{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.8627172708511353, "min": 0.8524813055992126, "max": 2.8850533962249756, "count": 50 }, "SnowballTarget.Policy.Entropy.sum": { "value": 8389.0625, "min": 8119.4716796875, "max": 29545.83203125, "count": 50 }, "SnowballTarget.Step.mean": { "value": 499976.0, "min": 9952.0, "max": 499976.0, "count": 50 }, "SnowballTarget.Step.sum": { "value": 499976.0, "min": 9952.0, "max": 499976.0, "count": 50 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": { "value": 13.11306095123291, "min": 0.2759779393672943, "max": 13.196749687194824, "count": 50 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2688.177490234375, "min": 53.53972244262695, "max": 2694.05126953125, "count": 50 }, "SnowballTarget.Environment.EpisodeLength.mean": { "value": 199.0, "min": 199.0, "max": 199.0, "count": 50 }, "SnowballTarget.Environment.EpisodeLength.sum": { "value": 10945.0, "min": 8756.0, "max": 10945.0, "count": 50 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.07394753073327308, "min": 0.061065039271717046, "max": 0.0755091441327286, "count": 50 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.3697376536663654, "min": 0.2463664399578656, "max": 0.377545720663643, "count": 50 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.2078031230790942, "min": 0.09713734716733954, "max": 0.2695045339710572, "count": 50 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 1.039015615395471, "min": 0.3885493886693582, "max": 1.347522669855286, "count": 50 }, "SnowballTarget.Policy.LearningRate.mean": { "value": 1.017698982400001e-06, "min": 1.017698982400001e-06, "max": 9.891760108239999e-05, "count": 50 }, "SnowballTarget.Policy.LearningRate.sum": { "value": 5.088494912000005e-06, "min": 5.088494912000005e-06, "max": 0.0004846880153120001, "count": 50 }, "SnowballTarget.Policy.Epsilon.mean": { "value": 0.09999999999999998, "min": 0.09999999999999998, "max": 0.09999999999999998, "count": 50 }, "SnowballTarget.Policy.Epsilon.sum": { "value": 0.4999999999999999, "min": 0.3999999999999999, "max": 0.4999999999999999, "count": 50 }, "SnowballTarget.Policy.Beta.mean": { "value": 6.0778240000000044e-05, "min": 6.0778240000000044e-05, "max": 0.00494598824, "count": 50 }, "SnowballTarget.Policy.Beta.sum": { "value": 0.0003038912000000002, "min": 0.0003038912000000002, "max": 0.0242359312, "count": 50 }, "SnowballTarget.Environment.CumulativeReward.mean": { "value": 25.4, "min": 2.8863636363636362, "max": 26.01818181818182, "count": 50 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1397.0, "min": 127.0, "max": 1431.0, "count": 50 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.4, "min": 2.8863636363636362, "max": 26.01818181818182, "count": 50 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1397.0, "min": 127.0, "max": 1431.0, "count": 50 }, "SnowballTarget.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 50 }, "SnowballTarget.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 50 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1695679755", "python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [GCC 11.4.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn /content/ml-agents/config/ppo/SnowballTarget.yaml --env=/content/training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics", "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": "1695681084" }, "total": 1329.170950608, "count": 1, "self": 0.4895465140000397, "children": { "run_training.setup": { "total": 0.047538376999909815, "count": 1, "self": 0.047538376999909815 }, "TrainerController.start_learning": { "total": 1328.6338657170002, "count": 1, "self": 1.581985888049303, "children": { "TrainerController._reset_env": { "total": 5.669187456999907, "count": 1, "self": 5.669187456999907 }, "TrainerController.advance": { "total": 1321.2220265949506, "count": 45485, "self": 0.8536482509919097, "children": { "env_step": { "total": 1320.3683783439587, "count": 45485, "self": 952.3454227859552, "children": { "SubprocessEnvManager._take_step": { "total": 367.1807587820233, "count": 45485, "self": 5.059029095002188, "children": { "TorchPolicy.evaluate": { "total": 362.1217296870211, "count": 45485, "self": 362.1217296870211 } } }, "workers": { "total": 0.8421967759802556, "count": 45485, "self": 0.0, "children": { "worker_root": { "total": 1324.1520868480773, "count": 45485, "is_parallel": true, "self": 617.6274106430028, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.006462588999966101, "count": 1, "is_parallel": true, "self": 0.004928837000079511, "children": { "_process_rank_one_or_two_observation": { "total": 0.00153375199988659, "count": 10, "is_parallel": true, "self": 0.00153375199988659 } } }, "UnityEnvironment.step": { "total": 0.08947068299994498, "count": 1, "is_parallel": true, "self": 0.0006374999998115527, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004998890001388645, "count": 1, "is_parallel": true, "self": 0.0004998890001388645 }, "communicator.exchange": { "total": 0.07538081699999566, "count": 1, "is_parallel": true, "self": 0.07538081699999566 }, "steps_from_proto": { "total": 0.012952476999998908, "count": 1, "is_parallel": true, "self": 0.00047811900026317744, "children": { "_process_rank_one_or_two_observation": { "total": 0.01247435799973573, "count": 10, "is_parallel": true, "self": 0.01247435799973573 } } } } } } }, "UnityEnvironment.step": { "total": 706.5246762050745, "count": 45484, "is_parallel": true, "self": 29.761946230092462, "children": { "UnityEnvironment._generate_step_input": { "total": 15.53466729000138, "count": 45484, "is_parallel": true, "self": 15.53466729000138 }, "communicator.exchange": { "total": 555.5564219840101, "count": 45484, "is_parallel": true, "self": 555.5564219840101 }, "steps_from_proto": { "total": 105.67164070097056, "count": 45484, "is_parallel": true, "self": 19.976381920026142, "children": { "_process_rank_one_or_two_observation": { "total": 85.69525878094441, "count": 454840, "is_parallel": true, "self": 85.69525878094441 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00014137100015432225, "count": 1, "self": 0.00014137100015432225, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 1309.95004040563, "count": 1235757, "is_parallel": true, "self": 30.082049291500653, "children": { "process_trajectory": { "total": 715.3998538361279, "count": 1235757, "is_parallel": true, "self": 712.6927167791277, "children": { "RLTrainer._checkpoint": { "total": 2.707137057000182, "count": 10, "is_parallel": true, "self": 2.707137057000182 } } }, "_update_policy": { "total": 564.4681372780014, "count": 227, "is_parallel": true, "self": 215.88860994198035, "children": { "TorchPPOOptimizer.update": { "total": 348.5795273360211, "count": 11574, "is_parallel": true, "self": 348.5795273360211 } } } } } } } } }, "TrainerController._save_models": { "total": 0.1605244060001496, "count": 1, "self": 0.0009059580002030998, "children": { "RLTrainer._checkpoint": { "total": 0.1596184479999465, "count": 1, "self": 0.1596184479999465 } } } } } } }