\ud48d\ubd80\ud55c \ubb38\uc11c\ud654:<\/strong> \ud29c\ud1a0\ub9ac\uc5bc\uacfc \uc608\uc81c\ub97c \ud1b5\ud55c \uc815\ubcf4 \uc81c\uacf5\uc774 \uc798 \ub418\uc5b4 \uc788\uc2b5\ub2c8\ub2e4.<\/li>\n<\/ul>\n2.3 \uc608\uc81c<\/h3>\n
Stable Baselines3\ub97c \uc0ac\uc6a9\ud558\uc5ec \ud658\uacbd\uc5d0\uc11c \uc5d0\uc774\uc804\ud2b8\ub97c \ud559\uc2b5\ud558\ub294 \uac04\ub2e8\ud55c \uc608\uc81c\ub97c \ubcf4\uaca0\uc2b5\ub2c8\ub2e4. \uc544\ub798 \ucf54\ub4dc\ub294 OpenAI\uc758 Gym \ud658\uacbd\uc744 \uc0ac\uc6a9\ud558\uc5ec PPO \uc54c\uace0\ub9ac\uc998\uc744 \uc801\uc6a9\ud569\ub2c8\ub2e4.<\/p>\n
import gym\nfrom stable_baselines3 import PPO\n\n# \ud658\uacbd \uc0dd\uc131\nenv = gym.make('CartPole-v1')\n\n# \ubaa8\ub378 \uc0dd\uc131\nmodel = PPO('MlpPolicy', env, verbose=1)\n\n# \ubaa8\ub378 \ud559\uc2b5\nmodel.learn(total_timesteps=10000)\n\n# \ud559\uc2b5 \ud6c4 \ud3c9\uac00\nobs = env.reset()\nfor _ in range(1000):\n action, _states = model.predict(obs)\n obs, rewards, done, info = env.step(action)\n if done:\n obs = env.reset()\nenv.close()<\/code><\/pre>\n3. RLlib<\/h2>\n3.1 \uac1c\uc694<\/h3>\n
RLlib\ub294 Ray \ud504\ub808\uc784\uc6cc\ud06c\uc758 \uc77c\ubd80\ubd84\uc73c\ub85c, \ub300\uaddc\ubaa8 \ubd84\uc0b0 \uac15\ud654\ud559\uc2b5\uc744 \uc704\ud55c \ub77c\uc774\ube0c\ub7ec\ub9ac\uc785\ub2c8\ub2e4. diversos \uc54c\uace0\ub9ac\uc998\uacfc \ucee4\uc2a4\ud130\ub9c8\uc774\uc9d5 \uae30\ub2a5\uc744 \uc81c\uacf5\ud569\ub2c8\ub2e4. \ub300\uaddc\ubaa8 \ubd84\uc0b0 \ucc98\ub9ac\uc640 \uac15\ub825\ud55c \uc131\ub2a5 \ub355\ubd84\uc5d0 \uc5f0\uad6c \ubc0f \uc0c1\uc5c5\uc801 \ud658\uacbd\uc5d0\uc11c \uad11\ubc94\uc704\ud558\uac8c \uc0ac\uc6a9\ub418\uace0 \uc788\uc2b5\ub2c8\ub2e4.<\/p>\n
3.2 \ud2b9\uc9d5<\/h3>\n
RLlib\uc758 \uc8fc\uc694 \ud2b9\uc9d5\uc740 \ub2e4\uc74c\uacfc \uac19\uc2b5\ub2c8\ub2e4:<\/p>\n
\n- \ubd84\uc0b0 \ucc98\ub9ac:<\/strong> \ud074\ub7ec\uc2a4\ud130\uc5d0\uc11c\uc758 \uc2e4\ud589\uc744 \uc9c0\uc6d0\ud558\uba70 \uc27d\uac8c \uc2a4\ucf00\uc77c\ub9c1\uc774 \uac00\ub2a5\ud569\ub2c8\ub2e4.<\/li>\n
- \ub2e4\uc591\ud55c \uc54c\uace0\ub9ac\uc998:<\/strong> A3C, DDPG, PPO \ub4f1 \ub2e4\uc591\ud55c \uc54c\uace0\ub9ac\uc998\uc744 \uc9c0\uc6d0\ud569\ub2c8\ub2e4.<\/li>\n
- \uc720\uc5f0\uc131:<\/strong> \uc0ac\uc6a9\uc790 \uc815\uc758 \uc54c\uace0\ub9ac\uc998\uacfc \uc815\ucc45\uc744 \uc190\uc27d\uac8c \uad6c\ud604\ud560 \uc218 \uc788\uc2b5\ub2c8\ub2e4.<\/li>\n<\/ul>\n
3.3 \uc608\uc81c<\/h3>\n
\ub2e4\uc74c\uc740 RLlib\ub97c \uc0ac\uc6a9\ud558\uc5ec PPO \uc54c\uace0\ub9ac\uc998\uc744 \ud1b5\ud574 \uce74\ud2b8\ud3f4 \ud658\uacbd\uc5d0\uc11c \uc5d0\uc774\uc804\ud2b8\ub97c \ud559\uc2b5\ud558\ub294 \uc608\uc81c\uc785\ub2c8\ub2e4.<\/p>\n
import gym\nfrom ray import tune\nfrom ray.rllib.agents import ppo\n\n# \ud658\uacbd \uc815\uc758\nconfig = {\n \"env\": \"CartPole-v0\",\n \"num_workers\": 1,\n}\n\n# \ud2b8\ub808\uc774\ub2dd\nanalysis = tune.run(ppo.PPOTrainer, config=config, stop={\"training_iteration\": 10})\n\n# \ucd5c\uc801\uc758 \uc815\ucc45 \uc774\uc6a9\ud558\uae30\ntrainer = ppo.PPOTrainer(config=config)\ntrainer.restore(analysis.best_checkpoint) # \ucd5c\uc801\uc758 \uccb4\ud06c\ud3ec\uc778\ud2b8 \ubcf5\uad6c\n<\/code><\/pre>\n4. TensorFlow Agents<\/h2>\n4.1 \uac1c\uc694<\/h3>\n
