Questions tagged [ddpg]
6 questions
1
vote
1 answer
How to correctly define this Observation Space for the custom Gym environment I am creating using Gym.Scpaces.Box?
I am trying to implement DDPG algorithm of the Paper.
Here in the image below, gk[n] and rk[n] are KxM matrices of real values.
Theta[n] and v[n] are arrays of size M.
I want to write correct code to specify state/observation space in my custom…
Sukhamjot Singh
- 35
- 6
1
vote
1 answer
DDPG training in Tensorflow.js
I'm trying to figure out how to implement DDPG in Tensorflow.js using Python examples such as this one from keras website. I got stuck on the training code:
with tf.GradientTape() as tape:
target_actions =…
Oleg Khalidov
- 5,108
- 1
- 28
- 29
0
votes
0 answers
How to apply DDPG OUnoise to my environment
I am trying to perform reinforcement learning using the DDPG algorithm in my custom environment. I looked for various OUnoises here, but I couldn't find one that fits my environment.
Detail :
A total of four actions are output from the Actor…
M J
- 1
0
votes
1 answer
Tensorflow DDPG agent. Shape mismatch in critic loss function using DDPG agent. Mismatch between td_targets and q_values tensors
I have an issue when computing the mean squared error in the critic loss function using a DDPG agent. The error message I receive indicates a shape mismatch between the expected tensor shape and the actual tensor shape in the critic loss function of…
Peter Renz
- 23
- 5
0
votes
0 answers
DDPG algorithm was used to solve the tasks in continuous environment, but the performance was not shown in the training stage
I wanted to try the DDPG algorithm with the mujoco's task, 'Reacher-v2', witch can be seen in this code.
I ran my code but the performance like the episode rewards in the training didn't go up.
Some of my code mimics the package, cleanrl, mainly on…
0
votes
0 answers
How i can use dqn and ddpg to successfully train an agent excellent in customized environment?
I'm new in AI, and i want to get in the field, i have spent some time finishing a program to train an agent for a simple customized environment, but when i perform the training in colab for 10000 episodes, it still can not get well performance. I…
guanming Bao
- 21
- 3