{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.6973702311515808, "min": 0.6904993057250977, "max": 2.8704049587249756, "count": 50 }, "SnowballTarget.Policy.Entropy.sum": { "value": 6689.17529296875, "min": 6685.970703125, "max": 29301.09375, "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": 13.421541213989258, "min": 0.03015226125717163, "max": 13.436004638671875, "count": 50 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2751.416015625, "min": 5.849538803100586, "max": 2752.867919921875, "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.Environment.CumulativeReward.mean": { "value": 26.2, "min": 2.909090909090909, "max": 26.666666666666668, "count": 50 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1441.0, "min": 128.0, "max": 1465.0, "count": 50 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 26.2, "min": 2.909090909090909, "max": 26.666666666666668, "count": 50 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1441.0, "min": 128.0, "max": 1465.0, "count": 50 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.0458764722102833, "min": 0.041454736376823245, "max": 0.05417047013921261, "count": 50 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.0917529444205666, "min": 0.08290947275364649, "max": 0.1600261076082996, "count": 50 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.17608630218926596, "min": 0.10103318186056819, "max": 0.2907617414504095, "count": 50 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.35217260437853193, "min": 0.20206636372113637, "max": 0.8722852243512285, "count": 50 }, "SnowballTarget.Policy.LearningRate.mean": { "value": 3.0528989824000053e-06, "min": 3.0528989824000053e-06, "max": 0.00029609280130239995, "count": 50 }, "SnowballTarget.Policy.LearningRate.sum": { "value": 6.105797964800011e-06, "min": 6.105797964800011e-06, "max": 0.0008367984210671999, "count": 50 }, "SnowballTarget.Policy.Epsilon.mean": { "value": 0.10101760000000001, "min": 0.10101760000000001, "max": 0.1986976, "count": 50 }, "SnowballTarget.Policy.Epsilon.sum": { "value": 0.20203520000000003, "min": 0.20203520000000003, "max": 0.5789328, "count": 50 }, "SnowballTarget.Policy.Beta.mean": { "value": 4.042624000000006e-05, "min": 4.042624000000006e-05, "max": 0.00296105824, "count": 50 }, "SnowballTarget.Policy.Beta.sum": { "value": 8.085248000000012e-05, "min": 8.085248000000012e-05, "max": 0.008370090719999999, "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": "1793139728", "python_version": "3.10.12 | packaged by conda-forge | (main, Jun 23 2023, 22:40:32) [GCC 12.3.0]", "command_line_arguments": "/content/miniforge3/envs/unity-mlagents/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics", "mlagents_version": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.8.0+cu128", "numpy_version": "1.23.5", "end_time_seconds": "1793140720" }, "total": 992.3626787339999, "count": 1, "self": 0.5367006460000994, "children": { "run_training.setup": { "total": 0.022844368999813014, "count": 1, "self": 0.022844368999813014 }, "TrainerController.start_learning": { "total": 991.803133719, "count": 1, "self": 0.8660418019389908, "children": { "TrainerController._reset_env": { "total": 3.178288736000013, "count": 1, "self": 3.178288736000013 }, "TrainerController.advance": { "total": 987.6820951540612, "count": 45464, "self": 0.9578047541167507, "children": { "env_step": { "total": 764.982479600973, "count": 45464, "self": 587.9907261079729, "children": { "SubprocessEnvManager._take_step": { "total": 176.46521113702602, "count": 45464, "self": 3.186533780051377, "children": { "TorchPolicy.evaluate": { "total": 173.27867735697464, "count": 45464, "self": 173.27867735697464 } } }, "workers": { "total": 0.5265423559740157, "count": 45464, "self": 0.0, "children": { "worker_root": { "total": 989.5410241790896, "count": 45464, "is_parallel": true, "self": 471.28527465513434, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005341273999874829, "count": 1, "is_parallel": true, "self": 0.003211501999885513, "children": { "_process_rank_one_or_two_observation": { "total": 0.002129771999989316, "count": 10, "is_parallel": true, "self": 0.002129771999989316 } } }, "UnityEnvironment.step": { "total": 0.039711036999960925, "count": 1, "is_parallel": true, "self": 0.0007282380001925048, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004290199999559263, "count": 1, "is_parallel": true, "self": 0.0004290199999559263 }, "communicator.exchange": { "total": 0.03647791399998823, "count": 1, "is_parallel": true, "self": 0.03647791399998823 }, "steps_from_proto": { "total": 0.0020758649998242618, "count": 1, "is_parallel": true, "self": 0.0004060869996465044, "children": { "_process_rank_one_or_two_observation": { "total": 0.0016697780001777573, "count": 10, "is_parallel": true, "self": 0.0016697780001777573 } } } } } } }, "UnityEnvironment.step": { "total": 518.2557495239553, "count": 45463, "is_parallel": true, "self": 26.2490457520762, "children": { "UnityEnvironment._generate_step_input": { "total": 13.690182933954475, "count": 45463, "is_parallel": true, "self": 13.690182933954475 }, "communicator.exchange": { "total": 392.3617733099627, "count": 45463, "is_parallel": true, "self": 392.3617733099627 }, "steps_from_proto": { "total": 85.9547475279619, "count": 45463, "is_parallel": true, "self": 15.173707373053276, "children": { "_process_rank_one_or_two_observation": { "total": 70.78104015490862, "count": 454630, "is_parallel": true, "self": 70.78104015490862 } } } } } } } } } } }, "trainer_advance": { "total": 221.74181079897153, "count": 45464, "self": 1.079637068923148, "children": { "process_trajectory": { "total": 58.47396752704935, "count": 45464, "self": 57.53050199705058, "children": { "RLTrainer._checkpoint": { "total": 0.9434655299987753, "count": 10, "self": 0.9434655299987753 } } }, "_update_policy": { "total": 162.18820620299903, "count": 113, "self": 88.53120770398709, "children": { "TorchPPOOptimizer.update": { "total": 73.65699849901193, "count": 5760, "self": 73.65699849901193 } } } } } } }, "trainer_threads": { "total": 9.260002116207033e-07, "count": 1, "self": 9.260002116207033e-07 }, "TrainerController._save_models": { "total": 0.07670710099955613, "count": 1, "self": 0.0007692780000070343, "children": { "RLTrainer._checkpoint": { "total": 0.0759378229995491, "count": 1, "self": 0.0759378229995491 } } } } } } }