironment._generate_step_input": { "total": 857.56477716472, "count": 3451095, "is_parallel": true, "self": 857.56477716472 }, "communicator.exchange": { "total": 17020.58405685937, "count": 3451095, "is_parallel": true, "self": 17020.58405685937 }, "steps_from_proto": { "total": 3911.3559088453185, "count": 6902190, "is_parallel": true, "self": 814.7830948443152, "children": { "_process_rank_one_or_two_observation": { "total": 3096.5728140010033, "count": 27608760, "is_parallel": true, "self": 3096.5728140010033 } } } } }, "steps_from_proto": { "total": 1.1904745423235, "count": 1988, "is_parallel": true, "self": 0.2469224245287478, "children": { "_process_rank_one_or_two_observation": { "total": 0.9435521177947521, "count": 7952, "is_parallel": true, "self": 0.9435521177947521 } } } } } } } } }, "trainer_advance": { "total": 13281.416881470941, "count": 3451096, "self": 405.0560196649749, "children": { "process_trajectory": { "total": 4799.068029365502, "count": 3451096, "self": 4783.627852224512, "children": { "RLTrainer._checkpoint": { "total": 15.440177140990272, "count": 100, "self": 15.440177140990272 } } }, "_update_policy": { "total": 8077.292832440464, "count": 2412, "self": 5181.555676384829, "children": { "TorchPOCAOptimizer.update": { "total": 2895.737156055635, "count": 72360, "self": 2895.737156055635 } } } } } } }, "trainer_threads": { "total": 5.59026375412941e-07, "count": 1, "self": 5.59026375412941e-07 }, "TrainerController._save_models": { "total": 0.14678599615581334, "count": 1, "self": 0.0011825382243841887, "children": { "RLTrainer._checkpoint": { "total": 0.14560345793142915, "count": 1, "self": 0.14560345793142915 } } } } } } }