Questions tagged [off-policy-methods]

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
1 vote
0 answers
23 views

off-policy Monte Carlo learning: Why is Probability of Sampling a Trajectory the same as Having a return?

In Sutton and Barto's RL book, in the section for off-policy learning, we would like to find the expected value of the random variable $G_t$, given $S_t = s$ under our target policy: $$E_{\pi}[G_t|S_t ...
1 vote
0 answers
63 views

Why Soft Actor-Critic (SAC) uses a double Q trick?

Twin Delayed DDPG (TD3) uses a double Q trick since the policy is deterministic like in DDPG, which is to mitigate the maximum overestimation bias in DDPG. However, in SAC, the policy is stochastic, ...
1 vote
0 answers
24 views

How does off-policy monte carlo explore and converge?

Premises to question: Behavior Policy: e-greedy (stochastic) & Target Policy: greedy, (deterministic) Importance Sampling Included In Off-policy Monte-Carlo control, the behavior policy chooses ...
0 votes
0 answers
20 views

Why would it be easy to evaluate a probability, when it is hard to sample from for importance sampling?

Suppose we want to perform importance sampling where we have trajectories from some behavioral policy $b$, but we want to perform off-policy evaluation. From these prior questions, I understand that ...
0 votes
1 answer
53 views

Has there been a study done in tuning hyper-parameters for off-policy reinforcement learning?

I am interested in learning about hyper-parameter tuning for off-policy reinforcement learning (specifically DQN). Could someone point me to papers published or empirical observations in this area?
0 votes
0 answers
39 views

Is Bayesian Reinforcement Learning used as off-policy RL?

Are there any examples where Bayesian Reinforcement Learning is used as off-policy RL? What are the pros and cons of using it for this purpose?
2 votes
0 answers
59 views

Why do off-policy algorithms suffer from worse computational or time efficiency compared to on-policy algorithms?

When I run Soft-Actor-Critic (off-policy) in my Environment, the calculation of gradient updates takes almost twice the time compared to using PPO (on-policy). I also saw that ACER has a higher time ...
  • 95
1 vote
1 answer
49 views

Can off-policy algorithms benefit from the parallelization?

On-policy algorithms, such as A2C, A3C and PPO, leverage massive parallelization to achieve state of the art results. However, I’ve never come across parallelization efforts when it comes to the off-...
  • 299
1 vote
0 answers
52 views

Why does importance sampling ratio start and end one step later in off-policy SARSA given in Sutton-Barto's RL book?

In Sutton & Barto's RL book (page 149) they say: Sarsa update can be completely replaced by a simple off-policy form $Q_{t+n}(S_t,A_t)=Q_{t+n−1}(S_t,A_t) + \rho_{t+1:t+n} [G_{t:t+n} − Q_{t+n−1}(...
1 vote
0 answers
48 views

Proper way to count environment steps / frames in distributed RL architecture for algorithms like CLEAR or LASER => modified impala with replay

In classical - on-policy - vtrace/Impala algorithm env_steps are incremented every training iteration like this : ...
2 votes
1 answer
112 views

How does this TD(0) off-policy value update formula work?

The update formula for the TD(0) off-policy learning algorithm is (taken from these slides by D. Silver for lecture 5 of his course) $$ \underbrace{V(S_t)}_{\text{New value}} \leftarrow \underbrace{V(...
  • 133
2 votes
1 answer
39 views

How to prove importance sampling ratio is uncorrelated with action-value (or state-value) estimate?

In Sutton & Barto (2nd edition), the following is mentioned on page 150 (p. 172 of the pdf), section 7.4: the importance sampling ratio has expected value one (Section 5.9) and is uncorrelated ...
2 votes
0 answers
49 views

Doubt in Sutton & Barto's off-policy Monte Carlo control algorithm

The algorithm is described as below: My understanding: In the third last step, we act greedily w.r.t $Q$. Since we use importance sampling, this $Q \approx Q_\pi$. However, in the next step, whenever ...
1 vote
1 answer
64 views

Which policy has to be followed by a player while construction of its own Q-table?

Consider the scenario, where there are two players. One of the players perform the action randomly, whereas I want second player as a Q-player. I mean, the player selects a best action from the Q-...
  • 187
0 votes
1 answer
161 views

Which policy do I need to use in updating Q function?

Policy function can be of two types: deterministic policy and stochastic policy. Deterministic policy is of the form $\pi : S \rightarrow A$ Stochastic policy is defined using conditional probability ...
  • 187
2 votes
1 answer
116 views

In off-policy MC control algorithm by Sutton & Barto, why do we perform a last update when sample action is inconsistent with target policy?

