{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.2621898651123047, "min": 0.246557354927063, "max": 1.4669947624206543, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 7886.67138671875, "min": 7369.1064453125, "max": 44502.75390625, "count": 33 }, "Pyramids.Step.mean": { "value": 989920.0, "min": 29896.0, "max": 989920.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989920.0, "min": 29896.0, "max": 989920.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.6138461232185364, "min": -0.11208087205886841, "max": 0.6277032494544983, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 174.33230590820312, "min": -27.123571395874023, "max": 180.1508331298828, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.019913000985980034, "min": -0.04671953618526459, "max": 0.4691754877567291, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 5.655292510986328, "min": -13.174909591674805, "max": 111.19458770751953, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06912519675973804, "min": 0.06596817869395645, "max": 0.07385199389730888, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9677527546363326, "min": 0.5760884521703773, "max": 1.1077799084596334, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.01834283475328761, "min": 0.0014810885960932323, "max": 0.01834283475328761, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.2567996865460266, "min": 0.017773063153118787, "max": 0.25850673692755166, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.683868867314282e-06, "min": 7.683868867314282e-06, "max": 0.0002948463017179, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010757416414239996, "min": 0.00010757416414239996, "max": 0.003511239229587, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10256125714285716, "min": 0.10256125714285716, "max": 0.19828210000000002, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4358576000000003, "min": 1.4358576000000003, "max": 2.6177129000000003, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00026586958857142853, "min": 0.00026586958857142853, "max": 0.00982838179, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0037221742399999994, "min": 0.0037221742399999994, "max": 0.1170642587, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.01218847744166851, "min": 0.011894945986568928, "max": 0.40277358889579773, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.17063868045806885, "min": 0.16764679551124573, "max": 3.222188711166382, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 290.54455445544556, "min": 290.54455445544556, "max": 994.90625, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29345.0, "min": 16439.0, "max": 32927.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.6104118676468877, "min": -0.9333625526633114, "max": 1.6448195952118612, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 162.65159863233566, "min": -29.867601685225964, "max": 167.77159871160984, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.6104118676468877, "min": -0.9333625526633114, "max": 1.6448195952118612, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 162.65159863233566, "min": -29.867601685225964, "max": 167.77159871160984, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.036545257981391716, "min": 0.036545257981391716, "max": 7.6137446024838615, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.6910710561205633, "min": 3.5756970408256166, "max": 129.43365824222565, "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": "1684383165", "python_version": "3.10.11 (main, Apr 5 2023, 14:15:10) [GCC 9.4.0]", "command_line_arguments": "/usr/local/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+cu102", "numpy_version": "1.21.2", "end_time_seconds": "1684385421" }, "total": 2256.1180870870003, "count": 1, "self": 0.4878492110001389, "children": { "run_training.setup": { "total": 0.039724997000007534, "count": 1, "self": 0.039724997000007534 }, "TrainerController.start_learning": { "total": 2255.590512879, "count": 1, "self": 1.2930546019856592, "children": { "TrainerController._reset_env": { "total": 4.07260106800004, "count": 1, "self": 4.07260106800004 }, "TrainerController.advance": { "total": 2250.1342210540142, "count": 64128, "self": 1.3367333850292198, "children": { "env_step": { "total": 1605.526613015023, "count": 64128, "self": 1498.2535138689495, "children": { "SubprocessEnvManager._take_step": { "total": 106.47945661503866, "count": 64128, "self": 4.865504723041681, "children": { "TorchPolicy.evaluate": { "total": 101.61395189199698, "count": 62561, "self": 101.61395189199698 } } }, "workers": { "total": 0.7936425310347204, "count": 64128, "self": 0.0, "children": { "worker_root": { "total": 2250.626660233009, "count": 64128, "is_parallel": true, "self": 864.8810714050212, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005041886999947565, "count": 1, "is_parallel": true, "self": 0.003757292000045709, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012845949999018558, "count": 8, "is_parallel": true, "self": 0.0012845949999018558 } } }, "UnityEnvironment.step": { "total": 0.0477483789999269, "count": 1, "is_parallel": true, "self": 0.0005778020000661854, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005124239999076963, "count": 1, "is_parallel": true, "self": 0.0005124239999076963 }, "communicator.exchange": { "total": 0.04475132699997175, "count": 1, "is_parallel": true, "self": 0.04475132699997175 }, "steps_from_proto": { "total": 0.0019068259999812653, "count": 1, "is_parallel": true, "self": 0.00040562200013027905, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015012039998509863, "count": 8, "is_parallel": true, "self": 0.0015012039998509863 } } } } } } }, "UnityEnvironment.step": { "total": 1385.7455888279876, "count": 64127, "is_parallel": true, "self": 32.01565045000848, "children": { "UnityEnvironment._generate_step_input": { "total": 22.636981423033035, "count": 64127, "is_parallel": true, "self": 22.636981423033035 }, "communicator.exchange": { "total": 1233.5477101669417, "count": 64127, "is_parallel": true, "self": 1233.5477101669417 }, "steps_from_proto": { "total": 97.54524678800465, "count": 64127, "is_parallel": true, "self": 19.617723763113986, "children": { "_process_rank_one_or_two_observation": { "total": 77.92752302489066, "count": 513016, "is_parallel": true, "self": 77.92752302489066 } } } } } } } } } } }, "trainer_advance": { "total": 643.2708746539622, "count": 64128, "self": 2.6692506929808815, "children": { "process_trajectory": { "total": 109.17016456798092, "count": 64128, "self": 108.93566376898093, "children": { "RLTrainer._checkpoint": { "total": 0.23450079899998855, "count": 2, "self": 0.23450079899998855 } } }, "_update_policy": { "total": 531.4314593930004, "count": 457, "self": 345.32519100997536, "children": { "TorchPPOOptimizer.update": { "total": 186.10626838302505, "count": 22788, "self": 186.10626838302505 } } } } } } }, "trainer_threads": { "total": 1.2099999366910197e-06, "count": 1, "self": 1.2099999366910197e-06 }, "TrainerController._save_models": { "total": 0.09063494500014713, "count": 1, "self": 0.0013975880001453334, "children": { "RLTrainer._checkpoint": { "total": 0.0892373570000018, "count": 1, "self": 0.0892373570000018 } } } } } } }