{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 2.7587201595306396, "min": 2.7587201595306396, "max": 2.8903114795684814, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 4127.04541015625, "min": 1845.368896484375, "max": 4362.23828125, "count": 20 }, "SnowballTarget.Step.mean": { "value": 19992.0, "min": 960.0, "max": 19992.0, "count": 20 }, "SnowballTarget.Step.sum": { "value": 19992.0, "min": 960.0, "max": 19992.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": { "value": 1.6563712358474731, "min": 0.08288861811161041, "max": 1.6563712358474731, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 43.065650939941406, "min": 1.2433292865753174, "max": 43.065650939941406, "count": 20 }, "SnowballTarget.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 20 }, "SnowballTarget.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 20 }, "SnowballTarget.Environment.EpisodeLength.mean": { "value": 199.0, "min": 199.0, "max": 199.0, "count": 9 }, "SnowballTarget.Environment.EpisodeLength.sum": { "value": 2189.0, "min": 2189.0, "max": 2189.0, "count": 9 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.06064499910822704, "min": 0.057470670223290866, "max": 0.07652621067530822, "count": 9 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.06064499910822704, "min": 0.057470670223290866, "max": 0.07652621067530822, "count": 9 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.26373226823760015, "min": 0.07282388303428888, "max": 0.26373226823760015, "count": 9 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.26373226823760015, "min": 0.07282388303428888, "max": 0.26373226823760015, "count": 9 }, "SnowballTarget.Policy.LearningRate.mean": { "value": 4.320098559999991e-06, "min": 4.320098559999991e-06, "max": 0.00026832001056, "count": 9 }, "SnowballTarget.Policy.LearningRate.sum": { "value": 4.320098559999991e-06, "min": 4.320098559999991e-06, "max": 0.00026832001056, "count": 9 }, "SnowballTarget.Policy.Epsilon.mean": { "value": 0.10144, "min": 0.10144, "max": 0.18944000000000003, "count": 9 }, "SnowballTarget.Policy.Epsilon.sum": { "value": 0.10144, "min": 0.10144, "max": 0.18944000000000003, "count": 9 }, "SnowballTarget.Policy.Beta.mean": { "value": 8.185599999999986e-05, "min": 8.185599999999986e-05, "max": 0.0044730559999999996, "count": 9 }, "SnowballTarget.Policy.Beta.sum": { "value": 8.185599999999986e-05, "min": 8.185599999999986e-05, "max": 0.0044730559999999996, "count": 9 }, "SnowballTarget.Environment.CumulativeReward.mean": { "value": 6.909090909090909, "min": 2.6363636363636362, "max": 6.909090909090909, "count": 10 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 76.0, "min": 4.0, "max": 76.0, "count": 10 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 6.909090909090909, "min": 2.6363636363636362, "max": 6.909090909090909, "count": 10 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 76.0, "min": 4.0, "max": 76.0, "count": 10 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1676054036", "python_version": "3.8.10 (default, Nov 14 2022, 12:59:47) \n[GCC 9.4.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics", "mlagents_version": "0.29.0.dev0", "mlagents_envs_version": "0.29.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.8.1+cu102", "numpy_version": "1.21.6", "end_time_seconds": "1676054092" }, "total": 55.975558224999986, "count": 1, "self": 0.4365402499998936, "children": { "run_training.setup": { "total": 0.10454671300010432, "count": 1, "self": 0.10454671300010432 }, "TrainerController.start_learning": { "total": 55.43447126199999, "count": 1, "self": 0.07366377799939983, "children": { "TrainerController._reset_env": { "total": 8.959619227000076, "count": 1, "self": 8.959619227000076 }, "TrainerController.advance": { "total": 46.28408045700053, "count": 1873, "self": 0.026462621000860054, "children": { "env_step": { "total": 46.25761783599967, "count": 1873, "self": 31.262310697998146, "children": { "SubprocessEnvManager._take_step": { "total": 14.969418161000021, "count": 1873, "self": 0.1441046259982386, "children": { "TorchPolicy.evaluate": { "total": 14.825313535001783, "count": 1873, "self": 3.1935467169997764, "children": { "TorchPolicy.sample_actions": { "total": 11.631766818002006, "count": 1873, "self": 11.631766818002006 } } } } }, "workers": { "total": 0.02588897700150028, "count": 1873, "self": 0.0, "children": { "worker_root": { "total": 55.232414649999555, "count": 1873, "is_parallel": true, "self": 31.093465439995953, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.013714885000013055, "count": 1, "is_parallel": true, "self": 0.0036529909999671872, "children": { "_process_rank_one_or_two_observation": { "total": 0.010061894000045868, "count": 10, "is_parallel": true, "self": 0.010061894000045868 } } }, "UnityEnvironment.step": { "total": 0.038140119999980016, "count": 1, "is_parallel": true, "self": 0.00047808199997234624, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00038489199994273804, "count": 1, "is_parallel": true, "self": 0.00038489199994273804 }, "communicator.exchange": { "total": 0.035358736000034696, "count": 1, "is_parallel": true, "self": 0.035358736000034696 }, "steps_from_proto": { "total": 0.001918410000030235, "count": 1, "is_parallel": true, "self": 0.00042287500025395275, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014955349997762823, "count": 10, "is_parallel": true, "self": 0.0014955349997762823 } } } } } } }, "UnityEnvironment.step": { "total": 24.138949210003602, "count": 1872, "is_parallel": true, "self": 0.9491290560048355, "children": { "UnityEnvironment._generate_step_input": { "total": 0.5206017379995274, "count": 1872, "is_parallel": true, "self": 0.5206017379995274 }, "communicator.exchange": { "total": 19.578648397000734, "count": 1872, "is_parallel": true, "self": 19.578648397000734 }, "steps_from_proto": { "total": 3.0905700189985055, "count": 1872, "is_parallel": true, "self": 0.653014852011097, "children": { "_process_rank_one_or_two_observation": { "total": 2.4375551669874085, "count": 18720, "is_parallel": true, "self": 2.4375551669874085 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00014877299997806404, "count": 1, "self": 0.00014877299997806404, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 45.949094345992535, "count": 43152, "is_parallel": true, "self": 1.077423755987752, "children": { "process_trajectory": { "total": 27.06517685200481, "count": 43152, "is_parallel": true, "self": 25.837488955004915, "children": { "RLTrainer._checkpoint": { "total": 1.2276878969998961, "count": 4, "is_parallel": true, "self": 1.2276878969998961 } } }, "_update_policy": { "total": 17.806493737999972, "count": 9, "is_parallel": true, "self": 6.079309558998034, "children": { "TorchPPOOptimizer.update": { "total": 11.727184179001938, "count": 456, "is_parallel": true, "self": 11.727184179001938 } } } } } } } } }, "TrainerController._save_models": { "total": 0.11695902700000715, "count": 1, "self": 0.000866671000039787, "children": { "RLTrainer._checkpoint": { "total": 0.11609235599996737, "count": 1, "self": 0.11609235599996737 } } } } } } }