Questions tagged [reinforcement-learning]

For questions related to reinforcement learning, i.e. a machine learning technique where we imagine an agent that interacts with an environment (composed of states) in time steps by taking actions and receiving rewards (or reinforcements), then, based on these interactions, the agent tries to find a policy (i.e. a behavioural strategy) that maximizes the cumulative reward (in the long run), so the goal of the agent is to maximize the reward.

Filter by
Sorted by
Tagged with
0
votes
1answer
28 views

Q-learning agent stuck at taking same actions

I have created my own RL environment where I have a 2-dimensional matrix as a state space, the rows represent the users that are asking for a service, and 3 columns representing 3 types of users; so ...
1
vote
0answers
24 views

How can I evaluate a reinforcement learning algorithm over an entire problem space?

I am working on implementing an RL agent and I want to demonstrate its effectiveness over a bounded problem space. The setting is essentially a queueing network and so it can be represented as a graph....
3
votes
1answer
40 views

Improving DQN with fluctuations

Hello :) I'm pretty new to this community, so let me know if I posted anything incorrectly and I'll try to change it. I'm working on the project which aim is to create self-driving agent in CARLA. I ...
2
votes
2answers
39 views

How should I define the reward function to solve the Wumpus game with deep Q-learning?

I'm writing a DQN agent for the Wumpus game. Is the reward function to train the Q-networks (target network and policy) the same as the score of the game, i.e. +1000 for picking up gold, -1000 for ...
1
vote
0answers
37 views

Which Reinforcement learning model to use?

Suppose we are training an environment with 2 collaborative agents with Reinforcement Learning. We define the following example: There is a midfielder and a striker. The midfielder's reward depends on ...
1
vote
0answers
26 views

Dynamically adapting activation function

I am training a network through reinforcement learning. The policy network learns rotations, but depending on the actual input (state), the output of the network should be restricted to be in certain ...
1
vote
0answers
52 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 ...
1
vote
1answer
45 views

How to create a Q-Learning agent when we have a matrix as an action space?

I have a 2-dimentional matrix as an action space, the rows being a resource to be allocated, and the columns are the users that we will allocate the resources to. (I built my own RL environment) The ...
1
vote
1answer
25 views

How to define Agar.io state and action space?

I am trying to implement an AI bot for my Agar.io clone using deep neural network. However, I am struggling with the state and action space of the AI bot. Because the bot can take real number for ...
1
vote
1answer
39 views

In the definition of the state-action value function, what is the random variable we take the expectation of?

I know that $$\mathbb{E}[g(X) \mid A] = \sum\limits_{x} g(x) p_{X \mid A}(x)$$ for any random variable $X$. Now, consider the following expression. $$\mathbb{E}_{\pi} \left[ \sum \limits_{k=0}^{\infty}...
1
vote
1answer
33 views

Training while predicting on dataset

I have been trying to figure out whether if I train a model and then while predicting is it possible to train images too just like humans Somehow converting valid images to the dataset by asking us ...
2
votes
0answers
25 views

Problems with gradient-biased actor critic methods

To my knowledge, there are at least 6 different variants of Actor Critic: \begin{array}{l l l l} \text{actor gradient} & \text{critic gradient} & \text{actor gradient biased} & \text{name} ...
2
votes
0answers
27 views

What exactly does meta-learning in reinforcement learning setting mean?

We can use DDPG to train agents to stack objects. And stacking objects can be viewed as first grasping followed by pick and place. In this context, how does meta-reinforcement learning fit? Does it ...
3
votes
1answer
107 views

How to determine if Q-learning has converged in practice?

I am using Q-learning and SARSA to solve a problem. The agent learns to go from the start to the goal without falling in the holes. At each state, I can choose the action corresponding to the maximum ...
2
votes
1answer
32 views

Evaluate model multiple times in loss function? Is this reinforcement learning?

I am interested in models that exhibit behavior. My goal is a model that survives indefinitely on a two dimensional resource landscape. One dimension represents the location (0 to 1) and the second ...
3
votes
2answers
62 views

What happens when an opponent a neural network is playing with does not obey the rules of the game (i.e. cheats)?

