Questions tagged [proofs]

For questions that ask about or call for proofs for specific assertions, whether they be proofs of theorems or corollaries, proofs of concept through working implementation, counter proofs, or counter examples.

Filter by
Sorted by
Tagged with
0 votes
0 answers
23 views

Derivation in paper Deep Neural Networks as Gaussian processes in ICLR 2018

I am trying to understand the derivation of the main equation in the seminal paper titled Deep Neural Networks as Gaussian processes (in ICLR 2018). I have asked this question in https://math....
1 vote
1 answer
91 views

Are these two forms of the state value function the same?

Why are there different forms of the value function in reinforcement learning? Sutton & Barto (2nd edition, equation 3.14) define the state value function as follows $$v_{\pi}(s) = \displaystyle\...
  • 175
2 votes
1 answer
112 views

Is there an error in A* optimality proof Russel-Norvig 4th edition?

In "AI: A Modern Approach", 4th edition, by Russell and Norvig, they give a purported proof that A* is cost-optimal for any admissible heuristic. The given proof seems most certainly wrong. ...
  • 71
0 votes
0 answers
66 views

How to prove that "w will converge to TD fixed point once A is positive definite"

In Reinforcement Learning: An Introduction 2nd edition section 9.4 (p. 206), it says that when we use TD(0) as target and use semi-gradient method to update : In general, $w_t$ will be reduced ...
1 vote
0 answers
153 views

Why does the schema theorem of genetic algorithms hold?

I have been reading about the Schema Theorem - one of the first theorems from the field of evolutionary computing and genetic algorithms, largely responsible for justifying the use of genetic ...
1 vote
0 answers
109 views

Where do the characteristics of self-attention come into play in Linformer's proof that self-attention is low rank?

In Linformer's proof that self-attention is low rank in their paper, I don't see how it doesn't generalize to every matrix. They don't utilize any specifics of self-attention (the entire proof feels ...
  • 2,309
2 votes
0 answers
103 views

Why does TD (0) converge to the MLE solution of the Markov model?

Why does TD (0) converge to the MLE solution of the Markov model? Let's take the Example 6.4 in Sutton and Barto's book as an example. Example 6.4: You are the Predictor Place yourself now in the ...
  • 143
0 votes
1 answer
39 views

How to show $\rho > 0$ when $\rho$ be minimum attainable from $y_n(W^{*T}X_n)$, where $W^*$ the vector that separates the data?

In the book Learning from Data written (by Abu Mostafa), we have the following exercise: Let $\rho$ be minimum attainable from $y_n(W^{*T}X_n)$ where $W^*$ is the vector that separates the data. Show ...
2 votes
1 answer
122 views

What is the derivative of equation 1 in the paper "Conservative Q-Learning for Offline Reinforcement Learning"?

I am looking at the paper Conservative Q-Learning for Offline Reinforcement Learning, but I'm not sure how they proved theorem 3.1. Here is a screenshot of theorem 3.1. In the proof of theorem 3.1 ...
  • 121
0 votes
1 answer
48 views

Policies for which the policy improvement theorem holds

According to Reinforcement Learning (2nd Edition) by Sutton and Barto, the policy improvement theorem states that for any pair of deterministic policies $\pi'$ and $\pi$, if $q_\pi(s,\pi'(s)) \geq v_\...
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 ...
0 votes
0 answers
30 views

Non-locally Electrically Programmable Logic Gates - Technological Advances Progress

Preface: I’d like to clarify that I understand what a relay is and that a PLC uses a fairly conventional microprocessor that only digitally establishes logical logic gate configuration as a digitally ...
3 votes
0 answers
54 views

How to prove Lemma 1.6 in the book "Reinforcement Learning: Theory and Algorithms"

I am trying to prove the following lemma from Reinforcement Learning: Theory and Algorithms on page 8. Lemma 1.6. We have that: $$ \left[(1-\gamma)\left(I-\gamma P^{\pi}\right)^{-1}\right]_{(s, a),\...
5 votes
0 answers
76 views

Proof that there always exists a dominating policy in an MDP

I think that it is common knowledge that for any infinite horizon discounted MDP $(S, A, P, r, \gamma)$, there always exists a dominating policy $\pi$, i.e. a policy $\pi$ such that for all policies $\...
  • 175
2 votes
1 answer
122 views

Why adding a baseline doesn't affect the policy gradient?

On the OpenAI's Spinning Up, they justify the fact that adding a baseline $b(s_t)$ in the policy gradient doesn't change its gradient by saying that this is an immediate consequence of the EGLP Lemma ...
3 votes
1 answer
109 views

How to prove the second form of Bellman's equation?

I'd like to prove this "second form" of Bellman's equation: $v(s) = \mathbb{E}[R_{t + 1} + \gamma v(S_{t+1}) \mid S_{t} = s]$ starting from Bellman's equation: $v(s) = \mathbb{E}[G_{t} \mid ...
  • 509
2 votes
2 answers
211 views

Why is the equation $\mathbb{E} \left[ (Y - \hat{Y})^2 \right] = \left(f(X) - \hat{f}(X) \right)^2 + \operatorname{Var} (\epsilon)$ true?

