{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 3.1323869228363037, "min": 3.0606625080108643, "max": 3.2958083152770996, "count": 500 }, "SoccerTwos.Policy.Entropy.sum": { "value": 40996.6796875, "min": 17678.60546875, "max": 170737.53125, "count": 500 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 999.0, "min": 371.9230769230769, "max": 999.0, "count": 500 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19980.0, "min": 10600.0, "max": 25616.0, "count": 500 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1181.7160720870315, "min": 1177.4109326952434, "max": 1208.5830662436736, "count": 422 }, "SoccerTwos.Self-play.ELO.sum": { "value": 2363.432144174063, "min": 2357.199266755703, "max": 19141.64147920675, "count": 422 }, "SoccerTwos.Step.mean": { "value": 4999854.0, "min": 9658.0, "max": 4999854.0, "count": 500 }, "SoccerTwos.Step.sum": { "value": 4999854.0, "min": 9658.0, "max": 4999854.0, "count": 500 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": -0.003024178557097912, "min": -0.031495776027441025, "max": 0.06315721571445465, "count": 500 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": -0.03024178557097912, "min": -0.5153208374977112, "max": 0.862785816192627, "count": 500 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": -0.002978297881782055, "min": -0.033182282000780106, "max": 0.07270117849111557, "count": 500 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": -0.02978297881782055, "min": -0.5303707718849182, "max": 0.945115327835083, "count": 500 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 500 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 500 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": 0.0, "min": -0.6835333324140973, "max": 0.4140235273277058, "count": 500 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": 0.0, "min": -12.729200005531311, "max": 7.038399964570999, "count": 500 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": 0.0, "min": -0.6835333324140973, "max": 0.4140235273277058, "count": 500 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": 0.0, "min": -12.729200005531311, "max": 7.038399964570999, "count": 500 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 500 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 500 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.01682371503363053, "min": 0.011035426127515771, "max": 0.024981034867232667, "count": 232 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.01682371503363053, "min": 0.011035426127515771, "max": 0.024981034867232667, "count": 232 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.00032613252939578765, "min": 1.1867353927404642e-06, "max": 0.02258039607355992, "count": 232 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.00032613252939578765, "min": 1.1867353927404642e-06, "max": 0.02258039607355992, "count": 232 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.00032702218062089135, "min": 9.515035074514344e-07, "max": 0.016307429557976625, "count": 232 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.00032702218062089135, "min": 9.515035074514344e-07, "max": 0.016307429557976625, "count": 232 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0010000000000000002, "min": 0.001, "max": 0.0010000000000000002, "count": 232 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0010000000000000002, "min": 0.001, "max": 0.0010000000000000002, "count": 232 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.2, "max": 0.20000000000000007, "count": 232 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.2, "max": 0.20000000000000007, "count": 232 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005, "max": 0.005000000000000001, "count": 232 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005, "max": 0.005000000000000001, "count": 232 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1707916938", "python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [GCC 11.4.0]", "command_line_arguments": "/mnt/c/Users/anom/Desktop/rl_course/rl_env/bin/mlagents-learn config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos.x86_64 --run-id=SoccerTwos --no-graphics --force", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.1.2+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1707944874" }, "total": 27936.812676874, "count": 1, "self": 10.032790425000712, "children": { "run_training.setup": { "total": 0.5509300390003773, "count": 1, "self": 0.5509300390003773 }, "TrainerController.start_learning": { "total": 27926.22895641, "count": 1, "self": 8.590567313713109, "children": { "TrainerController._reset_env": { "total": 12.140077391002706, "count": 25, "self": 12.140077391002706 }, "TrainerController.advance": { "total": 27905.09097910728, "count": 325478, "self": 7.641760156941018, "children": { "env_step": { "total": 9921.630150804955, "count": 325478, "self": 7656.037897949961, "children": { "SubprocessEnvManager._take_step": { "total": 2260.346262503399, "count": 325478, "self": 53.99732742945798, "children": { "TorchPolicy.evaluate": { "total": 2206.348935073941, "count": 646134, "self": 2206.348935073941 } } }, "workers": { "total": 5.245990351594628, "count": 325478, "self": 0.0, "children": { "worker_root": { "total": 27907.781506887415, "count": 325478, "is_parallel": true, "self": 21440.227096126288, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.013961601001028612, "count": 2, "is_parallel": true, "self": 0.01151730100173154, "children": { "_process_rank_one_or_two_observation": { "total": 0.0024442999992970726, "count": 8, "is_parallel": true, "self": 0.0024442999992970726 } } }, "UnityEnvironment.step": { "total": 0.035664302999975916, "count": 1, "is_parallel": true, "self": 0.0006882000016048551, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0008597999994890415, "count": 1, "is_parallel": true, "self": 0.0008597999994890415 }, "communicator.exchange": { "total": 0.03181540199966548, "count": 1, "is_parallel": true, "self": 0.03181540199966548 }, "steps_from_proto": { "total": 0.0023009009992165375, "count": 2, "is_parallel": true, "self": 0.0005528999981834204, "children": { "_process_rank_one_or_two_observation": { "total": 0.001748001001033117, "count": 8, "is_parallel": true, "self": 0.001748001001033117 } } } } } } }, "UnityEnvironment.step": { "total": 6467.50261765512, "count": 325477, "is_parallel": true, "self": 216.06494273081535, "children": { "UnityEnvironment._generate_step_input": { "total": 242.568812012727, "count": 325477, "is_parallel": true, "self": 242.568812012727 }, "communicator.exchange": { "total": 5300.24297349226, "count": 325477, "is_parallel": true, "self": 5300.24297349226 }, "steps_from_proto": { "total": 708.6258894193179, "count": 650954, "is_parallel": true, "self": 169.0170130383558, "children": { "_process_rank_one_or_two_observation": { "total": 539.6088763809621, "count": 2603816, "is_parallel": true, "self": 539.6088763809621 } } } } }, "steps_from_proto": { "total": 0.05179310600669851, "count": 48, "is_parallel": true, "self": 0.01254410402088979, "children": { "_process_rank_one_or_two_observation": { "total": 0.03924900198580872, "count": 192, "is_parallel": true, "self": 0.03924900198580872 } } } } } } } } }, "trainer_advance": { "total": 17975.819068145385, "count": 325478, "self": 61.6821880695461, "children": { "process_trajectory": { "total": 1634.5572613858694, "count": 325478, "self": 1631.2246501808704, "children": { "RLTrainer._checkpoint": { "total": 3.3326112049990115, "count": 10, "self": 3.3326112049990115 } } }, "_update_policy": { "total": 16279.57961868997, "count": 232, "self": 924.5769946849359, "children": { "TorchPOCAOptimizer.update": { "total": 15355.002624005034, "count": 6963, "self": 15355.002624005034 } } } } } } }, "trainer_threads": { "total": 1.2000018614344299e-06, "count": 1, "self": 1.2000018614344299e-06 }, "TrainerController._save_models": { "total": 0.40733139800067875, "count": 1, "self": 0.1052960000015446, "children": { "RLTrainer._checkpoint": { "total": 0.30203539799913415, "count": 1, "self": 0.30203539799913415 } } } } } } }