Questions tagged [reinforce]

For questions related to the REINFORCE algorithm (or update rule), which is a policy gradient algorithm, that is, an algorithm which estimates the policy directly (that is, without first estimating any value function).

Filter by
Sorted by
Tagged with
1 vote
1 answer
26 views

How to implement PPO without using a Critic

I am using the standard policy gradient algorithm, REINFORCE, to solve a RL problem and was thinking about implementing Proximal Policy Optimization (PPO) to increase the sample efficiency of my ...
user avatar
  • 13
1 vote
0 answers
67 views

Why is an action-independent baseline required to reduce variance?

I'm learning policy gradient methods. I encountered the REINFORCE algorithm with variance reduction with a baseline. I see we can use a constant or state-dependent function (e.g value function) but ...
user avatar
  • 49
0 votes
0 answers
55 views

How to pass the rewards in zero-sum multiplayer context when using REINFORCE?

Suppose there are two players in my zero-sum game and they play in a row like chess. And I want to learn the policy function using the REINFORCE algorithm. I have doubts about passing reward values in ...
user avatar
  • 3,099
1 vote
1 answer
59 views

Is it the high probability action that is always selected by the agent in REINFORCE algorithm?

Consider the following algorithm from the textbook titled Reinforcement Learning: An Introduction (second edition) by Richard S. Sutton and Andrew G. Bart While playing the game for the generation of ...
user avatar
  • 3,099
0 votes
0 answers
69 views

FrozenLake-v0 not training using REINFORCE

I am implementing a simple REINFORCE (policy gradient) algorithm for openAI's FrozenLake-v0 environment. However, it does not seem to learn anything at all. I have used the same neural architecture ...
user avatar
  • 101
2 votes
0 answers
73 views

REINFORCE differentiation on sum or single value?

I'm currently learning Policy-gradient Methods for RL and encountered REINFORCE algorithm. I learned from this site : https://towardsdatascience.com/policy-gradient-methods-104c783251e0 that the ...
user avatar
  • 49
0 votes
0 answers
22 views

Why use two different embeddings for actions in this paper?

I was reading this paper Top-𝐾 Off-Policy Correction for a REINFORCE Recommender System and I'm wondering is there a particular advantage to use different embeddings for actions, one embedding is ...
user avatar
  • 509
0 votes
0 answers
146 views

How to normalize rewards in REINFORCE?

I'm trying to solve a reinforcement learning problem using a Monte Carlo policy gradient algorithm and, more specifically, REINFORCE, with rewards attributed to individual moves instead of applied to ...
user avatar
  • 121
2 votes
1 answer
102 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 ...
user avatar
1 vote
1 answer
90 views

How does the neural network learn when used in the REINFORCE algorithm?

As per my understanding, you run an entire episode, which contains many steps, and then back-propagate using just a single loss value. How does the neural network learn to differentiate between good ...
user avatar
1 vote
1 answer
159 views

Why does the implementation of REINFORCE algorithm minimize the gradient term but not the loss?

I read the book "Foundation of Deep Reinforcement Learning, Laura Graesser and Wah Loon Keng", and when I go through the REINFORCE algorithm, they show the objective function: $$ J\left(\...
user avatar
0 votes
1 answer
117 views

How to simplify policy gradient theorem to $E_{\pi}[G_t \frac{\nabla_{\theta}\pi(a|S_t,\theta)}{\pi(a|S_t,\theta)}]$?

In "Introduction to Reinforcement Learning" (Richard Sutton) section 13.3(Reinforce algorithm) they have the following equation: \begin{align} \nabla_{\theta}J &\propto \sum_s \mu(s) \...
user avatar
2 votes
0 answers
31 views

What is the name of this algorithm that estimates the gradient with an average by sampling from a distribution?

Consider maximizing the function $R(w)$ with parameter $w$ using gradient ascent. However, we don't know the gradient $\nabla_wR(w)$ formula. Now suppose $w$ is sampled from a probability distribution ...
user avatar
  • 121
1 vote
1 answer
136 views

It is mathematically correct to use a Policy Gradient method for 1-step trajectories?

I have come across a Google paper that uses the REINFORCE algorithm (a Policy Gradient Method) for a case where the trajectory of the episodes it proposes would be ...
user avatar
  • 171
3 votes
0 answers
88 views

How to implement REINFORCE with eligibility traces?

The pseudocode below is taken from Barto and Sutton's "Reinforcement Learning: an introduction". It shows an actor-critic implementation with eligibility traces. My question is: if I set $\...
user avatar
3 votes
2 answers
80 views

What does the parameter $y$ stand for in function $g(y,\mu,\sigma)$ related to REINFORCE algorithm?