I have a question about the $W$ term in the off-policy MC control algorithm on Page 111 of Sutton & Barto. I have also included it in the figure below. My question: shouldn't the check $A_{t} = \...
2 votes
2 answers
199 views

With Monte Carlo off-policy learning what do we correct by using importance sampling?

I do not understand the link of importance sampling to Monte Carlo off-policy learning. We estimate a value using sampling on whole episodes, and we take these values to construct the target policy. ...
3 votes
1 answer
113 views

Why can we take the action $a$ from the next state $s'$ in the max part of the Q-learning update rule, if that action doesn't lead to any reward?

I'm using OpenAI's cartpole environment. First of all, is this environment not Markov? Knowing that, my main question concerns Q-learning and off-policy methods: For me, there is something weird in ...
  • 155
2 votes
1 answer
210 views

Can I add expert data to the replay buffer used by the DDPG algorithm in order to make it converge faster?

I am working on a restricted reinforcement learning environment, i.e. the environment breaks very often (i.e.: the communication between the simulator and reinforcement learning agent breaks after ...
2 votes
1 answer
392 views

Offline/Batch Reinforcement Learning: when to stop training and what agent to select

Context: My team and I are working on a RL problem for a specific application. We have data collected from user interactions (states, actions, rewards, etc.). It is too costly for us to emulate agents....
  • 21
5 votes
1 answer
307 views

Why do we need importance sampling?

I was studying the off-policy policy improvement method. Then I encountered importance sampling. I completely understood the mathematics behind the calculation, but I am wondering what is the ...
4 votes
1 answer
131 views

Why does off-policy learning outperform on-policy learning?

I am self-studying about Reinforcement Learning using different online resources. I now have a basic understanding of how RL works. I saw this in a book: Q-learning is an off-policy learner. An off-...
3 votes
1 answer
105 views

When learning off-policy with multi-step returns, why do we use the current behaviour policy in importance sampling?

When learning off-policy with multi-step returns, we want to update the value of $Q(s_1, a_1)$ using rewards from the trajectory $\tau = (s_1, a_1, r_1, s_2, a_2, r_2, ..., s_n, a_n, r_n, s_n+1)$. We ...
2 votes
0 answers
83 views

Is Deep SARSA learning a feasible approach?

I noticed that SARSA has been rarely used in the deep RL setting. Usually, the training for DQN is done off-policy. I think one of the major reasons for this is due to greater sample efficiency in ...
  • 1,241
3 votes
0 answers
314 views

In Soft Actor Critic, why is the action sampled from current policy instead of replay buffer on value function update?

While reading the original paper of Soft Actor Critic, I came across on page number 5, under equation (5) and (6) $$ J_{V}(\psi)=\mathbb{E}_{\mathbf{s}_{t} \sim \mathcal{D}}\left[\frac{1}{2}\left(V_{\...
0 votes
0 answers
50 views

Off-policy full-random training in easy-to-explore environment

Let say we are in an environment where a random agent can easily explore all the states of an environment (for example: tic-tac-toe). In those environments, using off-policy algorithm, is it a good ...
  • 266
0 votes
1 answer
31 views

Learning only using off-policy samples

When training policies, is there a reason we need on-policy samples? For expensive simulations, it makes sense to try and reuse samples. Say we're interested in hyperparameter tuning. Can we collect a ...
  • 101
1 vote
0 answers
48 views

How can I derive n-step off-policy temporal difference formula?

I was reading the book "Reinforcement Learning: An Introduction" by Sutton and Barto. In section 7.3, they write the formula for n-step off-policy TD as $$V(S_t) = V(S_{t-1}) + \alpha \rho_{...
3 votes
1 answer
139 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: "...
  • 295
1 vote
0 answers
49 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 <...
  • 11
1 vote
0 answers
48 views

Does importance sampling for off-policy estimation also apply to the case of 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 ...
3 votes
0 answers
49 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)}...
  • 1,241
1 vote
0 answers
59 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). ...
1 vote
0 answers
89 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 ...
  • 207
0 votes
1 answer
138 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 ...
  • 1,241
2 votes
2 answers
571 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
0 answers
61 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 ...
  • 1,241
3 votes
3 answers
349 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 ...
  • 1,241
3 votes
1 answer
184 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 ...
  • 291
1 vote
1 answer
68 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 ...
  • 1,241
1 vote
1 answer
259 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 ...
2 votes
2 answers
733 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
3 answers
102 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
1 answer
524 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
1 answer
74 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 ...
6 votes
1 answer
2k 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 ...
  • 63
2 votes
1 answer
99 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
1 answer
44 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 \...
3 votes
1 answer
1k 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 ...
  • 583
2 votes
0 answers
57 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. ...
  • 207