8
votes
Accepted
Is a policy always deterministic in reinforcement learning?
There are multiple questions here: 1. Is a policy always deterministic? 2. If the policy is deterministic then shouldn't the value also be deterministic? 3. What is the expectation over in the value ...
- 2,534
3
votes
Accepted
Proof that any $\epsilon$-greedy policy is an improvement over any $\epsilon$-soft policy
I also spent some trying to understand this transition. I came up with this. Hope it helps.
$\pi$ is an $\epsilon-$soft policy. This implies that $\pi(a|s) \ge \frac{\epsilon}{|A(s)|}$ for all ...
- 46
2
votes
Accepted
Policy improvement in SARSA and Q learning
The current policy is derived in SARSA and Q learning from the current action values. It is always the $\epsilon$-greedy or greedy action choice according to $\text{argmax}_a Q(s,a)$. There is no need ...
- 6,944
1
vote
Discrete and continuous actions in the same environment
How about discretizing the continuous output?
For a binary decision:
$$
Binary(x) = \left\{\begin{array}{lr}
0, & \text{for } x < 0.5\\
1, & \text{for } x \geq 0.5\\
...
- 371
1
vote
Is a policy always deterministic in reinforcement learning?
The policy can be stochastic or deterministic. The expectation is over training examples given the conditions. The value function is an estimate of the return, which is why it's an expectation.
- 15.5k
Only top scored, non community-wiki answers of a minimum length are eligible