TensorFlow Agents\ub294 \uad6c\uae00\uc5d0\uc11c \uac1c\ubc1c\ud55c \uac15\ud654\ud559\uc2b5 \ub77c\uc774\ube0c\ub7ec\ub9ac\ub85c, TensorFlow\uc758 \uac15\ub825\ud55c \uae30\ub2a5\uc744 \ud65c\uc6a9\ud558\uc5ec \uc54c\uace0\ub9ac\uc998\uc744 \uac1c\ubc1c\ud560 \uc218 \uc788\ub3c4\ub85d \ub3d5\uc2b5\ub2c8\ub2e4. \ub2e4\uc591\ud55c \uac15\ud654\ud559\uc2b5 \uc54c\uace0\ub9ac\uc998\uc744 \uc9c0\uc6d0\ud558\uba70, \ud2b9\ud788 \uadf8\ub798\ub514\uc5b8\ud2b8 \uae30\ubc18\uc758 \ud559\uc2b5\uc744 \ucd5c\uc801\ud654\ud558\ub294 \ub370 \uc911\uc810\uc744 \ub450\uace0 \uc788\uc2b5\ub2c8\ub2e4.<\/p>\n
4.2 \ud2b9\uc9d5<\/h3>\n
TensorFlow Agents\uc758 \uc8fc\uc694 \ud2b9\uc9d5\uc740 \ub2e4\uc74c\uacfc \uac19\uc2b5\ub2c8\ub2e4:<\/p>\n
\n- \ubaa8\ub4c8\ud654:<\/strong> \ub2e4\uc591\ud55c \uad6c\uc131 \uc694\uc18c\uc640 \ubaa8\ub4c8\uc774 \uc798 \ub098\ub204\uc5b4\uc838 \uc788\uc5b4 \uc0ac\uc6a9\uc790 \uc815\uc758\uac00 \uc6a9\uc774\ud569\ub2c8\ub2e4.<\/li>\n
- \ucd5c\uc2e0 \uc5f0\uad6c \ud1b5\ud569:<\/strong> \ucd5c\uc2e0 RL \uc54c\uace0\ub9ac\uc998\uc744 \uc27d\uac8c \uc0ac\uc6a9\ud560 \uc218 \uc788\ub3c4\ub85d \uad6c\ud604\ub418\uc5b4 \uc788\uc2b5\ub2c8\ub2e4.<\/li>\n
- TENSORFLOW \ud1b5\ud569:<\/strong> TensorFlow\uc758 \ud30c\uc6cc\ud480\ud55c \uae30\ub2a5\uc744 \ud65c\uc6a9\ud55c \ud559\uc2b5 \ubc0f \ucd5c\uc801\ud654\uac00 \uac00\ub2a5\ud569\ub2c8\ub2e4.<\/li>\n<\/ul>\n
4.3 \uc608\uc81c<\/h3>\n
\ub2e4\uc74c \uc608\uc81c\ub294 TensorFlow Agents\ub97c \uc0ac\uc6a9\ud558\uc5ec CartPole \ud658\uacbd\uc5d0\uc11c DQN \uc54c\uace0\ub9ac\uc998\uc73c\ub85c \uc5d0\uc774\uc804\ud2b8\ub97c \ud559\uc2b5\ud558\ub294 \uc608\uc785\ub2c8\ub2e4.<\/p>\n
import tensorflow as tf\nfrom tf_agents.agents.dqn import dqn_agent\nfrom tf_agents.environments import suite_gym\nfrom tf_agents.policies import policy_saver\nfrom tf_agents.train import replay\n\n# \ud658\uacbd \uc0dd\uc131\nenv = suite_gym.load('CartPole-v0')\n\n# DQN \uc5d0\uc774\uc804\ud2b8 \uad6c\uc131\nq_net = ... # \uc2e0\uacbd\ub9dd \ubaa8\ub378 \uc815\uc758\noptimizer = tf.compat.v1.train.AdamOptimizer(learning_rate=1e-3)\nglobal_step = tf.Variable(0, trainable=False, dtype=tf.int64)\n\nagent = dqn_agent.DqnAgent(\n ... # \uc5d0\uc774\uc804\ud2b8 \uad6c\uc131 \uc124\uc815\n)\n\nagent.initialize()\n\n# \ud559\uc2b5 \ub8e8\ud504\nfor _ in range(num_episodes):\n train_step = ... # \ud559\uc2b5 \ub2e8\uacc4\n<\/code><\/pre>\n5. \ub77c\uc774\ube0c\ub7ec\ub9ac \ube44\uad50<\/h2>\n5.1 \uc0ac\uc6a9 \uc6a9\uc774\uc131<\/h3>\n
Stable Baselines3\ub294 \uc9c1\uad00\uc801\uc778 API\ub85c \uc2dc\uc791\ud558\uae30 \uac04\ud3b8\ud569\ub2c8\ub2e4. RLlib\ub294 \uc124\uc815\uc774 \uc0c1\ub300\uc801\uc73c\ub85c \ubcf5\uc7a1\ud560 \uc218 \uc788\uc9c0\ub9cc, \uac15\ub825\ud55c \ubd84\uc0b0 \ucc98\ub9ac\ub97c \uc9c0\uc6d0\ud569\ub2c8\ub2e4. TensorFlow Agents\ub294 TensorFlow \uae30\ubc18\uc73c\ub85c \uc798 \ud1b5\ud569\ub418\uc5b4 \uc788\uc73c\ub098, \uc124\uc815\uc774 \ub2e4\uc18c \ubcf5\uc7a1\ud560 \uc218 \uc788\uc2b5\ub2c8\ub2e4.<\/p>\n
5.2 \uc131\ub2a5<\/h3>\n