I am wondering what the parameter $y$ in the function $g(y,\mu,\sigma)=\frac{1}{(2\pi)^{1/2}\sigma}e^{-(y-\mu)^{2/2\sigma^2}}$ stands for in Section 6 (page 14) of the paper introducing the REINFORCE ...
user avatar
  • 705
1 vote
0 answers
160 views

Are actions deterministic during testing in continuous action space PPO?

In a continuous action space (for instance, in PPO, TRPO, REINFORCE, etc.), during training, an action is sampled from the random distribution with $\mu$ and $\sigma$. This results in an inherent ...
user avatar
  • 167
1 vote
0 answers
35 views

Why do we use big batch/epoch size in policy gradient methods (vpg specifically)?

I am re-implementing vpg and using Spinning Up as reference implementation. I noticed that the default epoch size is 4000. I also see cues in papers that big batch size is quite standard. My ...
user avatar
  • 26
2 votes
0 answers
131 views

Why is TD(0) not converging to the optimal policy?

I am trying to implement the basic RL algorithms to learn on this 10x10 GridWorld (from REINFORCEJS by Kaparthy). Currently I am stuck at TD(0). No matter how many episodes I run, when I am updating ...
user avatar
  • 121
1 vote
0 answers
182 views

What adapts an algorithm to continuous or to discrete action spaces?

Some RL algorithms can only be used for environments with continuous action spaces (e.g TD3, SAC), while others only for discrete action spaces (DQN), and some for both REINFORCE and other policy ...
user avatar
  • 509
1 vote
0 answers
82 views

If REINFORCE agent suddenly drops, how do I verify if it's due to catastrophic forgetting?

I am using the default implementations of REINFORCE, DQN and c51 available from the tf.agents repo (links). As you can see, DQN manages to improve performance while REINFORCE seems to suffer from ...
user avatar
1 vote
0 answers
122 views

SeqGAN - Policy gradient objective function interpretation

Could someone clear my doubt on the loss function used in SeqGAN paper . The paper uses policy gradient method to train the generator which is a recurrent neural network here. Have I interpreted the ...
user avatar
7 votes
1 answer
373 views

Which loss function should I use in REINFORCE, and what are the labels?

I understand that this is the update for the parameters of a policy in REINFORCE: $$ \Delta \theta_{t}=\alpha \nabla_{\theta} \log \pi_{\theta}\left(a_{t} \mid s_{t}\right) v_{t}, $$ where $v_t$ is ...
user avatar
  • 470
3 votes
1 answer
141 views

Why does REINFORCE work at all?

Here's a screenshot of the popular policy-gradient algorithm from Sutton and Barto's book - I understand the mathematical derivation of the update rule - but I'm not able to build intuition as to why ...
user avatar
2 votes
0 answers
55 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 ...
user avatar
  • 121
1 vote
1 answer
102 views

Why is the "reward to go" replaced by Q instead of V, when transitioning from PG to actor critic methods?

While transitioning from simple policy gradient to the actor-critic algorithm, most sources begin by replacing the "reward to go" with the state-action value function (see this slide 5). I am not ...
user avatar
  • 181
3 votes
1 answer
764 views

Can I apply DQN or policy gradient algorithms in the contextual bandit setting?

I have a problem which I believe can be described as a contextual bandit. More specifically, in each round, I observe a context from the environment consisting of five continuous features, and, ...
user avatar
  • 155
2 votes
1 answer
186 views

How long should the state-dependent baseline for policy gradient methods be trained at each iteration?

How long should the state-dependent baseline be trained at each iteration? Or what baseline loss should we target at each iteration for use with policy gradient methods? I'm using this equation to ...
user avatar
2 votes
0 answers
52 views

Can a typical supervised learning problem be solved with reinforcement learning methods?

Let's say I want to teach a neural to classify images, and, for some reason, I insist on using reinforcement learning rather than supervised learning. I have a dataset of images and their matching ...
user avatar
3 votes
0 answers
92 views

Understanding the TensorFlow implementation of the policy gradient method

I was trying to understand the implementation of a basic policy gradient (REINFORCE) method using TensorFlow. I think I got almost everything. The only thing that still bothers me is the loss function ...
user avatar
  • 31
4 votes
1 answer
80 views

How can I sample the output distribution multiple times when pruning the filters with reinforcement learning?

I was reading the paper Learning to Prune Filters in Convolutional Neural Networks, which is about pruning the CNN filters using reinforcement learning (policy gradient). The paper says that the input ...
user avatar
1 vote
1 answer
70 views

Is there a good and easy paper to code policy gradient algorithms (REINFORCE) from scratch?

I am interested in learning about policy gradient algorithms and REINFORCE. Can you suggest a good and easy paper that I can use to code them from scratch?
user avatar
  • 161
5 votes
2 answers
553 views

How to calculate the advantage in policy gradient functions?