For example, if AlphaZero plays with an opponent who has a right to move chess figures any way she wants, or make more than 1 move in a turn? Will a neural network adapt to that, as it adapted to an ...
1
vote
1answer
69 views

Reinforcement learning simple problem: agent not learning, wrong action

I am pretty new to RL and I am trying to code a simple RL task with pytorch. The goal/task is the following: The initial state is $t_o$ and the agent takes an action $\Delta_t$: $t_o +\Delta_t = t_1$. ...
2
votes
0answers
29 views

What is the return-to-go in reinforcement learning?

In reinforcement learning, the return is defined as some function of the rewards. For example, you can have the discounted return, where you multiply the rewards received at later time steps by ...
3
votes
0answers
46 views

Difficulty in agent's learning with increasing dimensions of continuous actions

I have been working on some RL project, where the policy is controlling the robot using its joint angles.Throughout the project I have noticed some phenomenon, which caught my attention. I have ...
4
votes
1answer
114 views

Is the state transition matrix known to the agents in a Markov decision processes?

The question is more or less in the title. A Markov decision process consists of a state space, a set of actions, the transition probabilities and the reward function. If I now take an agent's point ...
0
votes
1answer
26 views

How to train the NN of simple agents given a reward system?

I'm not an expert in AI or NN, I gathered most of the information I have from the internet, and I'm looking for advice and guidance. I'm trying to design a NN that is going to be used by all the ...
2
votes
1answer
36 views

Why is the fraction of time spent in state $s$, $\mu(s)$, not in the update rule of the parameters?

I am reading "Reinforcement Learning: An Introduction (2nd edition)" authored by Sutton and Barto. In Section 9, On-policy prediction with approximation, it first gives the mean squared ...
2
votes
1answer
24 views

How do we derive the expression for average reward setting in continuing tasks?

In the average reward setting we have: $$r(\pi)\doteq \lim_{h\rightarrow\infty}\frac{1}{h}\sum_{t=1}^{h}\mathbb{E}[R_{t}|S_0,A_{0:t-1}\sim\pi]$$ $$r(\pi)\doteq \lim_{t\rightarrow\infty}\mathbb{E}[R_{t}...
1
vote
2answers
34 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 ...
3
votes
2answers
73 views

Why do all states appear identical under the function approximation in the Short Corridor task?

This is the Short Corridor problem taken from the Sutton & Barto book. Here it's written: The problem is difficult because all the states appear identical under the function approximation But ...
0
votes
0answers
36 views

Variance of the Gaussian policy is not decreasing while training the agent using Soft Actor-Critic method

I've written my own version of SAC(v2) for a problem with continuous action space. While training, the losses for the value network and both q functions steadily decrease down to 0.02-0.03. The loss ...
2
votes
1answer
51 views

What's the difference between estimation and approximation error?

I'm unable to find online, or understand from context - the difference between estimation error and approximation error in the context of machine learning (and, specifically, reinforcement learning). ...
1
vote
0answers
39 views

What are the disadvantages of actor-only methods with respect to value-based ones?

While the advantages of actor-only algorithms, the ones that search directly the policy without the use of the value function, are clear (possibility of having a continuous action space, a stochastic ...
3
votes
1answer
52 views

Can we stop training as soon as epsilon is small?

I'm new to reinforcement learning. As it is common in RL, $\epsilon$-greedy search for the behavior/exploration is used. So, at the beginning of the training, $\epsilon$ is high, and therefore a lot ...
3
votes
1answer
81 views

What is the loss for policy gradients with continuous actions?

I know with policy gradients used in an environment with a discrete action space are updated with $$ \Delta \theta_{t}=\alpha \nabla_{\theta} \log \pi_{\theta}\left(a_{t} \mid s_{t}\right) v_{t} $$ ...
2
votes
0answers
31 views

Why is it necessary to divide the priority range according to the batch size in Prioritized Experience Replay?

According to DeepMinds's paper Prioritized Experience Replay (2016), one should equally divide the priority range $[0, p_\text{total}]$ into $k$ ranges, where $k$ is the size of the batch, and sample ...
1
vote
1answer
48 views

Why do my rewards reduce after extensive training using D3QN?

I am running a drone simulator for collision avoidance using a slight variant of D3QN. The training is usually costly (runs for at least a week) and I have observed that reward function gradually ...
1
vote
1answer
48 views

Chess Neural Network - Most Optimal Input vector/matrix?