In the book An Introduction to Statistical Learning, the authors claim (equation 2.3, p. 19, chapter 2) $$\mathbb{E} \left[ (Y - \hat{Y})^2 \right] = \left(f(X) - \hat{f}(X) \right)^2 + \operatorname{...
  • 35k
1 vote
1 answer
65 views

When showing that the policy improvement theorem applies to MC control, why is $q_{\pi_{k}}\left(s, \pi_{k}(s)\right) \geq v_{\pi_{k}}(s)$ true?

When discussing why the policy improvement theorem is true, when we do Monte Carlo control by updating greedily, it says on page 98 of Sutton and Barto's book (2nd edition) that: $$ \begin{aligned} ...
  • 203
2 votes
1 answer
82 views

Is the existence and uniqueness of the state-value function for $\gamma < 1$ theoretical?

Consider the following statement from 4.1 Policy Evaluation of the first edition of Sutton and Barto's book. The existence and uniqueness of $V^{\pi}$ are guaranteed as long as either $\gamma < 1$...
  • 3,251
1 vote
0 answers
38 views

Why is the number of examined nodes $ O(b^{3d/4})$ in $\alpha$-$\beta$ pruning?

I'm taking a course 'Introduction to AI' and, in one of the tutorials, it was written that when pruning the game tree using $\alpha$-$\beta$ boundaries, the number of nodes that will be developed, ...
1 vote
0 answers
38 views

How to prove that a regularisation method simplified a neural network?

There are a few ways to regularise a neural network, for example dropout or the L1. Now, both these methods, and possibly most other regularisation methods, tend to remove from, or simplify the neural ...
  • 206
2 votes
1 answer
87 views

Is $\min(h_1(s),\ h_2(s))$ consistent?

If $h_1(s)$ is a consistent heuristic and $h_2(s)$ is a admissible heuristic, is $\min(h_1(s),\ h_2(s))$ consistent?
  • 21
0 votes
1 answer
470 views

Are hill climbing variations always optimal and complete?

Are hill climbing variations (like steepest ascent hill climbing, stochastic hill climbing, random restart hill climbing, local beam search) always optimal and complete?
user avatar
0 votes
0 answers
35 views

How is the discounted maximum entropy objective obtained for soft-q-learning and SAC

In the soft q-learning paper, they provide an expression for the maximum entropy objective that takes discounting into account. My main question is: can someone explain how they incorporated ...
1 vote
1 answer
79 views

Can the law of iterated expectation be used on the inner expectation of the DQN cost function described in the DQN paper

Is the expression for the DQN cost function, Equation (2) of the DQN paper $$\begin{align}L_1 &= E_{\mu,\pi}\left[\left(y_i - q(s,a;\theta)\right)^2\right]\\ &=E_{\mu,\pi}\left[\left(E_{\...
2 votes
1 answer
150 views

If $h_1(n)$ is admissible, why does A* tree search with $h_2(n) = 3h_1(n)$ return a path that is at most thrice as long as the optimal path?

Consider a heuristic function $h_2(n) = 3h_1(n)$. Where $h_1(n)$ is admissible. Why are the following statements true? $A^*$ tree search with $h_2(n)$ will return a path that is at most thrice as ...
7 votes
2 answers
840 views

How is this Pytorch expression equivalent to the KL divergence?

I found the following PyTorch code (from this link) -0.5 * torch.sum(1 + sigma - mu.pow(2) - sigma.exp()) where mu is the mean ...
3 votes
1 answer
328 views

Is my proof of equation 0.6 in the book "Reinforcement Learning: Theory and Algorithms" correct?

In Sham Kakade's Reinforcement Learning: Theory and Algorithms, this equation (page 17) is used preceding the proof of performance difference lemma. I am attempting to prove equation 0.6. Here is my ...
4 votes
0 answers
75 views

When do two identical neural networks have uncorrelated errors?

In Chapter 9, section 9.1.6, Raul Rojas describes how committees of networks can reduce the prediction error by training N identical neural networks and averaging the results. If $f_i$ are the ...
2 votes
1 answer
113 views

How to prove the formula of eligibility traces operator in reinforcement learning?

I don't understand how the formula in the red circle is derived. The screenshot is taken from this paper
  • 23
2 votes
0 answers
39 views

Does there necessarily exist "dominated actions" in a MDP?

In a Markov Decision Process, is it possible that there exists no "dominated action"? I define a dominated action the following way: we say that $(s,a)$ is a dominated action, if $\forall \...
  • 31
1 vote
1 answer
74 views

How do I prove that the MSE is zero when all predictions are equal to the corresponding labels?

