Questions tagged [off-policy]

For questions related to off-policy reinforcement learning algorithms, which estimate a policy (the target policy) while using another policy (the behavior policy), during the learning process, which ensures that all states are sufficiently explored. An example of an off-policy algorithm is Q-learning.

Filter by
Sorted by
Tagged with
3
votes
1answer
107 views

What is meant by “generate the data” in describing the difference between on-policy and off-policy?

From the book: Sutton, Richard S.,Barto, Andrew G.. Reinforcement Learning (Adaptive Computation and Machine Learning series) (p. 100). The MIT Press. Kindle Edition. " following is stated: "...
1
vote
0answers
23 views

Should the importance sampling ratio be updated at the end of the for loop in the off-policy Monte Carlo control algorithm?

I'm studying RL with Sutton and Barto's book. I'd like to ask about the order of execution of a statement in the algorithm below. Here, $W$ (importance sampling ratio) is updated at the end of the <...
1
vote
0answers
31 views

Off-Policy Estimation - Importance Sampling with Negative Rewards

Importance sampling is a common method for calculating off-policy estimates in RL. I have been reading through some of the original documentation (D.G. Horvitz and D.J. Thompson, Powell, M.J. and ...
2
votes
0answers
26 views

Why is it the case that off - policy evaluation using importance sampling suffers from high variance?

The average return for trajectories, $V^{\pi_e}$(s) is often computed via the importance sampling estimate $$V^{\pi_e}(s) = \frac{1}{n}\sum_{i=1}^n\prod_{t=0}^{H}\frac{\pi_e(a_t | s_t)}{\pi_b(a_t|s_t)}...
1
vote
0answers
31 views

Is this figure a correct representation of off-policy actor-critic methods?

Does this figure correctly represent the overall general idea about actor-critic methods for on-policy (left) and off-policy (right) case? I am a bit confused about the off-policy case (right figure). ...
0
votes
0answers
40 views

Does the off-policy evaluation work for non-stationary policies?

As the title says, in reinforcement learning, does the off-policy evaluation work for non-stationary policies? For example, IS (importance sampling)-based estimators, such as weighted IS or doubly ...
0
votes
1answer
62 views

How do I know that the DQN has learnt an appropriate Q function?

Is there any sanity check to know whether the Q functions learnt are appropriate in deep Q networks? I know that the Q values for end states should approximate the terminal reward. However, is it ...
1
vote
0answers
64 views

How is per-decision importance sampling derived in Sutton & Barto's book?

In per-decison importance sampling given in Sutton & Barto's book: Eq 5.12 $\rho_{t:T-1}R_{t+k} = \frac{\pi(A_{t}|S_{t})}{b(A_{t}|S_{t})}\frac{\pi(A_{t+1}|S_{t+1})}{b(A_{t+1}|S_{t+1})}\frac{\pi(...
2
votes
0answers
45 views

Can weighted importance sampling be applied to off-policy evaluation for continuous state space MDPs?

Can weighted importance sampling (WIS) and importance sampling (IS) be applied to off-policy evaluation for continuous state spaces MDPs? Given that I have trajectories of $(s_t,a_t)$ pairs and the ...
1
vote
0answers
36 views

How can I perform policy update in python? [closed]

I'm using Python and tensorflow to implement a Deep Q-learning with experience replay in a continous action and state spaces and I have used two neural networks to approximate both the policy function ...
0
votes
2answers
70 views

What is the intuition behind importance sampling for off-policy value evaluation?

The technique for off-policy value evaluation comes from importance sampling, which states that $$E_{x \sim q}[f(x)] \approx \frac{1}{n}\sum_{i=1}^n f(x_i)\frac{q(x_i)}{p(x_i)},$$ where $x_i$ is ...
3
votes
1answer
69 views

What is the difference between on-policy and off-policy for continuous environments?

I'm trying to understand RL applied to time series (so with infinite horizon) which have a continous state space and a discrete action space. First, some preliminary questions: in this case, what is ...
1
vote
1answer
46 views

Is it possible to prove that the target policy is better than the behavioural policy based on learned Q values?

I have retrospective data for a sort of "behaviour policy" which I will use to train a deep q network to learn a target greedy policy. After learning the Q values for this target policy, can we make ...
1
vote
1answer
43 views

Can we combine Off-Policy with On-Policy Algorithms?

On-Policy Algorithms like PPO directly maximize the performance objective or an approximation of it. They tend to be quite stable and reliable but are often sample inefficient. Off-Policy Algorithms ...
1
vote
1answer
62 views

Why is DDPG an off-policy RL algorithm?

