{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 2.2531075477600098, "min": 2.205596923828125, "max": 3.2148594856262207, "count": 393 }, "SoccerTwos.Policy.Entropy.sum": { "value": 44485.35546875, "min": 21093.712890625, "max": 175992.0, "count": 393 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 54.333333333333336, "min": 42.55263157894737, "max": 999.0, "count": 393 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19560.0, "min": 3996.0, "max": 32648.0, "count": 393 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1450.3141492791954, "min": 1183.1308426287494, "max": 1458.2502183512165, "count": 376 }, "SoccerTwos.Self-play.ELO.sum": { "value": 261056.54687025517, "min": 2382.429530164287, "max": 331018.88755897584, "count": 376 }, "SoccerTwos.Step.mean": { "value": 4999989.0, "min": 1069006.0, "max": 4999989.0, "count": 394 }, "SoccerTwos.Step.sum": { "value": 4999989.0, "min": 1069006.0, "max": 4999989.0, "count": 394 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": 0.06466507166624069, "min": -0.045848406851291656, "max": 0.22180138528347015, "count": 394 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": 11.6397123336792, "min": -6.60572624206543, "max": 34.379215240478516, "count": 394 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": 0.06135227531194687, "min": -0.046617619693279266, "max": 0.2225351333618164, "count": 394 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": 11.04340934753418, "min": -7.996595859527588, "max": 34.49294662475586, "count": 394 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 394 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 394 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": 0.01482444273100959, "min": -0.6666666666666666, "max": 0.42734762210221516, "count": 394 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": 2.668399691581726, "min": -37.52600026130676, "max": 71.35640001296997, "count": 394 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": 0.01482444273100959, "min": -0.6666666666666666, "max": 0.42734762210221516, "count": 394 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": 2.668399691581726, "min": -37.52600026130676, "max": 71.35640001296997, "count": 394 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 394 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 394 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.015964625528431496, "min": 0.011339024729871501, "max": 0.022405783160744857, "count": 187 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.015964625528431496, "min": 0.011339024729871501, "max": 0.022405783160744857, "count": 187 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.10514686654011408, "min": 0.00021651945450381997, "max": 0.10809014067053795, "count": 187 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.10514686654011408, "min": 0.00021651945450381997, "max": 0.10809014067053795, "count": 187 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.107951819896698, "min": 0.0002174987540153476, "max": 0.1108481079339981, "count": 187 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.107951819896698, "min": 0.0002174987540153476, "max": 0.1108481079339981, "count": 187 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 187 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 187 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.19999999999999996, "max": 0.20000000000000007, "count": 187 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.19999999999999996, "max": 0.20000000000000007, "count": 187 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005, "max": 0.005000000000000001, "count": 187 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005, "max": 0.005000000000000001, "count": 187 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1675414378", "python_version": "3.8.16 (default, Jan 17 2023, 23:13:24) \n[GCC 11.2.0]", "command_line_arguments": "/home/emigoi/miniconda3/envs/rl/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos/SoccerTows.x86_64 --run-id=SoccerTwos --no-graphics --resume", "mlagents_version": "0.31.0.dev0", "mlagents_envs_version": "0.31.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.8.1+cu102", "numpy_version": "1.21.2", "end_time_seconds": "1675423513" }, "total": 9134.877508399999, "count": 1, "self": 0.5058795000004466, "children": { "run_training.setup": { "total": 0.01188659999999686, "count": 1, "self": 0.01188659999999686 }, "TrainerController.start_learning": { "total": 9134.3597423, "count": 1, "self": 4.736177900183975, "children": { "TrainerController._reset_env": { "total": 6.598423800003019, "count": 41, "self": 6.598423800003019 }, "TrainerController.advance": { "total": 9122.680936199813, "count": 267346, "self": 4.950059300006615, "children": { "env_step": { "total": 7276.087199399884, "count": 267346, "self": 4864.879236099585, "children": { "SubprocessEnvManager._take_step": { "total": 2408.223233100152, "count": 267346, "self": 32.16540580033279, "children": { "TorchPolicy.evaluate": { "total": 2376.057827299819, "count": 509968, "self": 2376.057827299819 } } }, "workers": { "total": 2.9847302001481566, "count": 267346, "self": 0.0, "children": { "worker_root": { "total": 9120.953405599965, "count": 267346, "is_parallel": true, "self": 4811.26172639982, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0026335000000017317, "count": 2, "is_parallel": true, "self": 0.0011161000000043941, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015173999999973375, "count": 8, "is_parallel": true, "self": 0.0015173999999973375 } } }, "UnityEnvironment.step": { "total": 0.02836279999999647, "count": 1, "is_parallel": true, "self": 0.0004635000000021705, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00038879999999608117, "count": 1, "is_parallel": true, "self": 0.00038879999999608117 }, "communicator.exchange": { "total": 0.026017500000001803, "count": 1, "is_parallel": true, "self": 0.026017500000001803 }, "steps_from_proto": { "total": 0.0014929999999964139, "count": 2, "is_parallel": true, "self": 0.00032689999999746533, "children": { "_process_rank_one_or_two_observation": { "total": 0.0011660999999989485, "count": 8, "is_parallel": true, "self": 0.0011660999999989485 } } } } } } }, "steps_from_proto": { "total": 0.06119719999665563, "count": 80, "is_parallel": true, "self": 0.011537400000626974, "children": { "_process_rank_one_or_two_observation": { "total": 0.04965979999602865, "count": 320, "is_parallel": true, "self": 0.04965979999602865 } } }, "UnityEnvironment.step": { "total": 4309.630482000148, "count": 267345, "is_parallel": true, "self": 123.45304180037056, "children": { "UnityEnvironment._generate_step_input": { "total": 89.1560935000251, "count": 267345, "is_parallel": true, "self": 89.1560935000251 }, "communicator.exchange": { "total": 3687.05164360012, "count": 267345, "is_parallel": true, "self": 3687.05164360012 }, "steps_from_proto": { "total": 409.96970309963245, "count": 534690, "is_parallel": true, "self": 79.19082019962849, "children": { "_process_rank_one_or_two_observation": { "total": 330.77888290000396, "count": 2138760, "is_parallel": true, "self": 330.77888290000396 } } } } } } } } } } }, "trainer_advance": { "total": 1841.643677499922, "count": 267346, "self": 29.870324400264508, "children": { "process_trajectory": { "total": 673.5833846996571, "count": 267346, "self": 672.0646403996572, "children": { "RLTrainer._checkpoint": { "total": 1.5187442999999803, "count": 8, "self": 1.5187442999999803 } } }, "_update_policy": { "total": 1138.1899684000002, "count": 187, "self": 435.380598200015, "children": { "TorchPOCAOptimizer.update": { "total": 702.8093701999852, "count": 5628, "self": 702.8093701999852 } } } } } } }, "trainer_threads": { "total": 5.999991117278114e-07, "count": 1, "self": 5.999991117278114e-07 }, "TrainerController._save_models": { "total": 0.3442037999993772, "count": 1, "self": 0.001438600000255974, "children": { "RLTrainer._checkpoint": { "total": 0.34276519999912125, "count": 1, "self": 0.34276519999912125 } } } } } } }