{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.740727424621582, "min": 0.740727424621582, "max": 2.8576884269714355, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 7039.87353515625, "min": 7039.87353515625, "max": 29171.283203125, "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": 13.201457023620605, "min": 0.5019160509109497, "max": 13.20280933380127, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2574.2841796875, "min": 97.37171173095703, "max": 2693.373046875, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.06949370991844939, "min": 0.0625717716128337, "max": 0.07472474327637339, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.27797483967379755, "min": 0.2656722854538684, "max": 0.373623716381867, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.19351105519807804, "min": 0.15001390774862147, "max": 0.28017352579855453, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.7740442207923122, "min": 0.6000556309944859, "max": 1.301514879453416, "count": 20 }, "SnowballTarget.Policy.LearningRate.mean": { "value": 8.082097306000005e-06, "min": 8.082097306000005e-06, "max": 0.000291882002706, "count": 20 }, "SnowballTarget.Policy.LearningRate.sum": { "value": 3.232838922400002e-05, "min": 3.232838922400002e-05, "max": 0.00138516003828, "count": 20 }, "SnowballTarget.Policy.Epsilon.mean": { "value": 0.10269400000000001, "min": 0.10269400000000001, "max": 0.19729400000000002, "count": 20 }, "SnowballTarget.Policy.Epsilon.sum": { "value": 0.41077600000000003, "min": 0.41077600000000003, "max": 0.96172, "count": 20 }, "SnowballTarget.Policy.Beta.mean": { "value": 0.0001444306000000001, "min": 0.0001444306000000001, "max": 0.0048649706, "count": 20 }, "SnowballTarget.Policy.Beta.sum": { "value": 0.0005777224000000004, "min": 0.0005777224000000004, "max": 0.023089828, "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.Environment.CumulativeReward.mean": { "value": 26.045454545454547, "min": 4.090909090909091, "max": 26.21818181818182, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1146.0, "min": 180.0, "max": 1442.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 26.045454545454547, "min": 4.090909090909091, "max": 26.21818181818182, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1146.0, "min": 180.0, "max": 1442.0, "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": "1727016462", "python_version": "3.10.12 (main, Sep 11 2024, 15:47:36) [GCC 11.4.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics --force", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.4.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1727016923" }, "total": 461.0190675670001, "count": 1, "self": 0.42530702700014444, "children": { "run_training.setup": { "total": 0.05529367799999818, "count": 1, "self": 0.05529367799999818 }, "TrainerController.start_learning": { "total": 460.53846686199995, "count": 1, "self": 0.45735754694487696, "children": { "TrainerController._reset_env": { "total": 1.6850756689998434, "count": 1, "self": 1.6850756689998434 }, "TrainerController.advance": { "total": 458.30806842605557, "count": 18192, "self": 0.4363357000645465, "children": { "env_step": { "total": 326.14303362695773, "count": 18192, "self": 247.38400480094333, "children": { "SubprocessEnvManager._take_step": { "total": 78.49936821901474, "count": 18192, "self": 1.3843124120141965, "children": { "TorchPolicy.evaluate": { "total": 77.11505580700054, "count": 18192, "self": 77.11505580700054 } } }, "workers": { "total": 0.25966060699965965, "count": 18192, "self": 0.0, "children": { "worker_root": { "total": 459.02036584302664, "count": 18192, "is_parallel": true, "self": 244.07836390403713, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0022324210001443134, "count": 1, "is_parallel": true, "self": 0.0006497699996543815, "children": { "_process_rank_one_or_two_observation": { "total": 0.001582651000489932, "count": 10, "is_parallel": true, "self": 0.001582651000489932 } } }, "UnityEnvironment.step": { "total": 0.0394237019997945, "count": 1, "is_parallel": true, "self": 0.0007280959998752223, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00042390599992359057, "count": 1, "is_parallel": true, "self": 0.00042390599992359057 }, "communicator.exchange": { "total": 0.03628753299994969, "count": 1, "is_parallel": true, "self": 0.03628753299994969 }, "steps_from_proto": { "total": 0.001984167000046, "count": 1, "is_parallel": true, "self": 0.0003749839997908566, "children": { "_process_rank_one_or_two_observation": { "total": 0.0016091830002551433, "count": 10, "is_parallel": true, "self": 0.0016091830002551433 } } } } } } }, "UnityEnvironment.step": { "total": 214.9420019389895, "count": 18191, "is_parallel": true, "self": 10.470794916032446, "children": { "UnityEnvironment._generate_step_input": { "total": 5.514188113997761, "count": 18191, "is_parallel": true, "self": 5.514188113997761 }, "communicator.exchange": { "total": 166.12609647597515, "count": 18191, "is_parallel": true, "self": 166.12609647597515 }, "steps_from_proto": { "total": 32.83092243298415, "count": 18191, "is_parallel": true, "self": 6.126949395979864, "children": { "_process_rank_one_or_two_observation": { "total": 26.70397303700429, "count": 181910, "is_parallel": true, "self": 26.70397303700429 } } } } } } } } } } }, "trainer_advance": { "total": 131.7286990990333, "count": 18192, "self": 0.5708853820128752, "children": { "process_trajectory": { "total": 30.692450622021397, "count": 18192, "self": 26.773987253023506, "children": { "RLTrainer._checkpoint": { "total": 3.918463368997891, "count": 40, "self": 3.918463368997891 } } }, "_update_policy": { "total": 100.46536309499902, "count": 90, "self": 42.59210965298439, "children": { "TorchPPOOptimizer.update": { "total": 57.87325344201463, "count": 4587, "self": 57.87325344201463 } } } } } } }, "trainer_threads": { "total": 1.0799999472510535e-06, "count": 1, "self": 1.0799999472510535e-06 }, "TrainerController._save_models": { "total": 0.08796413999971264, "count": 1, "self": 0.0009226739998666744, "children": { "RLTrainer._checkpoint": { "total": 0.08704146599984597, "count": 1, "self": 0.08704146599984597 } } } } } } }