From my understanding of the REINFORCE policy gradient method, we gently nudge the probabilities of actions based on the advantages. More specifically, the positive advantages increase the ...
user avatar
2 votes
1 answer
187 views

What is the difference between Sutton's and Levine's REINFORCE algorithm?

I followed the videos/slides of Berkley RL course, but now I am a bit confused when implementing it. Please see the picture below. In particular, what does $i$ represent in the REINFORCE algorithm? ...
user avatar
  • 223
3 votes
1 answer
161 views

Purpose of using actor-critic algorithms under deterministic MDP dynamics?

One of the main disadvantages of the MC Policy Gradient algorithm (REINFORCE) as described say here is the fact that it has high variance (returns, which we sample, will significantly vary from ...
user avatar
  • 129
1 vote
1 answer
298 views

How does the policy gradient's derivative work?

I am trying to understand the policy gradient method using a PyTorch implementation and this tutorial. My first question is about the end result of this gradient derivation, \begin{aligned} \nabla \...
user avatar
  • 946
4 votes
1 answer
612 views

Should the policy parameters be updated at each time step or at the end of the episode in REINFORCE?

REINFORCE is a Monte Carlo policy gradient algorithm, which updates weights (parameters) of policy network by generating episodes. Here's a pseudo-code from Sutton's book (which is same as the ...
user avatar
4 votes
1 answer
146 views

Why is my implementation of REINFORCE algorithm for portfolio optimization not converging?

I'm trying to implement the Reinforce algorithm (Monte Carlo policy gradient) in order to optimize a portfolio of 94 stocks on a daily basis (I have suitable historical data to achieve this). The idea ...
user avatar
  • 129
3 votes
1 answer
155 views

Confusion about temporal difference learning [closed]

I have a couple of small questions about the David Silver lecture about reinforcement learning, lecture slides (slides 23, 24). More specifically it is about the temporal difference algorithm: $$V(...
user avatar
  • 165
4 votes
0 answers
332 views

What is the simplest policy gradient method to implement for a problem continuous action space?

I have a problem I would like to tackle with RL, but I am not sure if it is even doable. My agent has to figure out how to fill a very large vector (let's say from 600 to 4000 in the most complex ...
user avatar
  • 145
1 vote
0 answers
39 views

How is computed the gradient with respect to each output node from a loss value?

newbie here. I am studying the REINFORCE method in "Deep Reinforcement Learning Hands-On". I can't understand how, after computing the loss of the episode, that loss is backpropagated in a NN with ...
user avatar
3 votes
1 answer
229 views

How is REINFORCE used instead of Backpropagation?

In neural networks with stochastic layers I've seen the use of the REINFORCE estimator for estimating the gradient (because it can't be computed directly). Some such examples are Show, Attend and ...
user avatar
  • 131
8 votes
1 answer
969 views

How is the policy gradient calculated in REINFORCE?

Reading Sutton and Barto, I see the following in describing policy gradients: How is the gradient calculated with respect to an action (taken at time t)? I've read implementations of the algorithm, ...
user avatar
  • 499
1 vote
0 answers
288 views

Policy gradient loss for neural network training

Say i want to train a neural network with 10 classes as outputs and use categorical_cross_entropy as a loss function in keras. This will try to fit the training ...
user avatar
  • 119
7 votes
3 answers
2k views

Is REINFORCE the same as 'vanilla policy gradient'?

I don't know what people mean by 'vanilla policy gradient', but what comes to mind is REINFORCE, which is the simplest policy gradient algorithm I can think of. Is this an accurate statement? By ...
user avatar
  • 311
3 votes
1 answer
177 views

How is equation 8 derived in the paper "Self-critical sequence training for image captioning"?

In the paper "Self-critical sequence training for image captioning", on page 3, they define the loss function (of the parameters $\theta$) of an image captioning system as the negative expected reward ...
user avatar
8 votes
2 answers
1k views

Why are lambda returns so rarely used in policy gradients?

I've seen the Monte Carlo return $G_{t}$ being used in REINFORCE and the TD($0$) target $r_t + \gamma Q(s', a')$ in vanilla actor-critic. However, I've never seen someone use the lambda return $G^{\...
user avatar
16 votes
3 answers
2k views

Why does the discount rate in the REINFORCE algorithm appear twice?

I was reading the book Reinforcement Learning: An Introduction by Richard S. Sutton and Andrew G. Barto (complete draft, November 5, 2017). On page 271, the pseudo-code for the episodic Monte-Carlo ...
user avatar
37 votes
5 answers
13k views

How should I handle invalid actions (when using REINFORCE)?

I want to create an AI which can play five-in-a-row/Gomoku. I want to use reinforcement learning for this. I use the policy gradient method, namely REINFORCE, with baseline. For the value and policy ...
user avatar