| { | |
| "name": "root", | |
| "gauges": { | |
| "Pyramids.Policy.Entropy.mean": { | |
| "value": 0.6532114744186401, | |
| "min": 0.6368648409843445, | |
| "max": 1.5197917222976685, | |
| "count": 33 | |
| }, | |
| "Pyramids.Policy.Entropy.sum": { | |
| "value": 19920.337890625, | |
| "min": 19054.99609375, | |
| "max": 46104.40234375, | |
| "count": 33 | |
| }, | |
| "Pyramids.Step.mean": { | |
| "value": 989943.0, | |
| "min": 29952.0, | |
| "max": 989943.0, | |
| "count": 33 | |
| }, | |
| "Pyramids.Step.sum": { | |
| "value": 989943.0, | |
| "min": 29952.0, | |
| "max": 989943.0, | |
| "count": 33 | |
| }, | |
| "Pyramids.Policy.ExtrinsicValueEstimate.mean": { | |
| "value": 0.3444861173629761, | |
| "min": -0.09679435193538666, | |
| "max": 0.4225064218044281, | |
| "count": 33 | |
| }, | |
| "Pyramids.Policy.ExtrinsicValueEstimate.sum": { | |
| "value": 90.59984588623047, | |
| "min": -22.940261840820312, | |
| "max": 114.49923706054688, | |
| "count": 33 | |
| }, | |
| "Pyramids.Policy.RndValueEstimate.mean": { | |
| "value": 0.6313345432281494, | |
| "min": -0.6745277643203735, | |
| "max": 0.6313345432281494, | |
| "count": 33 | |
| }, | |
| "Pyramids.Policy.RndValueEstimate.sum": { | |
| "value": 166.04098510742188, | |
| "min": -182.79702758789062, | |
| "max": 166.04098510742188, | |
| "count": 33 | |
| }, | |
| "Pyramids.Losses.PolicyLoss.mean": { | |
| "value": 0.07015644304019154, | |
| "min": 0.06346873553921063, | |
| "max": 0.07376255009037451, | |
| "count": 33 | |
| }, | |
| "Pyramids.Losses.PolicyLoss.sum": { | |
| "value": 0.9821902025626816, | |
| "min": 0.4835693312339865, | |
| "max": 1.0955869665214424, | |
| "count": 33 | |
| }, | |
| "Pyramids.Losses.ValueLoss.mean": { | |
| "value": 0.12520877534102293, | |
| "min": 0.000257511392466923, | |
| "max": 0.12520877534102293, | |
| "count": 33 | |
| }, | |
| "Pyramids.Losses.ValueLoss.sum": { | |
| "value": 1.752922854774321, | |
| "min": 0.003605159494536922, | |
| "max": 1.752922854774321, | |
| "count": 33 | |
| }, | |
| "Pyramids.Policy.LearningRate.mean": { | |
| "value": 7.265090435478572e-06, | |
| "min": 7.265090435478572e-06, | |
| "max": 0.00029515063018788575, | |
| "count": 33 | |
| }, | |
| "Pyramids.Policy.LearningRate.sum": { | |
| "value": 0.00010171126609670002, | |
| "min": 0.00010171126609670002, | |
| "max": 0.0035078348307217987, | |
| "count": 33 | |
| }, | |
| "Pyramids.Policy.Epsilon.mean": { | |
| "value": 0.1024216642857143, | |
| "min": 0.1024216642857143, | |
| "max": 0.19838354285714285, | |
| "count": 33 | |
| }, | |
| "Pyramids.Policy.Epsilon.sum": { | |
| "value": 1.4339033, | |
| "min": 1.3886848, | |
| "max": 2.5692782, | |
| "count": 33 | |
| }, | |
| "Pyramids.Policy.Beta.mean": { | |
| "value": 0.0002519242621428572, | |
| "min": 0.0002519242621428572, | |
| "max": 0.00983851593142857, | |
| "count": 33 | |
| }, | |
| "Pyramids.Policy.Beta.sum": { | |
| "value": 0.003526939670000001, | |
| "min": 0.003526939670000001, | |
| "max": 0.11695089218, | |
| "count": 33 | |
| }, | |
| "Pyramids.Losses.RNDLoss.mean": { | |
| "value": 0.010300911962985992, | |
| "min": 0.010300911962985992, | |
| "max": 0.47040826082229614, | |
| "count": 33 | |
| }, | |
| "Pyramids.Losses.RNDLoss.sum": { | |
| "value": 0.1442127674818039, | |
| "min": 0.1442127674818039, | |
| "max": 3.2928578853607178, | |
| "count": 33 | |
| }, | |
| "Pyramids.Environment.EpisodeLength.mean": { | |
| "value": 486.21875, | |
| "min": 417.9032258064516, | |