In DDPG, if there are no $\epsilon$-greedy and no action noise, is DDPG an on-policy algorithm?
2
votes
3answers
55 views

How to estimate a behavior policy for off-policy learning based on data?

I have a dataset which includes states, actions, and reward. The dataset includes information on the transition, i.e., $p(r,s' \mid s,a)$. Is there a way to estimate a behavior policy from this ...
1
vote
1answer
67 views

What are the differences between 1-step SARSA and SARSA?

SARSA is on-policy, while n-step SARSA is off-policy. But when n = 1, is it like an off-policy version of SARSA? Any similarity and difference between 1-step SARSA and SARSA?
1
vote
1answer
44 views

Understanding the W term in off policy monte carlo learning

In Sutton and Barto's RL textbook they included the following pseudocode for off policy Monte Carlo learning. I am a little confused, however, because to me it looks like the W term will become ...
3
votes
1answer
134 views

Is Expected SARSA an off-policy or on-policy algorithm?

I understand that SARSA is an On-policy algorithm, and Q-learning an off-policy one. Sutton and Barto's textbook describes Expected Sarsa thusly: In these cliff walking results Expected Sarsa was ...
2
votes
1answer
43 views

Could we update the policy network with previous trajectories using supervised learning?

I believe to understand the reason why on-policy methods cannot reuse trajectories collected from earlier policies: the trajectory distribution change with the policy and the policy gradient is ...
2
votes
1answer
27 views

Equivalence between expected parameter increments in “Off-Policy Temporal-Difference Learning with Function Approximation”

I am having a hard time understanding the proof of theorem 1 presented in the "Off-Policy Temporal-Difference Learning with Function Approximation" paper. Let $\Delta \theta$ and $\Delta \...
2
votes
1answer
439 views

Are model-free and off-policy algorithms the same?

In respect of RL, is model-free and off-policy the same thing, just different terminology? If not, what are the differences? I've read that the policy can be thought of as 'the brain', or decision ...
2
votes
0answers
35 views

Can the importance sampling estimator have a non-stationary behaviour policy even if the target policy is stationary?

The inverse propensity score (IPS) estimator, which is used for off-policy evaluation in a contextual bandit problem, is well explained in the paper Doubly Robust Policy Evaluation and Optimization. ...
3
votes
1answer
64 views

What is a non-starving policy in reinforcement learning?

In the paper, Eligibility Traces for off-Policy Policy Evaluation (2010), by Doina Precup et al., mentioned the term "non-starving" many times. The specific use of the term was like "non-starving ...
1
vote
1answer
33 views

Do I need to store the policy for RL?

I am creating a zero-sum game with RL and wondered if I need to store the policy, or if there are other RL methods that produce similar results (consistently beating the human player) without the need ...
3
votes
1answer
132 views

Understanding the n-step off-policy SARSA update

In Sutton & Barto's book (2nd ed) page 149, there is the equation 7.11 I am having a hard time understanding this equation. I would have thought that we should be moving $Q$ towards $G$, where $...
1
vote
1answer
61 views

On-policy distribution for Emphatic TD

The book by Sutton and Barto discussed in section 11.8 that the convergence of off-policy TD function approximation can be improved by correcting for distribution of states encountered. The section ...
3
votes
1answer
1k views

What is the relation between online learning and on-policy algorithms?

In the context of RL, there is the notion of on-policy and off-policy algorithms. I roughly understand the difference between on-policy and off-policy algorithms. Moreover, in RL, there's also the ...
6
votes
1answer
118 views

How do I compute the variance of the return of an evaluation policy using two behaviour policies?

Suppose there is an evaluation policy called $\pi_{e}$ and there are two behavior policies $\pi_{b1}$ and $\pi_{b2}$. I know that it is possible to estimate the return of policy $\pi_{e}$ through ...
2
votes
1answer
101 views

Why is the actor-critic algorithm limited to using on-policy data?

Why is the actor-critic algorithm limited to using on-policy data? Or can we use the actor-critic algorithm with off-policy data?
4
votes
1answer
505 views

Why is the n-step tree backup algorithm an off-policy algorithm?

In reinforcement learning book from Sutton & Barto (2018 edition), specifically in section 7.5 of the book, they present an n-step off-policy algorithm that doesn't require importance sampling ...
4
votes
2answers
813 views

What is the difference between on and off-policy deterministic actor-critic?

In the paper Deterministic Policy Gradient Algorithms, I am really confused about chapter 4.1 and 4.2 which is "On and off-policy Deterministic Actor-Critic". I don't know what's the difference ...
9
votes
1answer
2k views

Do off-policy policy gradient methods exist?

Do off-policy policy gradient methods exist? I know that policy gradient methods themselves using the policy function for sampling rollouts. But can't we easily have a model for sampling from the ...