Search Results
| Search type | Search syntax |
|---|---|
| Tags | [tag] |
| Exact | "words here" |
| Author |
user:1234 user:me (yours) |
| Score |
score:3 (3+) score:0 (none) |
| Answers |
answers:3 (3+) answers:0 (none) isaccepted:yes hasaccepted:no inquestion:1234 |
| Views | views:250 |
| Code | code:"if (foo != bar)" |
| Sections |
title:apples body:"apples oranges" |
| URL | url:"*.example.com" |
| Saves | in:saves |
| Status |
closed:yes duplicate:no migrated:no wiki:no |
| Types |
is:question is:answer |
| Exclude |
-[tag] -apples |
| For more details on advanced search visit our help page | |
Results tagged with reinforcement-learning
Search options not deleted
user 36821
For questions related to reinforcement learning, i.e. a machine learning technique where we imagine an agent that interacts with an environment (composed of states) in time steps by taking actions and receiving rewards (or reinforcements), then, based on these interactions, the agent tries to find a policy (i.e. a behavioural strategy) that maximizes the cumulative reward (in the long run), so the goal of the agent is to maximize the reward.
2
votes
Accepted
Solution to exercise 3.22 in the RL book by Sutton and Barto
Your answer is correct but I am not sure exactly on how you arrived at it, as e.g. in the last case you don't know that $v_{L,n}(S_0) = v_{R,n}(S_0)$.
I will show for case B when $\gamma = 0.9$ as c …
- 5,030
1
vote
1
answer
109
views
Where can I find short videos of examples of RL being used?
I would like to add a short ~1-3 minute video to a presentation, to demonstrate how Reinforcement Learning is used to solve problems. I am thinking something like a short gif of an agent playing an At …
- 5,030
4
votes
Accepted
Confusion in notation for state-value functions in reinforcement learning
The difference between $V_T(S_t)$ and $V_{T-1}(S_t)$ is simply that $V_{T-1}(S_t)$ is the estimate of $V$ after $T-1$ updates. The notation is a bit clumsy since there are two elements of 'time' here …
- 5,030
1
vote
Accepted
Looping over Sarsa algorithm for better Q values
Given that your state space is continuous, then I would recommend using Deep Q-Learning. As you say, running several episodes will definitely be beneficial so that the agent is able to explore the spa …
- 5,030
2
votes
Accepted
Can a convolutional network predict states for a RL Agent
It sounds like what you're suggesting is similar to what is done in methods that use a planner. These methods looks to learn the dynamics of the MDP to use to plan during training; that is they want t …
- 5,030
2
votes
What does it mean to parameterise a policy in policy gradient methods?
In the context of RL, for a policy to be parameterised it typically means we explicitly model the policy and is common in policy gradient methods.
Consider value based methods such as Q-learning whe …
- 5,030
2
votes
Accepted
Is the distribution of state-action pairs from sample based planning accurate for small expe...
I am aware that as the experience set grows the Central Limit Theorem
will come into play and the distribution of experience will more
accurately represent the true environment's state-actions- …
- 5,030
3
votes
Accepted
What is the purpose of storing the action $a$ within an experience tuple?
We need to store the action $a$ as it tells us the action that we took in the state that we are backing up.
Suppose we are in state $s$ and we take action $a$, then we will receive a reward $r$ and ne …
- 5,030
2
votes
Accepted
How is it possible that Q-learning can learn a state-action value without taking into accoun...
Q-learning can learn about the greedy policy (the policy that we define as $\pi(s) = \arg\max_a Q(s, a)$) whilst following some arbitrary exploratory policy because Q-learning is an off-policy algorit …
- 5,030
1
vote
Accepted
How does a model based agent learn the model?
If you already have some transition tuples then you can train a model to predict environment dynamics using these. However, you should be careful that your pre-gathered data is diverse enough to 'cove …
- 5,030
2
votes
Accepted
What does it mean for an episode to start in a state-action pair?
It simply means that you start an episode in any possible state-action combination. Consider a gridworld type environment: an example of starting in a state-action pair would be to start in the top le …
- 5,030
3
votes
Accepted
Can a policy with gaussian distribution allow two distinct optimal actions to have distincti...
Assuming by distinct you mean that, for example, the euclidean distance between the two actions is sufficiently large, then no it cannot be true. This is because the Normal distribution is uni-modal. …
- 5,030
0
votes
Do we use RL to train ANNs, or use ANNs as par of a RL solution?
I would say that this is just be the semantics of the sentence you read. I would understand the sentence 'RL can be used as a framework to train an ANN' to mean that we are using an RL algorithm to le …
- 5,030
2
votes
Accepted
Questions about notation in RL
Yes, $S_t \sim d^\pi$ is a nice way of saying that the states are distributed according to the state distribution induced by following $\pi$. Whilst $\pi$ does not directly choose the next state, choo …
- 5,030
-1
votes
Accepted
Why are neural networks used as reinforcement learning model value functions?
There is a much simpler answer than the ones already given. The value function represents the expected (discounted) returns from the current state when following policy $\pi$, i.e:
$$v_\pi(s) = \mathb …
- 5,030