In the back-propogation algorithm, the error term is: $$ E=\frac{1}{2}\sum_k(\hat{y}_k - y_k)^2, $$ where $\hat{y}_k$ is a vector of outputs from the network, $y_k$ is the vector of correct labels (...
5 votes
2 answers
4k views

Is there a proof to explain why XOR cannot be linearly separable?

Can someone explain to me with a proof or example why you can't linearly separate XOR (and therefore need a neural network, the context I'm looking at it in)? I understand why it's not linearly ...
5 votes
2 answers
591 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 ...
3 votes
2 answers
2k views

If uniform cost search is used for bidirectional search, is it guaranteed the solution is optimal?

If uniform cost search is used for both the forward and backward search in bidirectional search, is it guaranteed the solution is optimal?
user avatar
6 votes
1 answer
965 views

Why does a negative reward for every step really encourage the agent to reach the goal as quickly as possible?

If we shift the rewards by any constant (which is a type of reward shaping), the optimal state-action value function (and so optimal policy) does not change. The proof of this fact can be found here. ...
  • 35k
3 votes
2 answers
100 views

Why does (not) the distribution of states depend on the policy parameters that induce it?

I came across the following proof of what's commonly referred to as the log-derivative trick in policy-gradient algorithms, and I have a question - While transitioning from the first line to the ...
2 votes
0 answers
27 views

Do we assume the policy to be deterministic when proving the optimality?

In reinforcement learning, when we talk about the principle of optimality, do we assume the policy to be deterministic?
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_{...
2 votes
2 answers
191 views

Can a computer make a proof by induction?

Can a computer solve the following problem, i.e. make a proof by induction? And why? Prove by induction that $$\sum_{k=1}^nk^3=\left(\frac{n(n+1)}{2}\right)^2, \, \, \, \forall n\in\mathbb N .$$ I'm ...
8 votes
2 answers
1k views

Why are the Bellman operators contractions?

In these slides, it is written \begin{align} \left\|T^{\pi} V-T^{\pi} U\right\|_{\infty} & \leq \gamma\|V-U\|_{\infty} \tag{9} \label{9} \\ \|T V-T U\|_{\infty} & \leq \gamma\|V-U\|_{\infty} \...
  • 181
7 votes
0 answers
216 views

Is the Bellman equation that uses sampling weighted by the Q values (instead of max) a contraction?

It is proved that the Bellman update is a contraction (1). Here is the Bellman update that is used for Q-Learning: $$Q_{t+1}(s, a) = Q_{t}(s, a) + \alpha*(r(s, a, s') + \gamma \max_{a^*} (Q_{t}(s', ...
2 votes
0 answers
59 views

What is the proof that the variance of the gradient estimate in Actor-Critic is smaller than in REINFORCE?

The intuition provided when introducing actor-critic algorithms is that the variance of its gradient estimates is smaller than in REINFORCE as, e.g., discussed here. This intuition makes sense for the ...
  • 121
2 votes
2 answers
184 views

How exactly is $Pr(s \rightarrow x, k, \pi)$ deduced by "unrolling", in the proof of the policy gradient theorem?

In the proof of the policy gradient theorem in the RL book of Sutton and Barto (that I shamelessly paste here): there is the "unrolling" step that is supposed to be immediately clear With ...
  • 362
1 vote
1 answer
104 views

When to use AND and when to use Implies in first-order logic?

I am trying to learn the theory behind first-order logic (FOL) and do some practice runs of converting statements into the form of FOL. One issue I keep running into is hesitating on whether to use an ...
  • 25
3 votes
1 answer
808 views

Proof of Maximization Bias in Q-learning?

In the textbook "Reinforcement Learning: An Introduction" by Richard Sutton and Andrew Barto, the concept of Maximization Bias is introduced in section 6.7, and how Q-learning "over-estimates" action-...
2 votes
0 answers
281 views

What is the proof that "reward-to-go" reduces variance of policy gradient?

I am following the OpenAI's spinning up tutorial Part 3: Intro to Policy Optimization. It is mentioned there that the reward-to-go reduces the variance of the policy gradient. While I understand the ...
1 vote
0 answers
138 views

How do you prove that minimax algorithm outputs a subgame-perfect Nash equilibrium?

At every node, MAX would always move to maximise the minimum payoff while MIN choose to minimise the maximum payoff, hence there is nash equilibrium. By using backwards induction, at every node, MAX ...
6 votes
1 answer
286 views

Is this proof of $\epsilon$-greedy policy improvement correct?

The following paragraph about $\epsilon$-greedy policies can be found at the end of page 100, under section 5.4, of the book "Reinforcement Learning: An Introduction" by Richard Sutton and ...
5 votes
1 answer
579 views

How do I convert an MDP with the reward function in the form $R(s,a,s')$ to and an MDP with a reward function in the form $R(s,a)$?

The AIMA book has an exercise about showing that an MDP with rewards of the form $r(s, a, s')$ can be converted to an MDP with rewards $r(s, a)$, and to an MDP with rewards $r(s)$ with equivalent ...
  • 436