Questions tagged [discrete-action-spaces]
For questions about discrete action spaces in the context of reinforcement learning (or other artificial intelligence sub-fields). There is also the tag for continuous action spaces.
10
questions
0
votes
0
answers
20
views
Training Issue in Solving Multi-Dimensional Multiple Knapsack Problem with Transformer Model and PPO and SAC algorithm
I'm reaching out to the brilliant minds of the AI community to seek help with a challenging issue in my project on solving the multi-dimensional multiple knapsack problem using a transformer model. As ...
2
votes
1
answer
174
views
Model-based RL algorithms for continuous state space and finite action space
At the beginning, if I have a complete model $p(s' \mid s, a)$ (an assumed true model that describes the environment well enough) and the reward function $r(s,a,s')$. How can I exploit the model and ...
- 35
1
vote
1
answer
699
views
PPO: multiple discrete actions per step, one depends on the other
I have a custom PPO implementation, and it works fine, but I need to add to it the ability to select 2 actions per turn, one different in nature from the other, one dependent on the other.
Imagine ...
2
votes
1
answer
343
views
Is there a multi-agent deep reinforcement learning algorithm which is for environments with only discrete action spaces (Not hybrid)?
Is there a multi-agent deep reinforcement learning algorithm which is for environments with only discrete action spaces (Not hybrid) and have centralized training?
I have been looking for algorithms, (...
- 21
4
votes
1
answer
592
views
Can a large discrete action space be represented using Gaussian distributions?
I have a large 1D action space, e.g. dim(A)=2000-10000. Can I use continuous action space where I could learn the mean and std of the Gaussian distributions that I would use to sample action from and ...
- 331
0
votes
0
answers
133
views
How to implement RL model with increasing dimensions of state space and action space?
I've read in this discussion that "reinforcement learning is a way of finding the value function of a Markov Decision Process".
I want to implement an RL model, whose state space and action ...
- 141
1
vote
0
answers
370
views
What adapts an algorithm to continuous or to discrete action spaces?
Some RL algorithms can only be used for environments with continuous action spaces (e.g TD3, SAC), while others only for discrete action spaces (DQN), and some for both
REINFORCE and other policy ...
- 531
16
votes
3
answers
7k
views
How to implement a variable action space in Proximal Policy Optimization?
I'm coding a Proximal Policy Optimization (PPO) agent with the Tensorforce library (which is built on top of TensorFlow).
The first environment was very simple. Now, I'm diving into a more complex ...
- 163
2
votes
1
answer
457
views
Extend the loss function from the single action to the n-action case per time step
My question concerns a side question (which was not answered) asked here:
How can policy gradients be applied in the case of multiple continuous actions?
I am trying to implement a simple policy ...
- 31
6
votes
1
answer
594
views
What techniques are used to make MDP discrete state space manageable?
Generating a discretized state space for an MDP (Markov Decision Process) model seems to suffer from the curse of dimensionality.
Supposed my state has a few simple features:
Feeling: Happy/Neutral/...
- 263