{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 3.2107036113739014, "min": 3.2107036113739014, "max": 3.2957074642181396, "count": 54 }, "SoccerTwos.Policy.Entropy.sum": { "value": 57022.09765625, "min": 19751.228515625, "max": 120480.046875, "count": 54 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 820.0, "min": 410.0833333333333, "max": 999.0, "count": 54 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19680.0, "min": 17484.0, "max": 23316.0, "count": 54 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1194.4402875724832, "min": 1191.8185477132163, "max": 1202.0502547782216, "count": 48 }, "SoccerTwos.Self-play.ELO.sum": { "value": 4777.761150289933, "min": 2386.682498380749, "max": 16738.525213557245, "count": 48 }, "SoccerTwos.Step.mean": { "value": 539736.0, "min": 9722.0, "max": 539736.0, "count": 54 }, "SoccerTwos.Step.sum": { "value": 539736.0, "min": 9722.0, "max": 539736.0, "count": 54 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": -0.016038794070482254, "min": -0.028663326054811478, "max": 0.01893448457121849, "count": 54 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": -0.208504319190979, "min": -0.43301811814308167, "max": 0.28401726484298706, "count": 54 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": -0.015257940627634525, "min": -0.0349409244954586, "max": 0.018840912729501724, "count": 54 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": -0.19835323095321655, "min": -0.5032390356063843, "max": 0.2825426161289215, "count": 54 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 54 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 54 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": -0.253753845508282, "min": -0.46153846153846156, "max": 0.37597333590189613, "count": 54 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": -3.298799991607666, "min": -9.589199990034103, "max": 5.639600038528442, "count": 54 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": -0.253753845508282, "min": -0.46153846153846156, "max": 0.37597333590189613, "count": 54 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": -3.298799991607666, "min": -9.589199990034103, "max": 5.639600038528442, "count": 54 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 54 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 54 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.018719479351178354, "min": 0.011478485410043504, "max": 0.021412606455851347, "count": 25 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.018719479351178354, "min": 0.011478485410043504, "max": 0.021412606455851347, "count": 25 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.0013482887239661067, "min": 0.0012590042082592846, "max": 0.004628484478841225, "count": 25 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.0013482887239661067, "min": 0.0012590042082592846, "max": 0.004628484478841225, "count": 25 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.0015571090955442438, "min": 0.0012690392807902147, "max": 0.0047715426655486224, "count": 25 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.0015571090955442438, "min": 0.0012690392807902147, "max": 0.0047715426655486224, "count": 25 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 25 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 25 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 25 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 25 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 25 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 25 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1682521439", "python_version": "3.9.12 (main, Jun 1 2022, 11:38:51) \n[GCC 7.5.0]", "command_line_arguments": "/home/osman/.pyenv/versions/miniconda3-4.7.12/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": "1682525292" }, "total": 3853.2143541509995, "count": 1, "self": 0.03964080599871522, "children": { "run_training.setup": { "total": 0.011409361999540124, "count": 1, "self": 0.011409361999540124 }, "TrainerController.start_learning": { "total": 3853.1633039830012, "count": 1, "self": 0.8838827939034672, "children": { "TrainerController._reset_env": { "total": 2.1896473490014614, "count": 3, "self": 2.1896473490014614 }, "TrainerController.advance": { "total": 3849.8151345830956, "count": 35469, "self": 1.012086826023733, "children": { "env_step": { "total": 3524.0637932190184, "count": 35469, "self": 3366.3506852638566, "children": { "SubprocessEnvManager._take_step": { "total": 157.15537886607672, "count": 35469, "self": 6.24865723907169, "children": { "TorchPolicy.evaluate": { "total": 150.90672162700503, "count": 70422, "self": 150.90672162700503 } } }, "workers": { "total": 0.5577290890851145, "count": 35468, "self": 0.0, "children": { "worker_root": { "total": 3851.248489515987, "count": 35468, "is_parallel": true, "self": 586.9425321369217, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.002904982999098138, "count": 2, "is_parallel": true, "self": 0.000577157998122857, "children": { "_process_rank_one_or_two_observation": { "total": 0.002327825000975281, "count": 8, "is_parallel": true, "self": 0.002327825000975281 } } }, "UnityEnvironment.step": { "total": 0.12336154600052396, "count": 1, "is_parallel": true, "self": 0.00018118299885827582, "children": { "UnityEnvironment._generate_step_input": { "total": 0.002515493000828428, "count": 1, "is_parallel": true, "self": 0.002515493000828428 }, "communicator.exchange": { "total": 0.1184253510000417, "count": 1, "is_parallel": true, "self": 0.1184253510000417 }, "steps_from_proto": { "total": 0.0022395190007955534, "count": 2, "is_parallel": true, "self": 0.000321391002216842, "children": { "_process_rank_one_or_two_observation": { "total": 0.0019181279985787114, "count": 8, "is_parallel": true, "self": 0.0019181279985787114 } } } } } } }, "UnityEnvironment.step": { "total": 3264.3009966850623, "count": 35467, "is_parallel": true, "self": 9.9563358037758, "children": { "UnityEnvironment._generate_step_input": { "total": 60.41453447101594, "count": 35467, "is_parallel": true, "self": 60.41453447101594 }, "communicator.exchange": { "total": 3081.7995622021717, "count": 35467, "is_parallel": true, "self": 3081.7995622021717 }, "steps_from_proto": { "total": 112.1305642080988, "count": 70934, "is_parallel": true, "self": 16.36381647961207, "children": { "_process_rank_one_or_two_observation": { "total": 95.76674772848673, "count": 283736, "is_parallel": true, "self": 95.76674772848673 } } } } }, "steps_from_proto": { "total": 0.004960694002875243, "count": 4, "is_parallel": true, "self": 0.0007037500072328839, "children": { "_process_rank_one_or_two_observation": { "total": 0.004256943995642359, "count": 16, "is_parallel": true, "self": 0.004256943995642359 } } } } } } } } }, "trainer_advance": { "total": 324.7392545380535, "count": 35468, "self": 5.901465543018276, "children": { "process_trajectory": { "total": 59.90979997703835, "count": 35468, "self": 59.71050950603785, "children": { "RLTrainer._checkpoint": { "total": 0.19929047100049502, "count": 1, "self": 0.19929047100049502 } } }, "_update_policy": { "total": 258.9279890179969, "count": 25, "self": 73.02800088002914, "children": { "TorchPOCAOptimizer.update": { "total": 185.89998813796774, "count": 750, "self": 185.89998813796774 } } } } } } }, "trainer_threads": { "total": 2.2120002540759742e-06, "count": 1, "self": 2.2120002540759742e-06 }, "TrainerController._save_models": { "total": 0.27463704500041786, "count": 1, "self": 0.0014027090001036413, "children": { "RLTrainer._checkpoint": { "total": 0.2732343360003142, "count": 1, "self": 0.2732343360003142 } } } } } } }