| { |
| "name": "root", |
| "gauges": { |
| "SnowballTarget.Policy.Entropy.mean": { |
| "value": 0.8480338454246521, |
| "min": 0.8480338454246521, |
| "max": 0.8480338454246521, |
| "count": 1 |
| }, |
| "SnowballTarget.Policy.Entropy.sum": { |
| "value": 8656.7294921875, |
| "min": 8656.7294921875, |
| "max": 8656.7294921875, |
| "count": 1 |
| }, |
| "SnowballTarget.Step.mean": { |
| "value": 209936.0, |
| "min": 209936.0, |
| "max": 209936.0, |
| "count": 1 |
| }, |
| "SnowballTarget.Step.sum": { |
| "value": 209936.0, |
| "min": 209936.0, |
| "max": 209936.0, |
| "count": 1 |
| }, |
| "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": { |
| "value": 12.852452278137207, |
| "min": 12.852452278137207, |
| "max": 12.852452278137207, |
| "count": 1 |
| }, |
| "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { |
| "value": 2467.6708984375, |
| "min": 2467.6708984375, |
| "max": 2467.6708984375, |
| "count": 1 |
| }, |
| "SnowballTarget.Policy.CuriosityValueEstimate.mean": { |
| "value": -0.26364466547966003, |
| "min": -0.26364466547966003, |
| "max": -0.26364466547966003, |
| "count": 1 |
| }, |
| "SnowballTarget.Policy.CuriosityValueEstimate.sum": { |
| "value": -50.61977767944336, |
| "min": -50.61977767944336, |
| "max": -50.61977767944336, |
| "count": 1 |
| }, |
| "SnowballTarget.Losses.PolicyLoss.mean": { |
| "value": 0.07305969190729586, |
| "min": 0.07305969190729586, |
| "max": 0.07305969190729586, |
| "count": 1 |
| }, |
| "SnowballTarget.Losses.PolicyLoss.sum": { |
| "value": 0.29223876762918344, |
| "min": 0.29223876762918344, |
| "max": 0.29223876762918344, |
| "count": 1 |
| }, |
| "SnowballTarget.Losses.ValueLoss.mean": { |
| "value": 0.10914913157238534, |
| "min": 0.10914913157238534, |
| "max": 0.10914913157238534, |
| "count": 1 |
| }, |
| "SnowballTarget.Losses.ValueLoss.sum": { |
| "value": 0.4365965262895414, |
| "min": 0.4365965262895414, |
| "max": 0.4365965262895414, |
| "count": 1 |
| }, |
| "SnowballTarget.Policy.LearningRate.mean": { |
| "value": 0.00026917141027619996, |
| "min": 0.00026917141027619996, |
| "max": 0.00026917141027619996, |
| "count": 1 |
| }, |
| "SnowballTarget.Policy.LearningRate.sum": { |
| "value": 0.0010766856411047999, |
| "min": 0.0010766856411047999, |
| "max": 0.0010766856411047999, |
| "count": 1 |
| }, |
| "SnowballTarget.Policy.Epsilon.mean": { |
| "value": 0.1897238, |
| "min": 0.1897238, |
| "max": 0.1897238, |
| "count": 1 |
| }, |
| "SnowballTarget.Policy.Epsilon.sum": { |
| "value": 0.7588952, |
| "min": 0.7588952, |
| "max": 0.7588952, |
| "count": 1 |
| }, |
| "SnowballTarget.Policy.Beta.mean": { |
| "value": 0.00448721762, |
| "min": 0.00448721762, |
| "max": 0.00448721762, |
| "count": 1 |
| }, |
| "SnowballTarget.Policy.Beta.sum": { |
| "value": 0.01794887048, |
| "min": 0.01794887048, |
| "max": 0.01794887048, |
| "count": 1 |
| }, |
| "SnowballTarget.Losses.CuriosityForwardLoss.mean": { |
| "value": 0.30136276854603894, |
| "min": 0.30136276854603894, |
| "max": 0.30136276854603894, |
| "count": 1 |
| }, |
| "SnowballTarget.Losses.CuriosityForwardLoss.sum": { |
| "value": 1.2054510741841558, |
| "min": 1.2054510741841558, |
| "max": 1.2054510741841558, |
| "count": 1 |
