{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.3679918944835663, "min": 0.3551021218299866, "max": 1.4462023973464966, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 11033.869140625, "min": 10670.1083984375, "max": 43871.99609375, "count": 33 }, "Pyramids.Step.mean": { "value": 989951.0, "min": 29952.0, "max": 989951.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989951.0, "min": 29952.0, "max": 989951.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.27651453018188477, "min": -0.09532951563596725, "max": 0.33998408913612366, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 69.95817565917969, "min": -22.97441291809082, "max": 89.75579833984375, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -0.039725832641124725, "min": -0.05147663503885269, "max": 0.21246053278446198, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -10.05063533782959, "min": -13.538354873657227, "max": 51.20298767089844, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06863575475950758, "min": 0.06420329417423568, "max": 0.07407966320404259, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9609005666331061, "min": 0.5185576424282982, "max": 1.0563603748268375, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.009475972343235434, "min": 0.001818657141099264, "max": 0.014369131123865465, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.13266361280529607, "min": 0.016367914269893376, "max": 0.215536966857982, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.761225984385714e-06, "min": 7.761225984385714e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.0001086571637814, "min": 0.0001086571637814, "max": 0.003758749047083699, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10258704285714286, "min": 0.10258704285714286, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4362186000000001, "min": 1.3886848, "max": 2.6529163000000002, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002684455814285715, "min": 0.0002684455814285715, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.003758238140000001, "min": 0.003758238140000001, "max": 0.12530633837, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.008830172009766102, "min": 0.008830172009766102, "max": 0.3411354124546051, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.12362240254878998, "min": 0.12362240254878998, "max": 2.3879477977752686, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 603.3125, "min": 503.44642857142856, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 28959.0, "min": 15984.0, "max": 33137.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 0.8548541309622427, "min": -1.0000000521540642, "max": 1.2712881096591384, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 41.03299828618765, "min": -29.948001705110073, "max": 75.00599846988916, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 0.8548541309622427, "min": -1.0000000521540642, "max": 1.2712881096591384, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 41.03299828618765, "min": -29.948001705110073, "max": 75.00599846988916, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.054995463272462075, "min": 0.0473928350766073, "max": 6.789634536486119, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 2.6397822370781796, "min": 2.6397822370781796, "max": 108.6341525837779, "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": "1658487033", "python_version": "3.8.10 (default, Jun 22 2022, 20:18:18) \n[GCC 9.4.0]", "command_line_arguments": "/home/xrh1/experiments/hf_deep_rl_course/hf_env/bin/mlagents-learn ./config/ppo/PyramidsRND.yaml --env=./trained-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids Training --no-graphics --force", "mlagents_version": "0.29.0.dev0", "mlagents_envs_version": "0.29.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.8.2+cu111", "numpy_version": "1.23.1", "end_time_seconds": "1658487929" }, "total": 895.6079949880004, "count": 1, "self": 0.21812786100053927, "children": { "run_training.setup": { "total": 0.04634729099780088, "count": 1, "self": 0.04634729099780088 }, "TrainerController.start_learning": { "total": 895.3435198360021, "count": 1, "self": 0.5447104507256881, "children": { "TrainerController._reset_env": { "total": 1.9903457530017477, "count": 1, "self": 1.9903457530017477 }, "TrainerController.advance": { "total": 892.7663146862687, "count": 63598, "self": 0.5678141857279115, "children": { "env_step": { "total": 554.7010283552081, "count": 63598, "self": 502.99913873546757, "children": { "SubprocessEnvManager._take_step": { "total": 51.328095543060044, "count": 63598, "self": 1.9043558816847508, "children": { "TorchPolicy.evaluate": { "total": 49.42373966137529, "count": 62572, "self": 16.666617698552727, "children": { "TorchPolicy.sample_actions": { "total": 32.757121962822566, "count": 62572, "self": 32.757121962822566 } } } } }, "workers": { "total": 0.3737940766804968, "count": 63598, "self": 0.0, "children": { "worker_root": { "total": 894.0539208223854, "count": 63598, "is_parallel": true, "self": 439.5817079125409, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0015668170017306693, "count": 1, "is_parallel": true, "self": 0.0004762860044138506, "children": { "_process_rank_one_or_two_observation": { "total": 0.0010905309973168187, "count": 8, "is_parallel": true, "self": 0.0010905309973168187 } } }, "UnityEnvironment.step": { "total": 0.02926428700448014, "count": 1, "is_parallel": true, "self": 0.0003408840057090856, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00035091400059172884, "count": 1, "is_parallel": true, "self": 0.00035091400059172884 }, "communicator.exchange": { "total": 0.027560167996853124, "count": 1, "is_parallel": true, "self": 0.027560167996853124 }, "steps_from_proto": { "total": 0.0010123210013261996, "count": 1, "is_parallel": true, "self": 0.00026250199880450964, "children": { "_process_rank_one_or_two_observation": { "total": 0.00074981900252169, "count": 8, "is_parallel": true, "self": 0.00074981900252169 } } } } } } }, "UnityEnvironment.step": { "total": 454.47221290984453, "count": 63597, "is_parallel": true, "self": 16.29652033486491, "children": { "UnityEnvironment._generate_step_input": { "total": 11.880322591561708, "count": 63597, "is_parallel": true, "self": 11.880322591561708 }, "communicator.exchange": { "total": 380.4310195336002, "count": 63597, "is_parallel": true, "self": 380.4310195336002 }, "steps_from_proto": { "total": 45.86435044981772, "count": 63597, "is_parallel": true, "self": 11.202646650388488, "children": { "_process_rank_one_or_two_observation": { "total": 34.66170379942923, "count": 508776, "is_parallel": true, "self": 34.66170379942923 } } } } } } } } } } }, "trainer_advance": { "total": 337.4974721453327, "count": 63598, "self": 0.8618434425952728, "children": { "process_trajectory": { "total": 70.42296819979674, "count": 63598, "self": 70.3119258187944, "children": { "RLTrainer._checkpoint": { "total": 0.11104238100233488, "count": 2, "self": 0.11104238100233488 } } }, "_update_policy": { "total": 266.2126605029407, "count": 455, "self": 78.96995272532513, "children": { "TorchPPOOptimizer.update": { "total": 187.24270777761558, "count": 22776, "self": 187.24270777761558 } } } } } } }, "trainer_threads": { "total": 5.600013537332416e-07, "count": 1, "self": 5.600013537332416e-07 }, "TrainerController._save_models": { "total": 0.042148386004555505, "count": 1, "self": 0.0005437060026451945, "children": { "RLTrainer._checkpoint": { "total": 0.04160468000191031, "count": 1, "self": 0.04160468000191031 } } } } } } }