I'm wanting to build a NN that can create a policy for each possible state. I want to combine this with MCTS to eliminate randomness so when expansion occurs, I can get the probability of the move to ...
0
votes
0answers
13 views

How to design the step() method in a custom-built environment when the action space is a 2-dimentional matrix?

I have an action space that is a matrix. I am struggling with finding how to choose how to take the action when the number of possible actions is huge.
0
votes
1answer
29 views

How to let the agent choose how to populate a state space matrix in RL (using python)

I have an agent (drone) that has to allocate subchannels for different types of User Equipment. I have represented the subchannel allocation with a 2-dimentional binary matrix, that is initialized to ...
3
votes
0answers
31 views

Why weighting by lambda that sums to 1 ensures convergence in eligibility trace?

In Sutton and Barto's Book in chapter 12, they state that if weights sum to 1, then an equation's updates have "guaranteed convergence properties". Actually why it ensures convergence? There ...
2
votes
1answer
31 views

Why is regret so defined in MABs?

Consider a multi-armed bandit(MAB). There are $k$ arms, with reward distributions $R_i$ where $1 \leq i \leq k$. Let $\mu_i$ denote the mean of the $i^{th}$ distribution. If we run the multi-armed ...
1
vote
0answers
9 views

Relation between a value function of an MDP and a value function of the corresponding latent MDP

In paper "DeepMDP: Learning Continuous Latent Space Models for Representation Learning", Gelada et al. state in the beginning of section 2.4 The degree to which a value function of $\bar{\...
1
vote
2answers
77 views

How does one know that a problem is “model-free” in reinforcement learning?

Consider this slide from a Stanford lecture on reinforcement learning. It states that a model is the agent's representation of how the world changes in response to the agent's action. I've been ...
1
vote
1answer
45 views

Is this ML task possible?

What I want to do is from an Internet challenge to transform any given image into the Polish flag using the available filters and crop tool on the iPhone camera app. Here's an example. There aren't ...
2
votes
0answers
13 views

Mapping given probabilities to empirical probabilities

Consider following problem statement: You have given $n$ actions. You can perform any of them. Each action gives you success with some probability. The challenge is to perform given finite number of ...
1
vote
1answer
37 views

What are the strategies for computationally heavy environments or long-time waiting environments?

I have an environment that is computationally heavy (takes several seconds to get a reward and next state). This limits reinforcement capability, due to poor sampling of the problem. There is any ...
4
votes
2answers
213 views

What is the meaning of “exploration” in reinforcement and supervised learning?

While exploration is an integral part of reinforcement learning (RL), it does not pertain to supervised learning (SL) since the latter is already provided with the data set from the start. That said, ...
1
vote
0answers
38 views

How many types of variational auto-encoders are there?

I have been studying about auto-encoders and variational auto-encoders. I would like to know how many variants of VAEs are there today. If there are many variants, can they be used for feature ...
2
votes
1answer
49 views

What are proxy reward functions?

The understanding I have is that they somehow adjust the objective to make it easier to meet, without changing the reward function. ... the observed proxy reward function is the approximate solution ...
1
vote
1answer
37 views

Pytorch Deep q network not learning and step not stepping towards target

I am trying to create a simple deep q network for rl with conv2d layers. I can’t figure out what I am doing wrong, and the only thing I can see that doesn’t seem right is when I get the model ...
1
vote
0answers
22 views

Is there a UCB type algorithm for linear stochastic bandit with lasso regression?

Why is there no upper confidence bound algorithm for linear stochastic bandits that uses lasso regression in the case that the regression parameters are sparse in the features? In particular, I don't ...
0
votes
1answer
51 views

What is the search depth of AlphaGo and AlphaGo Zero?

I cannot find reliable sources but someone says it is 40 moves and someone else says it is 50+ moves. I read their papers and they use value function (NN) and policy function to trim the tree, so more ...
1
vote
1answer
29 views

What framework for a project with a custom environment?

I'm planning an RL project and I have to decide which RL framework do I use if any at all. The project has a highly custom environment, and testing different algorithms will be required to obtain ...
5
votes
1answer
107 views

What, exactly, does the REINFORCE update equation mean?

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 𝑣𝑡 is ...

1
2 3 4 5
29