| "max": 999.0, | |
| "count": 33 | |
| }, | |
| "Pyramids.Environment.EpisodeLength.sum": { | |
| "value": 31118.0, | |
| "min": 15984.0, | |
| "max": 33306.0, | |
| "count": 33 | |
| }, | |
| "Pyramids.Environment.CumulativeReward.mean": { | |
| "value": 1.2357599658461718, | |
| "min": -1.0000000521540642, | |
| "max": 1.4852903037061613, | |
| "count": 33 | |
| }, | |
| "Pyramids.Environment.CumulativeReward.sum": { | |
| "value": 80.32439778000116, | |
| "min": -29.847001530230045, | |
| "max": 94.68799851834774, | |
| "count": 33 | |
| }, | |
| "Pyramids.Policy.ExtrinsicReward.mean": { | |
| "value": 1.2357599658461718, | |
| "min": -1.0000000521540642, | |
| "max": 1.4852903037061613, | |
| "count": 33 | |
| }, | |
| "Pyramids.Policy.ExtrinsicReward.sum": { | |
| "value": 80.32439778000116, | |
| "min": -29.847001530230045, | |
| "max": 94.68799851834774, | |
| "count": 33 | |
| }, | |
| "Pyramids.Policy.RndReward.mean": { | |
| "value": 0.05197611933735271, | |
| "min": 0.04757005864408829, | |
| "max": 9.749240828678012, | |
| "count": 33 | |
| }, | |
| "Pyramids.Policy.RndReward.sum": { | |
| "value": 3.378447756927926, | |
| "min": 2.9493436359334737, | |
| "max": 155.9878532588482, | |
| "count": 33 | |
| }, | |
| "Pyramids.IsTraining.mean": { | |
| "value": 1.0, | |
| "min": 1.0, | |
| "max": 1.0, | |
| "count": 33 | |
| }, | |
| "Pyramids.IsTraining.sum": { | |
| "value": 1.0, | |
| "min": 1.0, | |
| "max": 1.0, | |
| "count": 33 | |
| } | |
| }, | |
| "metadata": { | |
| "timer_format_version": "0.1.0", | |
| "start_time_seconds": "1724767650", | |
| "python_version": "3.10.12 (main, Jul 29 2024, 16:56:48) [GCC 11.4.0]", | |
| "command_line_arguments": "/usr/local/bin/mlagents-learn /content/ml-agents/config/ppo/PyramidsRND.yaml --env=/content/training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids Training --no-graphics", | |
| "mlagents_version": "1.0.0", | |
| "mlagents_envs_version": "1.0.0", | |
| "communication_protocol_version": "1.5.0", | |
| "pytorch_version": "2.4.0+cu121", | |
| "numpy_version": "1.21.2", | |
| "end_time_seconds": "1724769618" | |
| }, | |
| "total": 1967.9082074530002, | |
| "count": 1, | |
| "self": 0.44080519399994955, | |
| "children": { | |
| "run_training.setup": { | |
| "total": 0.04658625199999733, | |
| "count": 1, | |
| "self": 0.04658625199999733 | |
| }, | |
| "TrainerController.start_learning": { | |
| "total": 1967.4208160070002, | |
| "count": 1, | |
| "self": 1.1306049239656204, | |
| "children": { | |
| "TrainerController._reset_env": { | |
| "total": 1.4842024600002333, | |
| "count": 1, | |
| "self": 1.4842024600002333 | |
| }, | |
| "TrainerController.advance": { | |
| "total": 1964.7203205380347, | |
| "count": 63424, | |
| "self": 1.2110444460095096, | |
| "children": { | |
| "env_step": { | |
| "total": 1341.8071175200266, | |
| "count": 63424, | |
| "self": 1227.0697119661327, | |
| "children": { | |
| "SubprocessEnvManager._take_step": { | |
| "total": 114.03951276197677, | |
| "count": 63424, | |
| "self": 4.330421416053468, | |
| "children": { | |
| "TorchPolicy.evaluate": { | |
| "total": 109.7090913459233, | |
| "count": 62565, | |
| "self": 109.7090913459233 | |
| } | |
| } | |
| }, | |
| "workers": { | |
| "total": 0.6978927919171838, | |
| "count": 63424, | |
| "self": 0.0, | |
| "children": { | |
| "worker_root": { | |
| "total": 1962.923946409962, | |
| "count": 63424, | |
| "is_parallel": true, | |
| "self": 836.8594917269074, | |
| "children": { | |
