{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.48316624760627747, "min": 0.46158719062805176, "max": 1.536176323890686, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 14479.5263671875, "min": 13862.38671875, "max": 46601.4453125, "count": 33 }, "Pyramids.Step.mean": { "value": 989928.0, "min": 29952.0, "max": 989928.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989928.0, "min": 29952.0, "max": 989928.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.450664222240448, "min": -0.1778678447008133, "max": 0.5172435641288757, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 123.93266296386719, "min": -42.15467834472656, "max": 142.75921630859375, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.026660582050681114, "min": 0.008024522103369236, "max": 0.19899135828018188, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 7.331660270690918, "min": 2.014155149459839, "max": 47.75792694091797, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06939801706596174, "min": 0.0651353574775734, "max": 0.07292570924389823, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 1.040970255989426, "min": 0.4844879845816953, "max": 1.0619872919895559, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.017058044473459533, "min": 0.00022055281044107425, "max": 0.017058044473459533, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.255870667101893, "min": 0.0015438696730875198, "max": 0.255870667101893, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.555537481520004e-06, "min": 7.555537481520004e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00011333306222280007, "min": 0.00011333306222280007, "max": 0.0030221321926227, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10251848000000001, "min": 0.10251848000000001, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.5377772, "min": 1.327104, "max": 2.3595074, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002615961520000002, "min": 0.0002615961520000002, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.003923942280000003, "min": 0.003923942280000003, "max": 0.10076699226999998, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.011759220622479916, "min": 0.011397404596209526, "max": 0.30264565348625183, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.17638830840587616, "min": 0.15956366062164307, "max": 2.1185195446014404, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 391.44871794871796, "min": 364.7951807228916, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30533.0, "min": 15984.0, "max": 32590.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.4546666471048808, "min": -1.0000000521540642, "max": 1.5628867231040116, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 113.4639984741807, "min": -32.000001668930054, "max": 129.71959801763296, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.4546666471048808, "min": -1.0000000521540642, "max": 1.5628867231040116, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 113.4639984741807, "min": -32.000001668930054, "max": 129.71959801763296, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.04763805696692986, "min": 0.043909484965176916, "max": 5.7657929877750576, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.7157684434205294, "min": 3.5283234392118175, "max": 92.25268780440092, "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": "1679485093", "python_version": "3.9.16 (main, Mar 8 2023, 14:00:05) \n[GCC 11.2.0]", "command_line_arguments": "/home/aarriandiaga/anaconda3/envs/rl/bin/mlagents-learn ./config/ppo/PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids Training --no-graphics", "mlagents_version": "0.31.0.dev0", "mlagents_envs_version": "0.31.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.11.0", "numpy_version": "1.21.2", "end_time_seconds": "1679487331" }, "total": 2237.689590997994, "count": 1, "self": 0.5768418349325657, "children": { "run_training.setup": { "total": 0.013511080294847488, "count": 1, "self": 0.013511080294847488 }, "TrainerController.start_learning": { "total": 2237.0992380827665, "count": 1, "self": 1.7175821512937546, "children": { "TrainerController._reset_env": { "total": 7.363319288939238, "count": 1, "self": 7.363319288939238 }, "TrainerController.advance": { "total": 2227.8724238947034, "count": 63576, "self": 1.5774700865149498, "children": { "env_step": { "total": 1559.9401970617473, "count": 63576, "self": 1424.7582129463553, "children": { "SubprocessEnvManager._take_step": { "total": 134.15467617288232, "count": 63576, "self": 6.101937722414732, "children": { "TorchPolicy.evaluate": { "total": 128.0527384504676, "count": 62576, "self": 128.0527384504676 } } }, "workers": { "total": 1.0273079425096512, "count": 63576, "self": 0.0, "children": { "worker_root": { "total": 2233.3103634379804, "count": 63576, "is_parallel": true, "self": 929.4069621525705, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0027832016348838806, "count": 1, "is_parallel": true, "self": 0.0007379241287708282, "children": { "_process_rank_one_or_two_observation": { "total": 0.0020452775061130524, "count": 8, "is_parallel": true, "self": 0.0020452775061130524 } } }, "UnityEnvironment.step": { "total": 0.052181269973516464, "count": 1, "is_parallel": true, "self": 0.0005972497165203094, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005339980125427246, "count": 1, "is_parallel": true, "self": 0.0005339980125427246 }, "communicator.exchange": { "total": 0.04904080554842949, "count": 1, "is_parallel": true, "self": 0.04904080554842949 }, "steps_from_proto": { "total": 0.002009216696023941, "count": 1, "is_parallel": true, "self": 0.0004444420337677002, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015647746622562408, "count": 8, "is_parallel": true, "self": 0.0015647746622562408 } } } } } } }, "UnityEnvironment.step": { "total": 1303.90340128541, "count": 63575, "is_parallel": true, "self": 37.10331588983536, "children": { "UnityEnvironment._generate_step_input": { "total": 23.461123514920473, "count": 63575, "is_parallel": true, "self": 23.461123514920473 }, "communicator.exchange": { "total": 1130.824714563787, "count": 63575, "is_parallel": true, "self": 1130.824714563787 }, "steps_from_proto": { "total": 112.51424731686711, "count": 63575, "is_parallel": true, "self": 24.162193592637777, "children": { "_process_rank_one_or_two_observation": { "total": 88.35205372422934, "count": 508600, "is_parallel": true, "self": 88.35205372422934 } } } } } } } } } } }, "trainer_advance": { "total": 666.3547567464411, "count": 63576, "self": 3.2264714054763317, "children": { "process_trajectory": { "total": 107.26819369569421, "count": 63576, "self": 106.99215091392398, "children": { "RLTrainer._checkpoint": { "total": 0.27604278177022934, "count": 2, "self": 0.27604278177022934 } } }, "_update_policy": { "total": 555.8600916452706, "count": 428, "self": 315.781774636358, "children": { "TorchPPOOptimizer.update": { "total": 240.07831700891256, "count": 22863, "self": 240.07831700891256 } } } } } } }, "trainer_threads": { "total": 1.4863908290863037e-06, "count": 1, "self": 1.4863908290863037e-06 }, "TrainerController._save_models": { "total": 0.14591126143932343, "count": 1, "self": 0.0020628757774829865, "children": { "RLTrainer._checkpoint": { "total": 0.14384838566184044, "count": 1, "self": 0.14384838566184044 } } } } } } }