Disclaimer:
Educational Use Only:
The website links provided are to be used strictly for educational and knowledge-gaining purposes only.
No Misuse:
Do not misuse the links or the information contained therein for any commercial, illegal, or unethical activities.
Respect for Websites and Businesses:
Respect the intellectual property and business interests of the websites and their owners. Do not attempt to alter, copy, or redistribute content without proper authorization.
Acknowledge Value of Knowledge:
Recognize and value the knowledge and resources shared by these websites. Use the information responsibly and ethically.
No Endorsement:
The provision of these links does not imply endorsement of the linked sites, their content, or their products and services. Users are responsible for evaluating the suitability and accuracy of the information.
User Responsibility:
By accessing these links, you agree to use the information at your own risk and to comply with all applicable laws and website terms of use.
Overall MCQs for Reference
- What is the primary objective in the CartPole environment?
a. To maximize total rewards
b. To balance a pole on a cart
c. To minimize cart velocity
d. To reduce pole angle oscillations
Answer: b. To balance a pole on a cartgithub+1 - Which library is commonly used for the CartPole environment?
a. OpenCV
b. OpenAI Gym
c. TensorFlow
d. PyTorch
Answer: b. OpenAI Gymlinkedin+1 - What type of learning is typically used to solve CartPole?
a. Supervised learning
b. Unsupervised learning
c. Reinforcement learning
d. Transfer learning
Answer: c. Reinforcement learningngaifyoutube - How many features are present in the CartPole state space?
a. 2
b. 3
c. 4
d. 5
Answer: c. 4dev+1 - Which of these is NOT a CartPole state feature?
a. Cart position
b. Cart velocity
c. Pole color
d. Pole angle
Answer: c. Pole colorgithub+1 - The CartPole action space is:
a. Continuous
b. Multi-dimensional
c. Discrete
d. Boolean
Answer: c. Discretedev+1 - Which algorithm is basic to train CartPole?
a. Q-Learning
b. K-means
c. PCA
d. AdaBoost
Answer: a. Q-Learninggithub+1 - What reward does CartPole give for each time step the pole is upright?
a. 0
b. -1
c. 1
d. 10
Answer: c. 1stackoverflow+1 - An episode in CartPole ends when:
a. Cart velocity exceeds threshold
b. Pole falls past a certain angle
c. Cart moves right
d. Cart moves left
Answer: b. Pole falls past a certain anglelinkedin+1 - Which variable represents the exploration rate in Q-learning for CartPole?
a. Alpha
b. Beta
c. Epsilon
d. Gamma
Answer: c. Epsilongithub+1 - What is the main challenge of CartPole?
a. Image recognition
b. Balancing an unstable system
c. Multi-agent coordination
d. Speech processing
Answer: b. Balancing an unstable systempylessons+1 - In OpenAI Gym, CartPole is considered:
a. A classification task
b. A regression task
c. A classic control problem
d. An unsupervised task
Answer: c. A classic control problemwandb+1 - Which of the following is NOT a CartPole action?
a. Move left
b. Move right
c. Jump
d. Stay
Answer: c. Jumpgithub+1 - Discount factor in Q-learning for CartPole is denoted by:
a. Alpha
b. Beta
c. Gamma
d. Theta
Answer: c. Gammadev+1 - When does the CartPole episode terminate due to cart position?
a. When cart position exceeds ±2.4 units
b. When pole angle exceeds ±15 degrees
c. When reward drops to 0
d. When cart velocity is max
Answer: a. When cart position exceeds ±2.4 unitsstackoverflow+1 - Which parameter smoothens the Q-value updates?
a. Alpha
b. Epsilon
c. Lambda
d. Gamma
Answer: a. Alphagithub+1 - The policy in CartPole decides:
a. Which observation to record
b. Which reward to give
c. Which action to take
d. Which environment to simulate
Answer: c. Which action to takengaif+1 - Adaptive hyperparameters in CartPole Q-learning include:
a. Changing only gamma
b. Adjusting alpha and epsilon
c. Fixing all hyperparameters
d. Ignoring rewards
Answer: b. Adjusting alpha and epsilondev+1 - Which function is used to interact with the CartPole environment in Python?
a. env.step(action)
b. env.run(action)
c. env.execute(action)
d. env.move(action)
Answer: a. env.step(action)linkedin+1 - Which deep RL algorithm is commonly used for CartPole?
a. DQN
b. CNN
c. SVM
d. GAN
Answer: a. DQNgithubyoutube - What is the goal reward for CartPole-v0 in OpenAI Gym?
a. 200
b. 500
c. 475
d. 100
Answer: a. 200wandb+1 - The number of possible actions for CartPole is:
a. 1
b. 2
c. 3
d. 4
Answer: b. 2github+1 - CartPole pole starts in what initial state?
a. Horizontal
b. Upright
c. At an angle
d. Oscillating
Answer: b. Uprightlinkedin+1 - Which observation is NOT part of CartPole?
a. Cart position
b. Cart velocity
c. Pole angle
d. Pole mass
Answer: d. Pole massgithub+1 - The environment resets after:
a. Every step
b. Every episode
c. Every action
d. Every reward
Answer: b. Every episodeaigreeks+1 - What does ‘done’ indicate in env.step(action)?
a. Time to stop training
b. Terminal state reached
c. Invalid action
d. Hyperparameter error
Answer: b. Terminal state reachedlinkedin+1 - What happens if the pole falls in CartPole?
a. Reward = -1
b. Reward = 0
c. Reward continues
d. Reward doubles
Answer: b. Reward = 0stackoverflow+1 - Which library helps visualize learning in CartPole?
a. Matplotlib
b. Seaborn
c. OpenCV
d. NLTK
Answer: a. Matplotlibgithub+1 - Which action takes the cart left in CartPole’s discrete action space?
a. 1
b. 2
c. 0
d. -1
Answer: c. 0github+1 - Policy gradient methods in CartPole use:
a. Direct optimization of the policy
b. Value function estimation only
c. Image recognition
d. Unsupervised clustering
Answer: a. Direct optimization of the policytensorflow+1 - In DQN, what is typically used for function approximation?
a. Decision trees
b. Neural networks
c. SVM
d. K-means
Answer: b. Neural networksyoutubetensorflow - What is critical for CartPole agent’s generalization?
a. Random initialization
b. Multi-episode training
c. Fixed actions
d. Dataset balancing
Answer: b. Multi-episode trainingwandb+1 - Which type of exploration policy is often used?
a. Deterministic policy
b. Epsilon-greedy policy
c. Maximal policy
d. Fixed policy
Answer: b. Epsilon-greedy policydev+1 - When using RL for CartPole, what is updated during learning?
a. State observations
b. Q-values
c. Reward signal
d. Pole mass
Answer: b. Q-valuesgithub+1 - Which of these is NOT a termination criterion in CartPole?
a. Pole exceeds 15 degrees from vertical
b. Cart position goes out of bounds
c. Reward exceeds 10
d. Environment ‘done’ returns True
Answer: c. Reward exceeds 10stackoverflow+1 - Which observation range is a constraint for cart position?
a. ±1.5 units
b. ±2.4 units
c. ±3.0 units
d. ±0.5 units
Answer: b. ±2.4 unitsstackoverflow+1 - CartPole environment is suitable for which concept?
a. Probabilistic reasoning
b. Control theory
c. Natural language processing
d. Computer vision
Answer: b. Control theorywandb+1 - What does ‘env.reset()’ do in OpenAI Gym’s CartPole?
a. Pauses the environment
b. Ends the game
c. Starts a new episode
d. Links multiple environments
Answer: c. Starts a new episodelinkedin+1 - Which model-free RL method is used for CartPole?
a. SARSA
b. Q-learning
c. DDPG
d. Bayesian inference
Answer: b. Q-learningdev+1 - In Q-learning, which hyperparameter is often tuned for CartPole?
a. Alpha
b. Beta
c. Lambda
d. Delta
Answer: a. Alphagithub+1 - Which value function is most central for CartPole RL?
a. State-value function
b. Action-value function
c. Prediction function
d. Loss function
Answer: b. Action-value functiontensorflow+1 - Which approach seeks to maximize expected cumulative reward in CartPole?
a. Policy optimization
b. Feature engineering
c. Label smoothing
d. Loss regularization
Answer: a. Policy optimizationanyscale+1 - Which environment variant increases CartPole’s difficulty?
a. CartPole-v0
b. CartPole-v1
c. MountainCar-v0
d. LunarLander-v2
Answer: b. CartPole-v1towardsdatascience+1 - What is a common trick for stabilizing DQN in CartPole?
a. Target network
b. Feature selection
c. Gradient clipping
d. Batch normalization
Answer: a. Target networkyoutubetensorflow - What is the default maximum time steps per CartPole episode in v0?
a. 100
b. 200
c. 500
d. 475
Answer: b. 200wandb+1 - In CartPole, which function returns resulting state & reward?
a. env.run()
b. env.step()
c. env.act()
d. env.finish()
Answer: b. env.step()github+1 - Which loss function is typically used in neural RL for CartPole?
a. Cross-entropy
b. Mean squared error
c. Hinge loss
d. Log loss
Answer: b. Mean squared errortensorflowyoutube - What is the pole’s typical failure threshold angle in degrees?
a. 10
b. 15
c. 20
d. 25
Answer: b. 15stackoverflow+1 - What can cause CartPole RL agent to fail suddenly?
a. Poor exploration rate
b. Good policy
c. High reward
d. Data balancing
Answer: a. Poor exploration ratedev+1 - Which method trains CartPole using observed rewards?
a. Supervised learning
b. Reinforcement learning
c. Unsupervised learning
d. Self-organizing maps
Answer: b. Reinforcement learningngaif+2
- https://github.com/pythonlessons/CartPole_reinforcement_learning
- https://pylessons.com/CartPole-reinforcement-learning
- https://www.linkedin.com/pulse/reinforcement-learning-pytorch-mastering-cartpole-v0-akbarnezhad
- https://ngaif.com/reinforcement-learning-with-gym-a-beginners-guide-to-cartpole/
- https://www.youtube.com/watch?v=D795oNqa-Vk
- https://dev.to/n1try/cartpole-with-q-learning—first-experiences-with-openai-gym
- https://github.com/enerrio/CartPole-Reinforcement-Learning
- https://stackoverflow.com/questions/41684801/whats-the-best-objective-function-for-the-cartpole-task
- https://wandb.ai/rebeccabot/rebecca_project/reports/Cartpole-Reinforcement-Learning-in-Gym–VmlldzoxOTI5MDA3
- https://github.com/topics/cartpole
- https://aigreeks.com/cartpole-in-openai-gym-guide-treinforcement-learning/
- https://www.tensorflow.org/tutorials/reinforcement_learning/actor_critic
- https://www.anyscale.com/blog/an-introduction-to-reinforcement-learning-with-openai-gym-rllib-and-google
- https://towardsdatascience.com/hands-on-reinforcement-learning-course-part-4-55da5eae851f/
- https://www.sanfoundry.com/artificial-intelligence-questions-answers/
- https://testbook.com/objective-questions/mcq-on-artificial-intelligence–5eea6a0d39140f30f369e30e
- https://www.interviewbit.com/artificial-intelligence-mcq/
- https://www.kaggle.com/code/saquib7hussain/cartpole-game-reinforcement-learning
- https://www.scribd.com/document/737189591/Artificial-Intelligence-MCQ-unit1-2
- https://pythonprogramming.net/openai-cartpole-neural-network-example-machine-learning-tutorial/