| }, |
| "SnowballTarget.Losses.CuriosityInverseLoss.mean": { |
| "value": 1.2597437747115012, |
| "min": 1.2597437747115012, |
| "max": 1.2597437747115012, |
| "count": 1 |
| }, |
| "SnowballTarget.Losses.CuriosityInverseLoss.sum": { |
| "value": 5.038975098846005, |
| "min": 5.038975098846005, |
| "max": 5.038975098846005, |
| "count": 1 |
| }, |
| "SnowballTarget.Environment.EpisodeLength.mean": { |
| "value": 199.0, |
| "min": 199.0, |
| "max": 199.0, |
| "count": 1 |
| }, |
| "SnowballTarget.Environment.EpisodeLength.sum": { |
| "value": 8756.0, |
| "min": 8756.0, |
| "max": 8756.0, |
| "count": 1 |
| }, |
| "SnowballTarget.Environment.CumulativeReward.mean": { |
| "value": 25.34090909090909, |
| "min": 25.34090909090909, |
| "max": 25.34090909090909, |
| "count": 1 |
| }, |
| "SnowballTarget.Environment.CumulativeReward.sum": { |
| "value": 1115.0, |
| "min": 1115.0, |
| "max": 1115.0, |
| "count": 1 |
| }, |
| "SnowballTarget.Policy.ExtrinsicReward.mean": { |
| "value": 25.34090909090909, |
| "min": 25.34090909090909, |
| "max": 25.34090909090909, |
| "count": 1 |
| }, |
| "SnowballTarget.Policy.ExtrinsicReward.sum": { |
| "value": 1115.0, |
| "min": 1115.0, |
| "max": 1115.0, |
| "count": 1 |
| }, |
| "SnowballTarget.Policy.CuriosityReward.mean": { |
| "value": 1.6820884825323115, |
| "min": 1.6820884825323115, |
| "max": 1.6820884825323115, |
| "count": 1 |
| }, |
| "SnowballTarget.Policy.CuriosityReward.sum": { |
| "value": 74.01189323142171, |
| "min": 74.01189323142171, |
| "max": 74.01189323142171, |
| "count": 1 |
| }, |
| "SnowballTarget.IsTraining.mean": { |
| "value": 1.0, |
| "min": 1.0, |
| "max": 1.0, |
| "count": 1 |
| }, |
| "SnowballTarget.IsTraining.sum": { |
| "value": 1.0, |
| "min": 1.0, |
| "max": 1.0, |
| "count": 1 |
| } |
| }, |
| "metadata": { |
| "timer_format_version": "0.1.0", |
| "start_time_seconds": "1756802225", |
| "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]", |
| "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": "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": "1756802256" |
| }, |
| "total": 31.338433906999853, |
| "count": 1, |
| "self": 0.2968910239997058, |
| "children": { |
| "run_training.setup": { |
| "total": 0.02272881499993673, |
| "count": 1, |
| "self": 0.02272881499993673 |
| }, |
| "TrainerController.start_learning": { |
| "total": 31.01881406800021, |
| "count": 1, |
| "self": 0.027829952990032325, |
| "children": { |
| "TrainerController._reset_env": { |
| "total": 1.81535464100034, |
| "count": 1, |
| "self": 1.81535464100034 |
| }, |
| "TrainerController.advance": { |
| "total": 28.672942395009613, |
| "count": 1121, |
| "self": 0.02096365402076117, |
| "children": { |
| "env_step": { |
| "total": 18.185425256999224, |
| "count": 1121, |
| "self": 14.027776797000115, |
| "children": { |
| "SubprocessEnvManager._take_step": { |
| "total": 4.145900908994918, |
| "count": 1121, |
| "self": 0.07304100900091726, |
| "children": { |
| "TorchPolicy.evaluate": { |
| "total": 4.072859899994, |
| "count": 1121, |
| "self": 4.072859899994 |
| } |
| } |
| }, |
| "workers": { |
| "total": 0.011747551004191337, |
| "count": 1120, |
| "self": 0.0, |
| "children": { |
