Linked Questions

4
votes
1answer
3k views

What is the difference between a stationary and a non-stationary policy?

In reinforcement learning, there are deterministic and non-deterministic (or stochastic) policies, but there are also stationary and non-stationary policies. What is the difference between a ...
3
votes
2answers
639 views

What is a probability distribution in machine learning?

If we were learning or working in the machine learning field, then we frequently come across the term "probability distribution". I know what probability, conditional probability, and ...
8
votes
2answers
512 views

What is experience replay in laymen's terms?

I've been reading Google's DeepMind Atari paper and I'm trying to understand the concept of "experience replay". Experience replay comes up in a lot of other reinforcement learning papers (...
5
votes
2answers
314 views

Given two optimal policies, is an affine combination of them also optimal?

If there are two different optimal policies $\pi_1, \pi_2$ in a reinforcement learning task, will the linear combination (or affine combination) of the two policies $\alpha \pi_1 + \beta \pi_2, \alpha ...
4
votes
2answers
201 views

What is the difference between return and expected return?

At a time step $t$, for a state $S_{t}$, the return is defined as the discounted cumulative reward from that time step $t$. If an agent is following a policy (which in itself is a probability ...
4
votes
1answer
184 views

Is tabular Q-learning considered interpretable?

I am working on a research project in a domain where other related works have always resorted to deep Q-learning. The motivation of my research stems from the fact that the domain has an inherent ...
1
vote
1answer
221 views

What kind of problems is DQN algorithm good and bad for?

I know this is a general question, but I'm just looking for intuition. What are the characteristics of problems (in terms of state-space, action-space, environment, or anything else you can think of) ...
3
votes
1answer
176 views

Why do RL implementations converge on one action?

I have seen this happening in implementations of state-of-the-art RL algorithms where the model converges to a single action over time after multiple training iterations. Are there some general ...
1
vote
1answer
129 views

What is the difference between the definition of a stationary policy in reinforcement learning and contextual bandit?

A stationary policy is a function that maps a state to a probability distribution of actions. In a contextual bandit problem, a state itself does not include the history. But in a reinforcement ...
3
votes
1answer
86 views

Does stochasticity of an environment necessarily mean non-stationarity in MDPs?

Is a stochastic environment necessarily also non-stationary? To elaborate, consider a two-state environment ($s_1$ and $s_2$), with two actions $a_1$ and $a_2$. In $s_1$, taking action $a_1$ has a ...
1
vote
2answers
90 views

When should one prefer using Total Variational Divergence over KL divergence in RL

In RL, both the KL divergence (DKL) and Total variational divergence (DTV) are used to measure the distance between two policies. I'm most familiar with using DKL as an early stopping metric during ...