\uc138 \uac00\uc9c0 \ub77c\uc774\ube0c\ub7ec\ub9ac\ub294 \ubaa8\ub450 \ub192\uc740 \uc131\ub2a5\uc744 \uc81c\uacf5\ud558\uc9c0\ub9cc, RLlib\ub294 \ub300\uaddc\ubaa8 \ud074\ub77c\uc6b0\ub4dc \ud658\uacbd\uc5d0\uc11c \ucd5c\uc801\uc758 \uc131\ub2a5\uc744 \ubc1c\ud718\ud569\ub2c8\ub2e4. Stable Baselines3\ub294 \uad6d\ub0b4 \uc5f0\uad6c\uc790\ub4e4 \uc0ac\uc774\uc5d0\uc11c \uc548\uc815\uc131\uc774 \ub192\uc544 \uc778\uae30\uac00 \ub9ce\uc2b5\ub2c8\ub2e4.<\/p>\n
5.3 \ucee4\uc2a4\ud130\ub9c8\uc774\uc9d5<\/h3>\n
RLlib\ub294 \uc720\uc5f0\ud55c \ucee4\uc2a4\ud130\ub9c8\uc774\uc9d5 \uac00\ub2a5\uc131\uc744 \uc81c\uacf5\ud558\uc5ec \ubcf5\uc7a1\ud55c \ud658\uacbd\uc5d0\uc11c\uc758 \uc2e4\ud5d8\uc5d0\uc11c \uc7a5\uc810\uc774 \uc788\uc2b5\ub2c8\ub2e4. TensorFlow Agents \ub610\ud55c \ubaa8\ub4c8\ud654\ub418\uc5b4 \uc788\uc5b4 \uc0ac\uc6a9\uc790 \uc815\uc758\uac00 \uc6a9\uc774\ud569\ub2c8\ub2e4. Stable Baselines3\ub294 \uae30\ubcf8\uc801\uc778 \ucee4\uc2a4\ud130\ub9c8\uc774\uc9d5 \uae30\ub2a5\uc774 \uc788\uc9c0\ub9cc, \uc77c\ubd80 \ucd08 \uace0\uae09 \uc635\uc158\uc5d0 \ub300\ud55c \uc9c0\uc6d0\uc740 \uc81c\ud55c\uc801\uc785\ub2c8\ub2e4.<\/p>\n
\uacb0\ub860<\/h2>\n
\uac15\ud654\ud559\uc2b5\uc740 \ub2e4\uc591\ud55c \ubd84\uc57c\uc5d0\uc11c \ud65c\uc6a9\ub420 \uc218 \uc788\uc73c\uba70, \ud6a8\uacfc\uc801\uc778 \uc54c\uace0\ub9ac\uc998 \uad6c\ud604\uacfc \uc2e4\ud5d8\uc744 \uc704\ud574 \uc801\ud569\ud55c \ub77c\uc774\ube0c\ub7ec\ub9ac\ub97c \uc120\ud0dd\ud558\ub294 \uac83\uc774 \uc911\uc694\ud569\ub2c8\ub2e4. Stable Baselines3, RLlib, TensorFlow Agents\ub294 \uac01\uae30 \ub2e4\ub978 \uc7a5\uc810\uacfc \ub2e8\uc810\uc744 \uac00\uc9c0\ubbc0\ub85c, \ud504\ub85c\uc81d\ud2b8\uc758 \uc694\uad6c\uc0ac\ud56d\uc5d0 \ub9de\ucd94\uc5b4 \uc801\ud569\ud55c \ub77c\uc774\ube0c\ub7ec\ub9ac\ub97c \uc120\ud0dd\ud558\uc5ec \ud65c\uc6a9\ud558\uc2dc\uae30 \ubc14\ub78d\ub2c8\ub2e4. \uc55e\uc73c\ub85c\ub3c4 \uac15\ud654\ud559\uc2b5 \ubd84\uc57c\uc758 \ub77c\uc774\ube0c\ub7ec\ub9ac\ub294 \uacc4\uc18d \ubc1c\uc804\ud560 \uac83\uc73c\ub85c \uc608\uc0c1\ub418\uba70, \uc774\ub97c \ud1b5\ud574 \ub354 \ub9ce\uc740 \uc5f0\uad6c\uc640 \uc801\uc6a9\uc774 \uc774\ub8e8\uc5b4\uc9c8 \uac83\uc785\ub2c8\ub2e4.<\/p>\n
<\/body><\/p>\n","protected":false},"excerpt":{"rendered":"
\uac15\ud654\ud559\uc2b5(Reinforcement Learning, RL)\uc740 \uc5d0\uc774\uc804\ud2b8\uac00 \ud658\uacbd\uacfc \uc0c1\ud638\uc791\uc6a9\ud558\uba70 \ucd5c\uc801\uc758 \ud589\ub3d9\uc744 \ud559\uc2b5\ud558\ub294 \uacfc\uc815\uc785\ub2c8\ub2e4. \ucd5c\uadfc\uc5d0\ub294 RL\uc758 \uc801\uc6a9 \ubd84\uc57c\uac00 \ub2e4\uc591\ud574\uc9c0\uba74\uc11c \ub9ce\uc740 \ub77c\uc774\ube0c\ub7ec\ub9ac\uc640 \ub3c4\uad6c\ub4e4\uc774 \uac1c\ubc1c\ub418\uc5c8\uc2b5\ub2c8\ub2e4. \ubcf8 \uae00\uc5d0\uc11c\ub294 \uac15\ud654\ud559\uc2b5\uc744 \uc704\ud55c \uc8fc\uc694 \ub77c\uc774\ube0c\ub7ec\ub9ac\ub4e4\uacfc \ub3c4\uad6c\ub4e4\uc744 \uc18c\uac1c\ud558\uace0, \uac01 \ub77c\uc774\ube0c\ub7ec\ub9ac\uc758 \ud2b9\uc9d5\uacfc \uc7a5\ub2e8\uc810\uc744 \ube44\uad50\ud560 \uac83\uc785\ub2c8\ub2e4. \ub300\ud45c\uc801\uc73c\ub85c Stable Baselines3, RLlib, TensorFlow Agents\uc5d0 \ub300\ud574 \ub2e4\ub8e8\uaca0\uc2b5\ub2c8\ub2e4. 