| "worker_root": { |
| "total": 30.443461416006812, |
| "count": 1120, |
| "is_parallel": true, |
| "self": 18.139483271002064, |
| "children": { |
| "run_training.setup": { |
| "total": 0.0, |
| "count": 0, |
| "is_parallel": true, |
| "self": 0.0, |
| "children": { |
| "steps_from_proto": { |
| "total": 0.0020680239999819605, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.0006200059992806928, |
| "children": { |
| "_process_rank_one_or_two_observation": { |
| "total": 0.0014480180007012677, |
| "count": 10, |
| "is_parallel": true, |
| "self": 0.0014480180007012677 |
| } |
| } |
| }, |
| "UnityEnvironment.step": { |
| "total": 0.03450543100007053, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.0005361779999475402, |
| "children": { |
| "UnityEnvironment._generate_step_input": { |
| "total": 0.0004192500000499422, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.0004192500000499422 |
| }, |
| "communicator.exchange": { |
| "total": 0.03177147599990349, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.03177147599990349 |
| }, |
| "steps_from_proto": { |
| "total": 0.0017785270001695608, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.00034121399903597194, |
| "children": { |
| "_process_rank_one_or_two_observation": { |
| "total": 0.0014373130011335888, |
| "count": 10, |
| "is_parallel": true, |
| "self": 0.0014373130011335888 |
| } |
| } |
| } |
| } |
| } |
| } |
| }, |
| "UnityEnvironment.step": { |
| "total": 12.303978145004749, |
| "count": 1119, |
| "is_parallel": true, |
| "self": 0.5808981090235648, |
| "children": { |
| "UnityEnvironment._generate_step_input": { |
| "total": 0.31569907898665406, |
| "count": 1119, |
| "is_parallel": true, |
| "self": 0.31569907898665406 |
| }, |
| "communicator.exchange": { |
| "total": 9.53153811498396, |
| "count": 1119, |
| "is_parallel": true, |
| "self": 9.53153811498396 |
| }, |
| "steps_from_proto": { |
| "total": 1.8758428420105702, |
| "count": 1119, |
| "is_parallel": true, |
| "self": 0.3269197190279556, |
| "children": { |
| "_process_rank_one_or_two_observation": { |
| "total": 1.5489231229826146, |
| "count": 11190, |
| "is_parallel": true, |
| "self": 1.5489231229826146 |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
| }, |
| "trainer_advance": { |
| "total": 10.466553483989628, |
| "count": 1120, |
| "self": 0.023239342988290446, |
| "children": { |
| "process_trajectory": { |
| "total": 2.119433444000606, |
| "count": 1120, |
| "self": 2.119433444000606 |
| }, |
| "_update_policy": { |
| "total": 8.323880697000732, |
| "count": 5, |
| "self": 4.957675552002456, |
| "children": { |
| "TorchPPOOptimizer.update": { |
| "total": 3.3662051449982755, |
| "count": 252, |
| "self": 3.3662051449982755 |
| } |
| } |
| } |
| } |
| } |
| } |
| }, |
| "trainer_threads": { |
| "total": 1.8000000636675395e-06, |
| "count": 1, |
| "self": 1.8000000636675395e-06 |
| }, |
| "TrainerController._save_models": { |
| "total": 0.5026852790001612, |
| "count": 1, |
| "self": 0.0018124950001947582, |
| "children": { |
| "RLTrainer._checkpoint": { |
| "total": 0.5008727839999665, |
| "count": 1, |
| "self": 0.5008727839999665 |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
