{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.9919294118881226, "min": 0.9919294118881226, "max": 2.8707079887390137, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 9492.7646484375, "min": 9492.7646484375, "max": 28588.173828125, "count": 20 }, "SnowballTarget.Step.mean": { "value": 199984.0, "min": 9952.0, "max": 199984.0, "count": 20 }, "SnowballTarget.Step.sum": { "value": 199984.0, "min": 9952.0, "max": 199984.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": { "value": 12.340689659118652, "min": 0.47483932971954346, "max": 12.340689659118652, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2406.4345703125, "min": 86.89559936523438, "max": 2466.556640625, "count": 20 }, "SnowballTarget.Environment.EpisodeLength.mean": { "value": 199.0, "min": 199.0, "max": 199.0, "count": 20 }, "SnowballTarget.Environment.EpisodeLength.sum": { "value": 8756.0, "min": 8756.0, "max": 10945.0, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.05968101909549624, "min": 0.05968101909549624, "max": 0.07545579751083506, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.23872407638198495, "min": 0.23872407638198495, "max": 0.3593986798186248, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.22023401453214533, "min": 0.11516788928180605, "max": 0.28779958897069385, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.8809360581285813, "min": 0.4606715571272242, "max": 1.3673392025863425, "count": 20 }, "SnowballTarget.Policy.LearningRate.mean": { "value": 7.0260976579999984e-06, "min": 7.0260976579999984e-06, "max": 0.000290826003058, "count": 20 }, "SnowballTarget.Policy.LearningRate.sum": { "value": 2.8104390631999994e-05, "min": 2.8104390631999994e-05, "max": 0.0013138800620399998, "count": 20 }, "SnowballTarget.Policy.Epsilon.mean": { "value": 0.10234199999999999, "min": 0.10234199999999999, "max": 0.196942, "count": 20 }, "SnowballTarget.Policy.Epsilon.sum": { "value": 0.40936799999999995, "min": 0.40936799999999995, "max": 0.93796, "count": 20 }, "SnowballTarget.Policy.Beta.mean": { "value": 0.0001268658, "min": 0.0001268658, "max": 0.004847405799999999, "count": 20 }, "SnowballTarget.Policy.Beta.sum": { "value": 0.0005074632, "min": 0.0005074632, "max": 0.021904204, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.mean": { "value": 25.272727272727273, "min": 3.340909090909091, "max": 25.272727272727273, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1112.0, "min": 147.0, "max": 1342.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.272727272727273, "min": 3.340909090909091, "max": 25.272727272727273, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1112.0, "min": 147.0, "max": 1342.0, "count": 20 }, "SnowballTarget.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 20 }, "SnowballTarget.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 20 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1683726385", "python_version": "3.10.11 (main, Apr 5 2023, 14:15:10) [GCC 9.4.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics --resume", "mlagents_version": "0.31.0.dev0", "mlagents_envs_version": "0.31.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.11.0+cu102", "numpy_version": "1.21.2", "end_time_seconds": "1683726840" }, "total": 454.631565686, "count": 1, "self": 0.3730786109999258, "children": { "run_training.setup": { "total": 0.03956130400001712, "count": 1, "self": 0.03956130400001712 }, "TrainerController.start_learning": { "total": 454.21892577100004, "count": 1, "self": 0.521140170005367, "children": { "TrainerController._reset_env": { "total": 4.3780131049999795, "count": 1, "self": 4.3780131049999795 }, "TrainerController.advance": { "total": 449.17362834799474, "count": 18160, "self": 0.25017312100254685, "children": { "env_step": { "total": 448.9234552269922, "count": 18160, "self": 330.764241203986, "children": { "SubprocessEnvManager._take_step": { "total": 117.91236443200958, "count": 18160, "self": 1.598348536009155, "children": { "TorchPolicy.evaluate": { "total": 116.31401589600043, "count": 18160, "self": 116.31401589600043 } } }, "workers": { "total": 0.24684959099661796, "count": 18160, "self": 0.0, "children": { "worker_root": { "total": 452.82743140800204, "count": 18160, "is_parallel": true, "self": 214.55674952600413, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0018757510000000366, "count": 1, "is_parallel": true, "self": 0.0005720659999894906, "children": { "_process_rank_one_or_two_observation": { "total": 0.001303685000010546, "count": 10, "is_parallel": true, "self": 0.001303685000010546 } } }, "UnityEnvironment.step": { "total": 0.09445674899998835, "count": 1, "is_parallel": true, "self": 0.000571453999981486, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004055910000033691, "count": 1, "is_parallel": true, "self": 0.0004055910000033691 }, "communicator.exchange": { "total": 0.0913653350000061, "count": 1, "is_parallel": true, "self": 0.0913653350000061 }, "steps_from_proto": { "total": 0.002114368999997396, "count": 1, "is_parallel": true, "self": 0.0004076920000386508, "children": { "_process_rank_one_or_two_observation": { "total": 0.001706676999958745, "count": 10, "is_parallel": true, "self": 0.001706676999958745 } } } } } } }, "UnityEnvironment.step": { "total": 238.27068188199792, "count": 18159, "is_parallel": true, "self": 9.351902168994712, "children": { "UnityEnvironment._generate_step_input": { "total": 5.04722082701187, "count": 18159, "is_parallel": true, "self": 5.04722082701187 }, "communicator.exchange": { "total": 191.8290114670009, "count": 18159, "is_parallel": true, "self": 191.8290114670009 }, "steps_from_proto": { "total": 32.04254741899044, "count": 18159, "is_parallel": true, "self": 6.083681431998656, "children": { "_process_rank_one_or_two_observation": { "total": 25.958865986991782, "count": 181590, "is_parallel": true, "self": 25.958865986991782 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00016835500002798653, "count": 1, "self": 0.00016835500002798653, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 445.9020511449775, "count": 388470, "is_parallel": true, "self": 9.028813983983582, "children": { "process_trajectory": { "total": 243.7722337399942, "count": 388470, "is_parallel": true, "self": 242.33055325399414, "children": { "RLTrainer._checkpoint": { "total": 1.4416804860000525, "count": 4, "is_parallel": true, "self": 1.4416804860000525 } } }, "_update_policy": { "total": 193.10100342099975, "count": 90, "is_parallel": true, "self": 77.21279202800221, "children": { "TorchPPOOptimizer.update": { "total": 115.88821139299753, "count": 4587, "is_parallel": true, "self": 115.88821139299753 } } } } } } } } }, "TrainerController._save_models": { "total": 0.14597579299993413, "count": 1, "self": 0.0017719989998568053, "children": { "RLTrainer._checkpoint": { "total": 0.14420379400007732, "count": 1, "self": 0.14420379400007732 } } } } } } }