| { |
| "name": "root", |
| "gauges": { |
| "Pyramids.Policy.Entropy.mean": { |
| "value": 0.11755502969026566, |
| "min": 0.10810098797082901, |
| "max": 1.486702799797058, |
| "count": 100 |
| }, |
| "Pyramids.Policy.Entropy.sum": { |
| "value": 3530.41259765625, |
| "min": 3232.65185546875, |
| "max": 45100.6171875, |
| "count": 100 |
| }, |
| "Pyramids.Step.mean": { |
| "value": 2999972.0, |
| "min": 29952.0, |
| "max": 2999972.0, |
| "count": 100 |
| }, |
| "Pyramids.Step.sum": { |
| "value": 2999972.0, |
| "min": 29952.0, |
| "max": 2999972.0, |
| "count": 100 |
| }, |
| "Pyramids.Policy.ExtrinsicValueEstimate.mean": { |
| "value": 0.7537398934364319, |
| "min": -0.18945033848285675, |
| "max": 0.8447432518005371, |
| "count": 100 |
| }, |
| "Pyramids.Policy.ExtrinsicValueEstimate.sum": { |
| "value": 227.62945556640625, |
| "min": -44.89973068237305, |
| "max": 253.4229736328125, |
| "count": 100 |
| }, |
| "Pyramids.Policy.RndValueEstimate.mean": { |
| "value": 0.019560201093554497, |
| "min": -0.03305143862962723, |
| "max": 0.3967272937297821, |
| "count": 100 |
| }, |
| "Pyramids.Policy.RndValueEstimate.sum": { |
| "value": 5.9071807861328125, |
| "min": -8.791682243347168, |
| "max": 94.02436828613281, |
| "count": 100 |
| }, |
| "Pyramids.Losses.PolicyLoss.mean": { |
| "value": 0.06471489507696658, |
| "min": 0.06420220529322423, |
| "max": 0.07530123800668162, |
| "count": 100 |
| }, |
| "Pyramids.Losses.PolicyLoss.sum": { |
| "value": 0.9060085310775321, |
| "min": 0.45217751185095273, |
| "max": 1.0853217355073794, |
| "count": 100 |
| }, |
| "Pyramids.Losses.ValueLoss.mean": { |
| "value": 0.0154226954840678, |
| "min": 0.0011369459943238647, |
| "max": 0.0171538870380674, |
| "count": 100 |
| }, |
| "Pyramids.Losses.ValueLoss.sum": { |
| "value": 0.2159177367769492, |
| "min": 0.010416567921483561, |
| "max": 0.257308305571011, |
| "count": 100 |
| }, |
| "Pyramids.Policy.LearningRate.mean": { |
| "value": 1.4905995031666675e-06, |
| "min": 1.4905995031666675e-06, |
| "max": 0.00029838354339596195, |
| "count": 100 |
| }, |
| "Pyramids.Policy.LearningRate.sum": { |
| "value": 2.0868393044333344e-05, |
| "min": 2.0868393044333344e-05, |
| "max": 0.0039827257724248, |
| "count": 100 |
| }, |
| "Pyramids.Policy.Epsilon.mean": { |
| "value": 0.10049683333333337, |
| "min": 0.10049683333333337, |
| "max": 0.19946118095238097, |
| "count": 100 |
| }, |
| "Pyramids.Policy.Epsilon.sum": { |
| "value": 1.4069556666666672, |
| "min": 1.3897045333333333, |
| "max": 2.8275752, |
| "count": 100 |
| }, |
| "Pyramids.Policy.Beta.mean": { |
| "value": 5.9633650000000035e-05, |
| "min": 5.9633650000000035e-05, |
| "max": 0.009946171977142856, |
| "count": 100 |
| }, |
| "Pyramids.Policy.Beta.sum": { |
| "value": 0.0008348711000000005, |
| "min": 0.0008348711000000005, |
| "max": 0.13277476248, |
| "count": 100 |
| }, |
| "Pyramids.Losses.RNDLoss.mean": { |
| "value": 0.006948373280465603, |
| "min": 0.006521920207887888, |
| "max": 0.44204825162887573, |
| "count": 100 |
| }, |
| "Pyramids.Losses.RNDLoss.sum": { |
| "value": 0.09727722406387329, |
| "min": 0.09130688011646271, |
| "max": 3.0943377017974854, |
| "count": 100 |
| }, |
| "Pyramids.Environment.EpisodeLength.mean": { |
| "value": 213.57462686567163, |
| "min": 206.86896551724138, |
| "max": 999.0, |
| "count": 100 |
| }, |
| "Pyramids.Environment.EpisodeLength.sum": { |
| "value": 28619.0, |
| "min": 15984.0, |
| "max": 32435.0, |
| "count": 100 |
| }, |
| "Pyramids.Environment.CumulativeReward.mean": { |
| "value": 1.7576444341076745, |
| "min": -1.0000000521540642, |
| "max": 1.7655351597687294, |
| "count": 100 |
| }, |
| "Pyramids.Environment.CumulativeReward.sum": { |
| "value": 237.28199860453606, |
| "min": -32.000001668930054, |
| "max": 256.00259816646576, |
| "count": 100 |
| }, |
| "Pyramids.Policy.ExtrinsicReward.mean": { |
| "value": 1.7576444341076745, |
| "min": -1.0000000521540642, |
| "max": 1.7655351597687294, |
| "count": 100 |
| }, |
| "Pyramids.Policy.ExtrinsicReward.sum": { |
| "value": 237.28199860453606, |
| "min": -32.000001668930054, |
| "max": 256.00259816646576, |
| "count": 100 |
| }, |
| "Pyramids.Policy.RndReward.mean": { |
| "value": 0.015607645939841557, |
| "min": 0.015607645939841557, |
| "max": 8.621653052046895, |
| "count": 100 |
| }, |
| "Pyramids.Policy.RndReward.sum": { |
| "value": 2.10703220187861, |
| "min": 2.0431639682028617, |
| "max": 137.94644883275032, |
| "count": 100 |
| }, |
| "Pyramids.IsTraining.mean": { |
| "value": 1.0, |
| "min": 1.0, |
| "max": 1.0, |
| "count": 100 |
| }, |
| "Pyramids.IsTraining.sum": { |
| "value": 1.0, |
| "min": 1.0, |
| "max": 1.0, |
| "count": 100 |
| } |
| }, |
| "metadata": { |
| "timer_format_version": "0.1.0", |
| "start_time_seconds": "1726328377", |
| "python_version": "3.10.12 (main, Mar 22 2024, 16:50:05) [GCC 11.4.0]", |
| "command_line_arguments": "/usr/local/bin/mlagents-learn /content/ml-agents/config/ppo/PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids Training --no-graphics", |
| "mlagents_version": "1.1.0.dev0", |
| "mlagents_envs_version": "1.1.0.dev0", |
| "communication_protocol_version": "1.5.0", |
| "pytorch_version": "2.3.0+cu121", |
| "numpy_version": "1.23.5", |
| "end_time_seconds": "1726332768" |
| }, |
| "total": 4391.207541147999, |
| "count": 1, |
| "self": 0.22025725299954502, |
| "children": { |
| "run_training.setup": { |
| "total": 0.03210915500039846, |
| "count": 1, |
| "self": 0.03210915500039846 |
| }, |
| "TrainerController.start_learning": { |
| "total": 4390.955174739999, |
| "count": 1, |
| "self": 2.7080107448600756, |
| "children": { |
| "TrainerController._reset_env": { |
| "total": 1.669521910000185, |
| "count": 1, |
| "self": 1.669521910000185 |
| }, |
| "TrainerController.advance": { |
| "total": 4386.521012173137, |
| "count": 195010, |
| "self": 2.8681896765983765, |
| "children": { |
| "env_step": { |
| "total": 2764.3965646409497, |
| "count": 195010, |
| "self": 2209.081024445035, |
| "children": { |
| "SubprocessEnvManager._take_step": { |
| "total": 553.526167332032, |
| "count": 195010, |
| "self": 8.190482780295497, |
| "children": { |
| "TorchPolicy.evaluate": { |
| "total": 545.3356845517364, |
| "count": 187558, |
| "self": 545.3356845517364 |
| } |
| } |
| }, |
| "workers": { |
| "total": 1.789372863882818, |
| "count": 195010, |
| "self": 0.0, |
| "children": { |
| "worker_root": { |
| "total": 4384.395946466193, |
| "count": 195010, |
| "is_parallel": true, |
