{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.3135221004486084, "min": 0.3080785870552063, "max": 1.3124607801437378, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 9390.6142578125, "min": 9296.5791015625, "max": 39814.80859375, "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": 0.6107106804847717, "min": -0.08106255531311035, "max": 0.7531508803367615, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 172.2204132080078, "min": -19.617137908935547, "max": 219.92005920410156, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.004609628114849329, "min": 0.004609628114849329, "max": 0.798308789730072, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 1.299915075302124, "min": 1.299915075302124, "max": 189.19918823242188, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.0673396650423196, "min": 0.06628346351681273, "max": 0.0738899672235244, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9427553105924744, "min": 0.5037647476735934, "max": 1.07743569652381, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.015478121448333175, "min": 0.0009254999552633766, "max": 0.02462924714090282, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.21669370027666446, "min": 0.012031499418423896, "max": 0.21702290107564562, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.658304590121429e-06, "min": 7.658304590121429e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.0001072162642617, "min": 0.0001072162642617, "max": 0.0033710305763231994, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10255273571428572, "min": 0.10255273571428572, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4357383000000001, "min": 1.3886848, "max": 2.5724042000000003, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002650182978571429, "min": 0.0002650182978571429, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.003710256170000001, "min": 0.003710256170000001, "max": 0.11238531232, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.012394525110721588, "min": 0.012394525110721588, "max": 0.5195097923278809, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.17352335155010223, "min": 0.17352335155010223, "max": 3.636568546295166, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 318.8191489361702, "min": 268.8125, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29969.0, "min": 15984.0, "max": 33007.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.6173404060462688, "min": -1.0000000521540642, "max": 1.7313893662881008, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 152.02999816834927, "min": -30.69900171458721, "max": 195.64699839055538, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.6173404060462688, "min": -1.0000000521540642, "max": 1.7313893662881008, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 152.02999816834927, "min": -30.69900171458721, "max": 195.64699839055538, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.08165901292631268, "min": 0.07084223590801528, "max": 21.35120641812682, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 7.675947215073393, "min": 7.675947215073393, "max": 341.61930269002914, "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": "1655887485", "python_version": "3.8.13 (default, Mar 28 2022, 06:59:08) [MSC v.1916 64 bit (AMD64)]", "command_line_arguments": "C:\\Users\\simon\\Anaconda3\\envs\\rl\\Scripts\\mlagents-learn config/ppo/PyramidsRND.yaml --env=training-envs-executables/windows/Pyramids --run-id=First Training --no-graphics", "mlagents_version": "0.29.0.dev0", "mlagents_envs_version": "0.29.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.11.0+cpu", "numpy_version": "1.22.3", "end_time_seconds": "1655889610" }, "total": 2124.2172705, "count": 1, "self": 0.33972799999992276, "children": { "run_training.setup": { "total": 0.10456939999999992, "count": 1, "self": 0.10456939999999992 }, "TrainerController.start_learning": { "total": 2123.7729731, "count": 1, "self": 1.4972784000137835, "children": { "TrainerController._reset_env": { "total": 2.5432875000000004, "count": 1, "self": 2.5432875000000004 }, "TrainerController.advance": { "total": 2119.637074799986, "count": 63922, "self": 1.3389061000143556, "children": { "env_step": { "total": 1002.009181799981, "count": 63922, "self": 914.5827900999385, "children": { "SubprocessEnvManager._take_step": { "total": 86.43811320004502, "count": 63922, "self": 4.581756500062625, "children": { "TorchPolicy.evaluate": { "total": 81.8563566999824, "count": 62562, "self": 17.661204599972166, "children": { "TorchPolicy.sample_actions": { "total": 64.19515210001023, "count": 62562, "self": 64.19515210001023 } } } } }, "workers": { "total": 0.9882784999974925, "count": 63922, "self": 0.0, "children": { "worker_root": { "total": 2118.8259228000197, "count": 63922, "is_parallel": true, "self": 1317.0071946000226, "children": { "steps_from_proto": { "total": 0.003038200000000213, "count": 1, "is_parallel": true, "self": 0.000812000000000701, "children": { "_process_rank_one_or_two_observation": { "total": 0.002226199999999512, "count": 8, "is_parallel": true, "self": 0.002226199999999512 } } }, "UnityEnvironment.step": { "total": 801.8156899999972, "count": 63922, "is_parallel": true, "self": 24.276597200004858, "children": { "UnityEnvironment._generate_step_input": { "total": 22.603133900009503, "count": 63922, "is_parallel": true, "self": 22.603133900009503 }, "communicator.exchange": { "total": 684.1701527999991, "count": 63922, "is_parallel": true, "self": 684.1701527999991 }, "steps_from_proto": { "total": 70.76580609998366, "count": 63922, "is_parallel": true, "self": 16.251438199991085, "children": { "_process_rank_one_or_two_observation": { "total": 54.51436789999258, "count": 511376, "is_parallel": true, "self": 54.51436789999258 } } } } } } } } } } }, "trainer_advance": { "total": 1116.2889868999905, "count": 63922, "self": 2.6867007000005287, "children": { "process_trajectory": { "total": 271.42028409998926, "count": 63922, "self": 271.0934065999891, "children": { "RLTrainer._checkpoint": { "total": 0.32687750000013693, "count": 2, "self": 0.32687750000013693 } } }, "_update_policy": { "total": 842.1820021000008, "count": 451, "self": 279.3468746999954, "children": { "TorchPPOOptimizer.update": { "total": 562.8351274000054, "count": 22797, "self": 562.8351274000054 } } } } } } }, "trainer_threads": { "total": 8.000001798791345e-07, "count": 1, "self": 8.000001798791345e-07 }, "TrainerController._save_models": { "total": 0.09533160000000862, "count": 1, "self": 0.002389300000231742, "children": { "RLTrainer._checkpoint": { "total": 0.09294229999977688, "count": 1, "self": 0.09294229999977688 } } } } } } }