1. \uac15\ud654\ud559\uc2b5 \ub77c\uc774\ube0c\ub7ec\ub9ac \uac1c\uc694 \uac15\ud654\ud559\uc2b5 \ub77c\uc774\ube0c\ub7ec\ub9ac\ub294 \uc5f0\uad6c\uc790\ub098 \uac1c\ubc1c\uc790\uac00 RL \uc54c\uace0\ub9ac\uc998\uc744 \uc27d\uac8c \uc2e4\ud5d8\ud558\uace0 \uc801\uc6a9\ud560 \uc218 … \ub354 \ubcf4\uae30 “55. \uac15\ud654\ud559\uc2b5\uc744 \uc704\ud55c \uc8fc\uc694 \ub77c\uc774\ube0c\ub7ec\ub9ac\uc640 \ub3c4\uad6c \uc18c\uac1c, Stable Baselines3, RLlib, TensorFlow Agents \ub4f1 \uc8fc\uc694 \ub77c\uc774\ube0c\ub7ec\ub9ac \ube44\uad50”<\/span><\/a><\/p>\n","protected":false},"author":1,"featured_media":0,"comment_status":"closed","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"_jetpack_memberships_contains_paid_content":false,"footnotes":""},"categories":[213],"tags":[],"class_list":["post-40400","post","type-post","status-publish","format-standard","hentry","category-213"],"yoast_head":"\n55. \uac15\ud654\ud559\uc2b5\uc744 \uc704\ud55c \uc8fc\uc694 \ub77c\uc774\ube0c\ub7ec\ub9ac\uc640 \ub3c4\uad6c \uc18c\uac1c, Stable Baselines3, RLlib, TensorFlow Agents \ub4f1 \uc8fc\uc694 \ub77c\uc774\ube0c\ub7ec\ub9ac \ube44\uad50 - \ub77c\uc774\ube0c\uc2a4\ub9c8\ud2b8<\/title>\n<meta name=\"robots\" content=\"index, follow, max-snippet:-1, max-image-preview:large, max-video-preview:-1\" \/>\n<link rel=\"canonical\" href=\"https:\/\/atmokpo.com\/w\/40400\/\" \/>\n<meta property=\"og:locale\" content=\"ko_KR\" \/>\n<meta property=\"og:type\" content=\"article\" \/>\n<meta property=\"og:title\" content=\"55. \uac15\ud654\ud559\uc2b5\uc744 \uc704\ud55c \uc8fc\uc694 \ub77c\uc774\ube0c\ub7ec\ub9ac\uc640 \ub3c4\uad6c \uc18c\uac1c, Stable Baselines3, RLlib, TensorFlow Agents \ub4f1 \uc8fc\uc694 \ub77c\uc774\ube0c\ub7ec\ub9ac \ube44\uad50 - \ub77c\uc774\ube0c\uc2a4\ub9c8\ud2b8\" \/>\n<meta property=\"og:description\" content=\"\uac15\ud654\ud559\uc2b5(Reinforcement Learning, RL)\uc740 \uc5d0\uc774\uc804\ud2b8\uac00 \ud658\uacbd\uacfc \uc0c1\ud638\uc791\uc6a9\ud558\uba70 \ucd5c\uc801\uc758 \ud589\ub3d9\uc744 \ud559\uc2b5\ud558\ub294 \uacfc\uc815\uc785\ub2c8\ub2e4. \ucd5c\uadfc\uc5d0\ub294 RL\uc758 \uc801\uc6a9 \ubd84\uc57c\uac00 \ub2e4\uc591\ud574\uc9c0\uba74\uc11c \ub9ce\uc740 \ub77c\uc774\ube0c\ub7ec\ub9ac\uc640 \ub3c4\uad6c\ub4e4\uc774 \uac1c\ubc1c\ub418\uc5c8\uc2b5\ub2c8\ub2e4. \ubcf8 \uae00\uc5d0\uc11c\ub294 \uac15\ud654\ud559\uc2b5\uc744 \uc704\ud55c \uc8fc\uc694 \ub77c\uc774\ube0c\ub7ec\ub9ac\ub4e4\uacfc \ub3c4\uad6c\ub4e4\uc744 \uc18c\uac1c\ud558\uace0, \uac01 \ub77c\uc774\ube0c\ub7ec\ub9ac\uc758 \ud2b9\uc9d5\uacfc \uc7a5\ub2e8\uc810\uc744 \ube44\uad50\ud560 \uac83\uc785\ub2c8\ub2e4. \ub300\ud45c\uc801\uc73c\ub85c Stable Baselines3, RLlib, TensorFlow Agents\uc5d0 \ub300\ud574 \ub2e4\ub8e8\uaca0\uc2b5\ub2c8\ub2e4. 1. \uac15\ud654\ud559\uc2b5 \ub77c\uc774\ube0c\ub7ec\ub9ac \uac1c\uc694 \uac15\ud654\ud559\uc2b5 \ub77c\uc774\ube0c\ub7ec\ub9ac\ub294 \uc5f0\uad6c\uc790\ub098 \uac1c\ubc1c\uc790\uac00 RL \uc54c\uace0\ub9ac\uc998\uc744 \uc27d\uac8c \uc2e4\ud5d8\ud558\uace0 \uc801\uc6a9\ud560 \uc218 … \ub354 \ubcf4\uae30 "55. \uac15\ud654\ud559\uc2b5\uc744 \uc704\ud55c \uc8fc\uc694 \ub77c\uc774\ube0c\ub7ec\ub9ac\uc640 \ub3c4\uad6c \uc18c\uac1c, Stable Baselines3, RLlib, TensorFlow Agents \ub4f1 \uc8fc\uc694 \ub77c\uc774\ube0c\ub7ec\ub9ac \ube44\uad50"\" \/>\n<meta property=\"og:url\" content=\"https:\/\/atmokpo.com\/w\/40400\/\" \/>\n<meta property=\"og:site_name\" content=\"\ub77c\uc774\ube0c\uc2a4\ub9c8\ud2b8\" \/>\n<meta property=\"article:published_time\" content=\"2024-11-04T01:51:26+00:00\" \/>\n<meta property=\"article:modified_time\" content=\"2024-11-26T06:39:17+00:00\" \/>\n<meta name=\"author\" content=\"root\" \/>\n<meta name=\"twitter:card\" content=\"summary_large_image\" \/>\n<meta name=\"twitter:creator\" content=\"@bebubo4\" \/>\n<meta name=\"twitter:site\" content=\"@bebubo4\" \/>\n<meta name=\"twitter:label1\" content=\"\uae00\uc4f4\uc774\" \/>\n\t<meta name=\"twitter:data1\" content=\"root\" \/>\n\t<meta name=\"twitter:label2\" content=\"\uc608\uc0c1 \ub418\ub294 \ud310\ub3c5 \uc2dc\uac04\" \/>\n\t<meta name=\"twitter:data2\" content=\"1\ubd84\" \/>\n<script type=\"application\/ld+json\" class=\"yoast-schema-graph\">{\"@context\":\"https:\/\/schema.org\",\"@graph\":[{\"@type\":\"Article\",\"@id\":\"https:\/\/atmokpo.com\/w\/40400\/#article\",\"isPartOf\":{\"@id\":\"https:\/\/atmokpo.com\/w\/40400\/\"},\"author\":{\"name\":\"root\",\"@id\":\"https:\/\/atmokpo.com\/w\/#\/schema\/person\/91b6b3b138fbba0efb4ae64b1abd81d7\"},\"headline\":\"55. \uac15\ud654\ud559\uc2b5\uc744 \uc704\ud55c \uc8fc\uc694 \ub77c\uc774\ube0c\ub7ec\ub9ac\uc640 \ub3c4\uad6c \uc18c\uac1c, Stable Baselines3, RLlib, TensorFlow Agents \ub4f1 \uc8fc\uc694 \ub77c\uc774\ube0c\ub7ec\ub9ac \ube44\uad50\",\"datePublished\":\"2024-11-04T01:51:26+00:00\",\"dateModified\":\"2024-11-26T06:39:17+00:00\",\"mainEntityOfPage\":{\"@id\":\"https:\/\/atmokpo.com\/w\/40400\/\"},\"wordCount\":108,\"publisher\":{\"@id\":\"https:\/\/atmokpo.com\/w\/#organization\"},\"articleSection\":[\"\uac15\ud654\ud559\uc2b5\"],\"inLanguage\":\"ko-KR\"},{\"@type\":\"WebPage\",\"@id\":\"https:\/\/atmokpo.com\/w\/40400\/\",\"url\":\"https:\/\/atmokpo.com\/w\/40400\/\",\"name\":\"55. \uac15\ud654\ud559\uc2b5\uc744 \uc704\ud55c \uc8fc\uc694 \ub77c\uc774\ube0c\ub7ec\ub9ac\uc640 \ub3c4\uad6c \uc18c\uac1c, Stable Baselines3, RLlib, TensorFlow Agents \ub4f1 \uc8fc\uc694 \ub77c\uc774\ube0c\ub7ec\ub9ac \ube44\uad50 - \ub77c\uc774\ube0c\uc2a4\ub9c8\ud2b8\",\"isPartOf\":{\"@id\":\"https:\/\/atmokpo.com\/w\/#website\"},\"datePublished\":\"2024-11-04T01:51:26+00:00\",\"dateModified\":\"2024-11-26T06:39:17+00:00\",\"breadcrumb\":{\"@id\":\"https:\/\/atmokpo.com\/w\/40400\/#breadcrumb\"},\"inLanguage\":\"ko-KR\",\"potentialAction\":[{\"@type\":\"ReadAction\",\"target\":[\"https:\/\/atmokpo.com\/w\/40400\/\"]}]},{\"@type\":\"BreadcrumbList\",\"@id\":\"https:\/\/atmokpo.com\/w\/40400\/#breadcrumb\",\"itemListElement\":[{\"@type\":\"ListItem\",\"position\":1,\"name\":\"\ud648\",\"item\":\"https:\/\/atmokpo.com\/w\/en\/\"},{\"@type\":\"ListItem\",\"position\":2,\"name\":\"55. \uac15\ud654\ud559\uc2b5\uc744 \uc704\ud55c \uc8fc\uc694 \ub77c\uc774\ube0c\ub7ec\ub9ac\uc640 \ub3c4\uad6c \uc18c\uac1c, Stable Baselines3, RLlib, TensorFlow Agents \ub4f1 \uc8fc\uc694 \ub77c\uc774\ube0c\ub7ec\ub9ac \ube44\uad50\"}]},{\"@type\":\"WebSite\",\"@id\":\"https:\/\/atmokpo.com\/w\/#website\",\"url\":\"https:\/\/atmokpo.com\/w\/\",\"name\":\"\ub77c\uc774\ube0c\uc2a4\ub9c8\ud2b8\",\"description\":\"\",\"publisher\":{\"@id\":\"https:\/\/atmokpo.com\/w\/#organization\"},\"potentialAction\":[{\"@type\":\"SearchAction\",\"target\":{\"@type\":\"EntryPoint\",\"urlTemplate\":\"https:\/\/atmokpo.com\/w\/?s={search_term_string}\"},\"query-input\":{\"@type\":\"PropertyValueSpecification\",\"valueRequired\":true,\"valueName\":\"search_term_string\"}}],\"inLanguage\":\"ko-KR\"},{\"@type\":\"Organization\",\"@id\":\"https:\/\/atmokpo.com\/w\/#organization\",\"name\":\"\ub77c\uc774\ube0c\uc2a4\ub9c8\ud2b8\",\"url\":\"https:\/\/atmokpo.com\/w\/\",\"logo\":{\"@type\":\"ImageObject\",\"inLanguage\":\"ko-KR\",\"@id\":\"https:\/\/atmokpo.com\/w\/#\/schema\/logo\/image\/\",\"url\":\"https:\/\/atmokpo.com\/w\/wp-content\/uploads\/2024\/11\/logo.png\",\"contentUrl\":\"https:\/\/atmokpo.com\/w\/wp-content\/uploads\/2024\/11\/logo.png\",\"width\":400,\"height\":400,\"caption\":\"\ub77c\uc774\ube0c\uc2a4\ub9c8\ud2b8\"},\"image\":{\"@id\":\"https:\/\/atmokpo.com\/w\/#\/schema\/logo\/image\/\"},\"sameAs\":[\"https:\/\/x.com\/bebubo4\"]},{\"@type\":\"Person\",\"@id\":\"https:\/\/atmokpo.com\/w\/#\/schema\/person\/91b6b3b138fbba0efb4ae64b1abd81d7\",\"name\":\"root\",\"image\":{\"@type\":\"ImageObject\",\"inLanguage\":\"ko-KR\",\"@id\":\"https:\/\/atmokpo.com\/w\/#\/schema\/person\/image\/\",\"url\":\"https:\/\/secure.gravatar.com\/avatar\/708197b41fc6435a7ce22d951b25d4a47e9e904270cb1f04682d4f025066f80c?s=96&d=mm&r=g\",\"contentUrl\":\"https:\/\/secure.gravatar.com\/avatar\/708197b41fc6435a7ce22d951b25d4a47e9e904270cb1f04682d4f025066f80c?s=96&d=mm&r=g\",\"caption\":\"root\"},\"sameAs\":[\"http:\/\/atmokpo.com\/w\"],\"url\":\"https:\/\/atmokpo.com\/w\/author\/root\/\"}]}<\/script>\n<!-- \/ Yoast SEO plugin. -->","yoast_head_json":{"title":"55. \uac15\ud654\ud559\uc2b5\uc744 \uc704\ud55c \uc8fc\uc694 \ub77c\uc774\ube0c\ub7ec\ub9ac\uc640 \ub3c4\uad6c \uc18c\uac1c, Stable Baselines3, RLlib, TensorFlow Agents \ub4f1 \uc8fc\uc694 \ub77c\uc774\ube0c\ub7ec\ub9ac \ube44\uad50 - \ub77c\uc774\ube0c\uc2a4\ub9c8\ud2b8","robots":{"index":"index","follow":"follow","max-snippet":"max-snippet:-1","max-image-preview":"max-image-preview:large","max-video-preview":"max-video-preview:-1"},"canonical":"https:\/\/atmokpo.com\/w\/40400\/","og_locale":"ko_KR","og_type":"article","og_title":"55. \uac15\ud654\ud559\uc2b5\uc744 \uc704\ud55c \uc8fc\uc694 \ub77c\uc774\ube0c\ub7ec\ub9ac\uc640 \ub3c4\uad6c \uc18c\uac1c, Stable Baselines3, RLlib, TensorFlow Agents \ub4f1 \uc8fc\uc694 \ub77c\uc774\ube0c\ub7ec\ub9ac \ube44\uad50 - \ub77c\uc774\ube0c\uc2a4\ub9c8\ud2b8","og_description":"\uac15\ud654\ud559\uc2b5(Reinforcement Learning, RL)\uc740 \uc5d0\uc774\uc804\ud2b8\uac00 \ud658\uacbd\uacfc \uc0c1\ud638\uc791\uc6a9\ud558\uba70 \ucd5c\uc801\uc758 \ud589\ub3d9\uc744 \ud559\uc2b5\ud558\ub294 \uacfc\uc815\uc785\ub2c8\ub2e4. \ucd5c\uadfc\uc5d0\ub294 RL\uc758 \uc801\uc6a9 \ubd84\uc57c\uac00 \ub2e4\uc591\ud574\uc9c0\uba74\uc11c \ub9ce\uc740 \ub77c\uc774\ube0c\ub7ec\ub9ac\uc640 \ub3c4\uad6c\ub4e4\uc774 \uac1c\ubc1c\ub418\uc5c8\uc2b5\ub2c8\ub2e4. \ubcf8 \uae00\uc5d0\uc11c\ub294 \uac15\ud654\ud559\uc2b5\uc744 \uc704\ud55c \uc8fc\uc694 \ub77c\uc774\ube0c\ub7ec\ub9ac\ub4e4\uacfc \ub3c4\uad6c\ub4e4\uc744 \uc18c\uac1c\ud558\uace0, \uac01 \ub77c\uc774\ube0c\ub7ec\ub9ac\uc758 \ud2b9\uc9d5\uacfc \uc7a5\ub2e8\uc810\uc744 \ube44\uad50\ud560 \uac83\uc785\ub2c8\ub2e4. \ub300\ud45c\uc801\uc73c\ub85c Stable Baselines3, RLlib, TensorFlow Agents\uc5d0 \ub300\ud574 \ub2e4\ub8e8\uaca0\uc2b5\ub2c8\ub2e4. 1. \uac15\ud654\ud559\uc2b5 \ub77c\uc774\ube0c\ub7ec\ub9ac \uac1c\uc694 \uac15\ud654\ud559\uc2b5 \ub77c\uc774\ube0c\ub7ec\ub9ac\ub294 \uc5f0\uad6c\uc790\ub098 \uac1c\ubc1c\uc790\uac00 RL \uc54c\uace0\ub9ac\uc998\uc744 \uc27d\uac8c \uc2e4\ud5d8\ud558\uace0 \uc801\uc6a9\ud560 \uc218 … \ub354 \ubcf4\uae30 \"55. \uac15\ud654\ud559\uc2b5\uc744 \uc704\ud55c \uc8fc\uc694 \ub77c\uc774\ube0c\ub7ec\ub9ac\uc640 \ub3c4\uad6c \uc18c\uac1c, Stable Baselines3, RLlib, TensorFlow Agents \ub4f1 \uc8fc\uc694 \ub77c\uc774\ube0c\ub7ec\ub9ac \ube44\uad50\"","og_url":"https:\/\/atmokpo.com\/w\/40400\/","og_site_name":"\ub77c\uc774\ube0c\uc2a4\ub9c8\ud2b8","article_published_time":"2024-11-04T01:51:26+00:00","article_modified_time":"2024-11-26T06:39:17+00:00","author":"root","twitter_card":"summary_large_image","twitter_creator":"@bebubo4","twitter_site":"@bebubo4","twitter_misc":{"\uae00\uc4f4\uc774":"root","\uc608\uc0c1 \ub418\ub294 \ud310\ub3c5 \uc2dc\uac04":"1\ubd84"},"schema":{"@context":"https:\/\/schema.org","@graph":[{"@type":"Article","@id":"https:\/\/atmokpo.com\/w\/40400\/#article","isPartOf":{"@id":"https:\/\/atmokpo.com\/w\/40400\/"},"author":{"name":"root","@id":"https:\/\/atmokpo.com\/w\/#\/schema\/person\/91b6b3b138fbba0efb4ae64b1abd81d7"},"headline":"55. \uac15\ud654\ud559\uc2b5\uc744 \uc704\ud55c \uc8fc\uc694 \ub77c\uc774\ube0c\ub7ec\ub9ac\uc640 \ub3c4\uad6c \uc18c\uac1c, Stable Baselines3, RLlib, TensorFlow Agents \ub4f1 \uc8fc\uc694 \ub77c\uc774\ube0c\ub7ec\ub9ac \ube44\uad50","datePublished":"2024-11-04T01:51:26+00:00","dateModified":"2024-11-26T06:39:17+00:00","mainEntityOfPage":{"@id":"https:\/\/atmokpo.com\/w\/40400\/"},"wordCount":108,"publisher":{"@id":"https:\/\/atmokpo.com\/w\/#organization"},"articleSection":["\uac15\ud654\ud559\uc2b5"],"inLanguage":"ko-KR"},{"@type":"WebPage","@id":"https:\/\/atmokpo.com\/w\/40400\/","url":"https:\/\/atmokpo.com\/w\/40400\/","name":"55. \uac15\ud654\ud559\uc2b5\uc744 \uc704\ud55c \uc8fc\uc694 \ub77c\uc774\ube0c\ub7ec\ub9ac\uc640 \ub3c4\uad6c \uc18c\uac1c, Stable Baselines3, RLlib, TensorFlow Agents \ub4f1 \uc8fc\uc694 \ub77c\uc774\ube0c\ub7ec\ub9ac \ube44\uad50 - \ub77c\uc774\ube0c\uc2a4\ub9c8\ud2b8","isPartOf":{"@id":"https:\/\/atmokpo.com\/w\/#website"},"datePublished":"2024-11-04T01:51:26+00:00","dateModified":"2024-11-26T06:39:17+00:00","breadcrumb":{"@id":"https:\/\/atmokpo.com\/w\/40400\/#breadcrumb"},"inLanguage":"ko-KR","potentialAction":[{"@type":"ReadAction","target":["https:\/\/atmokpo.com\/w\/40400\/"]}]},{"@type":"BreadcrumbList","@id":"https:\/\/atmokpo.com\/w\/40400\/#breadcrumb","itemListElement":[{"@type":"ListItem","position":1,"name":"\ud648","item":"https:\/\/atmokpo.com\/w\/en\/"},{"@type":"ListItem","position":2,"name":"55. \uac15\ud654\ud559\uc2b5\uc744 \uc704\ud55c \uc8fc\uc694 \ub77c\uc774\ube0c\ub7ec\ub9ac\uc640 \ub3c4\uad6c \uc18c\uac1c, Stable Baselines3, RLlib, TensorFlow Agents \ub4f1 \uc8fc\uc694 \ub77c\uc774\ube0c\ub7ec\ub9ac \ube44\uad50"}]},{"@type":"WebSite","@id":"https:\/\/atmokpo.com\/w\/#website","url":"https:\/\/atmokpo.com\/w\/","name":"\ub77c\uc774\ube0c\uc2a4\ub9c8\ud2b8","description":"","publisher":{"@id":"https:\/\/atmokpo.com\/w\/#organization"},"potentialAction":[{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https:\/\/atmokpo.com\/w\/?s={search_term_string}"},"query-input":{"@type":"PropertyValueSpecification","valueRequired":true,"valueName":"search_term_string"}}],"inLanguage":"ko-KR"},{"@type":"Organization","@id":"https:\/\/atmokpo.com\/w\/#organization","name":"\ub77c\uc774\ube0c\uc2a4\ub9c8\ud2b8","url":"https:\/\/atmokpo.com\/w\/","logo":{"@type":"ImageObject","inLanguage":"ko-KR","@id":"https:\/\/atmokpo.com\/w\/#\/schema\/logo\/image\/","url":"https:\/\/atmokpo.com\/w\/wp-content\/uploads\/2024\/11\/logo.png","contentUrl":"https:\/\/atmokpo.com\/w\/wp-content\/uploads\/2024\/11\/logo.png","width":400,"height":400,"caption":"\ub77c\uc774\ube0c\uc2a4\ub9c8\ud2b8"},"image":{"@id":"https:\/\/atmokpo.com\/w\/#\/schema\/logo\/image\/"},"sameAs":["https:\/\/x.com\/bebubo4"]},{"@type":"Person","@id":"https:\/\/atmokpo.com\/w\/#\/schema\/person\/91b6b3b138fbba0efb4ae64b1abd81d7","name":"root","image":{"@type":"ImageObject","inLanguage":"ko-KR","@id":"https:\/\/atmokpo.com\/w\/#\/schema\/person\/image\/","url":"https:\/\/secure.gravatar.com\/avatar\/708197b41fc6435a7ce22d951b25d4a47e9e904270cb1f04682d4f025066f80c?s=96&d=mm&r=g","contentUrl":"https:\/\/secure.gravatar.com\/avatar\/708197b41fc6435a7ce22d951b25d4a47e9e904270cb1f04682d4f025066f80c?s=96&d=mm&r=g","caption":"root"},"sameAs":["http:\/\/atmokpo.com\/w"],"url":"https:\/\/atmokpo.com\/w\/author\/root\/"}]}},"jetpack_featured_media_url":"","jetpack_sharing_enabled":true,"jetpack-related-posts":[],"_links":{"self":[{"href":"https:\/\/atmokpo.com\/w\/wp-json\/wp\/v2\/posts\/40400","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/atmokpo.com\/w\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/atmokpo.com\/w\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/atmokpo.com\/w\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/atmokpo.com\/w\/wp-json\/wp\/v2\/comments?post=40400"}],"version-history":[{"count":1,"href":"https:\/\/atmokpo.com\/w\/wp-json\/wp\/v2\/posts\/40400\/revisions"}],"predecessor-version":[{"id":40401,"href":"https:\/\/atmokpo.com\/w\/wp-json\/wp\/v2\/posts\/40400\/revisions\/40401"}],"wp:attachment":[{"href":"https:\/\/atmokpo.com\/w\/wp-json\/wp\/v2\/media?parent=40400"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/atmokpo.com\/w\/wp-json\/wp\/v2\/categories?post=40400"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/atmokpo.com\/w\/wp-json\/wp\/v2\/tags?post=40400"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}