| "self": 2360.08428768823, |
| "children": { |
| "run_training.setup": { |
| "total": 0.0, |
| "count": 0, |
| "is_parallel": true, |
| "self": 0.0, |
| "children": { |
| "steps_from_proto": { |
| "total": 0.0015632619997631991, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.0008985529993879027, |
| "children": { |
| "_process_rank_one_or_two_observation": { |
| "total": 0.0006647090003752965, |
| "count": 8, |
| "is_parallel": true, |
| "self": 0.0006647090003752965 |
| } |
| } |
| }, |
| "UnityEnvironment.step": { |
| "total": 0.024180029000490322, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.00021059900063846726, |
| "children": { |
| "UnityEnvironment._generate_step_input": { |
| "total": 0.0001585609998073778, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.0001585609998073778 |
| }, |
| "communicator.exchange": { |
| "total": 0.023315075999562396, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.023315075999562396 |
| }, |
| "steps_from_proto": { |
| "total": 0.000495793000482081, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.00012675499965553172, |
| "children": { |
| "_process_rank_one_or_two_observation": { |
| "total": 0.00036903800082654925, |
| "count": 8, |
| "is_parallel": true, |
| "self": 0.00036903800082654925 |
| } |
| } |
| } |
| } |
| } |
| } |
| }, |
| "UnityEnvironment.step": { |
| "total": 2024.3116587779632, |
| "count": 195009, |
| "is_parallel": true, |
| "self": 34.34818906841792, |
| "children": { |
| "UnityEnvironment._generate_step_input": { |
| "total": 20.75457554170862, |
| "count": 195009, |
| "is_parallel": true, |
| "self": 20.75457554170862 |
| }, |
| "communicator.exchange": { |
| "total": 1884.2381930600504, |
| "count": 195009, |
| "is_parallel": true, |
| "self": 1884.2381930600504 |
| }, |
| "steps_from_proto": { |
| "total": 84.97070110778623, |
| "count": 195009, |
| "is_parallel": true, |
| "self": 20.90425948745542, |
| "children": { |
| "_process_rank_one_or_two_observation": { |
| "total": 64.0664416203308, |
| "count": 1560072, |
| "is_parallel": true, |
| "self": 64.0664416203308 |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
| }, |
| "trainer_advance": { |
| "total": 1619.256257855589, |
| "count": 195010, |
| "self": 5.424056455792197, |
| "children": { |
| "process_trajectory": { |
| "total": 293.6851525217953, |
| "count": 195010, |
| "self": 293.3578862687964, |
| "children": { |
| "RLTrainer._checkpoint": { |
| "total": 0.32726625299892476, |
| "count": 6, |
| "self": 0.32726625299892476 |
| } |
| } |
| }, |
| "_update_policy": { |
| "total": 1320.1470488780014, |
| "count": 1399, |
| "self": 608.414413393999, |
| "children": { |
| "TorchPPOOptimizer.update": { |
| "total": 711.7326354840025, |
| "count": 68355, |
| "self": 711.7326354840025 |
| } |
| } |
| } |
| } |
| } |
| } |
| }, |
| "trainer_threads": { |
| "total": 5.470010364660993e-07, |
| "count": 1, |
| "self": 5.470010364660993e-07 |
| }, |
| "TrainerController._save_models": { |
| "total": 0.0566293650008447, |
| "count": 1, |
| "self": 0.0005830139998579398, |
| "children": { |
| "RLTrainer._checkpoint": { |
| "total": 0.05604635100098676, |
| "count": 1, |
| "self": 0.05604635100098676 |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