| "run_training.setup": { | |
| "total": 0.0, | |
| "count": 0, | |
| "is_parallel": true, | |
| "self": 0.0, | |
| "children": { | |
| "steps_from_proto": { | |
| "total": 0.0020315689998824382, | |
| "count": 1, | |
| "is_parallel": true, | |
| "self": 0.0006712430008519732, | |
| "children": { | |
| "_process_rank_one_or_two_observation": { | |
| "total": 0.001360325999030465, | |
| "count": 8, | |
| "is_parallel": true, | |
| "self": 0.001360325999030465 | |
| } | |
| } | |
| }, | |
| "UnityEnvironment.step": { | |
| "total": 0.04768276999993759, | |
| "count": 1, | |
| "is_parallel": true, | |
| "self": 0.0005286299997351307, | |
| "children": { | |
| "UnityEnvironment._generate_step_input": { | |
| "total": 0.0004970889999640349, | |
| "count": 1, | |
| "is_parallel": true, | |
| "self": 0.0004970889999640349 | |
| }, | |
| "communicator.exchange": { | |
| "total": 0.044758701999853656, | |
| "count": 1, | |
| "is_parallel": true, | |
| "self": 0.044758701999853656 | |
| }, | |
| "steps_from_proto": { | |
| "total": 0.0018983490003847692, | |
| "count": 1, | |
| "is_parallel": true, | |
| "self": 0.000371741000435577, | |
| "children": { | |
| "_process_rank_one_or_two_observation": { | |
| "total": 0.0015266079999491922, | |
| "count": 8, | |
| "is_parallel": true, | |
| "self": 0.0015266079999491922 | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| }, | |
| "UnityEnvironment.step": { | |
| "total": 1126.0644546830545, | |
| "count": 63423, | |
| "is_parallel": true, | |
| "self": 32.85578042297493, | |
| "children": { | |
| "UnityEnvironment._generate_step_input": { | |
| "total": 23.558216275981977, | |
| "count": 63423, | |
| "is_parallel": true, | |
| "self": 23.558216275981977 | |
| }, | |
| "communicator.exchange": { | |
| "total": 965.6920719660775, | |
| "count": 63423, | |
| "is_parallel": true, | |
| "self": 965.6920719660775 | |
| }, | |
| "steps_from_proto": { | |
| "total": 103.95838601802006, | |
| "count": 63423, | |
| "is_parallel": true, | |
| "self": 19.999649715838586, | |
| "children": { | |
| "_process_rank_one_or_two_observation": { | |
| "total": 83.95873630218148, | |
| "count": 507384, | |
| "is_parallel": true, | |
| "self": 83.95873630218148 | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| }, | |
| "trainer_advance": { | |
| "total": 621.7021585719986, | |
| "count": 63424, | |
| "self": 2.0394762390210417, | |
| "children": { | |
| "process_trajectory": { | |
| "total": 109.83486069597666, | |
| "count": 63424, | |
| "self": 109.65843226897687, | |
| "children": { | |
| "RLTrainer._checkpoint": { | |
| "total": 0.17642842699979155, | |
| "count": 2, | |
| "self": 0.17642842699979155 | |
| } | |
| } | |
| }, | |
| "_update_policy": { | |
| "total": 509.82782163700085, | |
| "count": 446, | |
| "self": 323.5116371209788, | |
| "children": { | |
| "TorchPPOOptimizer.update": { | |
| "total": 186.31618451602208, | |
| "count": 22800, | |
| "self": 186.31618451602208 | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| }, | |
| "trainer_threads": { | |
| "total": 1.5460000213352032e-06, | |
| "count": 1, | |
| "self": 1.5460000213352032e-06 | |
| }, | |
| "TrainerController._save_models": { | |
| "total": 0.08568653899965284, | |
| "count": 1, | |
| "self": 0.0014232719995561638, | |
| "children": { | |
| "RLTrainer._checkpoint": { | |
| "total": 0.08426326700009668, | |
| "count": 1, | |
| "self": 0.08426326700009668 | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } |