Top "Reinforcement-learning" questions

Reinforcement learning is an area of machine learning and computer science concerned with how to select an action in a state that maximizes a numerical reward in a particular environment.

Q-learning vs temporal-difference vs model-based reinforcement learning

I'm in a course called "Intelligent Machines" at the university. We were introduced with 3 methods of reinforced learning, and with …

machine-learning reinforcement-learning q-learning temporal-difference
PyTorch Model Training: RuntimeError: cuDNN error: CUDNN_STATUS_INTERNAL_ERROR

After training a PyTorch model on a GPU for several hours, the program fails with the error RuntimeError: cuDNN error: …

python pytorch lstm reinforcement-learning dqn
OpenAI Gym: Understanding `action_space` notation (spaces.Box)

I want to setup an RL agent on the OpenAI CarRacing-v0 environment, but before that I want to understand the …

reinforcement-learning openai-gym
Using Tensorflow Huber loss in Keras

I am trying to use huber loss in a keras model (writing DQN), but I am getting bad result, I …

python tensorflow keras reinforcement-learning
NameError: name 'base' is not defined OpenAI Gym

[Note that I am using xvfb-run -s "-screen 0 1400x900x24" jupyter notebook] I try to run a basic set of …

reinforcement-learning openai-gym
When should I use support vector machines as opposed to artificial neural networks?

I know SVMs are supposedly 'ANN killers' in that they automatically select representation complexity and find a global optimum (see …

machine-learning neural-network svm reinforcement-learning
Epsilon and learning rate decay in epsilon greedy q learning

I understand that epsilon marks the trade-off between exploration and exploitation. At the beginning, you want epsilon to be high …

machine-learning reinforcement-learning q-learning
What is the difference between reinforcement learning and deep RL?

What is the difference between deep reinforcement learning and reinforcement learning? I basically know what reinforcement learning is about, but …

machine-learning reinforcement-learning q-learning
DQN - Q-Loss not converging

I'm using the DQN algorithm to train an agent in my environment, that looks like this: Agent is controlling a …

tensorflow deep-learning reinforcement-learning q-learning
How to update weights manually with Keras

I'm using Keras to build a LSTM and tuning it by doing gradient descent with an external cost function. So …

python performance keras recurrent-neural-network reinforcement-learning