Questions tagged [q-learning]

Use for questions that involve Q-learning, where Q is the value of a particular next action among a set of possible actions, based on a specified function of each action and its projected result.

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

Unique game problem (ML, DP, PP etc)

Looking for a solution to my below game problem. I believe it to require some sort of reinforcement learning, dynamic programming, or probabilistic programming solution, but am unsure... This is my ...
2
votes
1answer
22 views

Will the target network, which is less trained than the normal network, output inferior estimates?

I'm having some trouble understanding some parts of the usage of target networks. I get that having the same network predict the state/action/advantage values for both the current networks can lead ...
3
votes
0answers
40 views

How can I use Q-learning for inventory decision making?

I am trying to model operational decisions in inventory control. The control policy is base stock with a fixed stock level $S$. That is replenishment orders are placed for every demand arrival to take ...
0
votes
1answer
31 views

Probabilistic action selection in pursuit algorithm

In the Pursuit algorithm (to balance exploration and exploitation), the greedy action has a probability say $p_1$ (updated every episode) of being selected, while the rest have a probability $p_2$ (...
3
votes
1answer
26 views

Is it possible to have a dynamic $Q$-function?

I am trying to use Q-learning for energy optimization. I only wish to have states that will be visited by the learning agent, and, for each state, I have a function that generates possible actions, so ...
1
vote
0answers
29 views

Can multiple reinforcement algorithms be applied to the same system?

Can a system, for instance robotic vehicle, be controlled by more than one reinforcement learning algorithm. I intend to use one to address collision avoidance whereas the other to tackle autonomous ...
2
votes
1answer
39 views

If deep Q learning involves adjusting the value function for a specific policy, then how do I choose the right policy?

I wrote a simple implementation of Flappy Bird in Python, and now I'm trying to train an agent to play it at a reasonable skill level using TFLearn. I feed the network an input vector of size 4: ...
2
votes
0answers
57 views

How does Friend-or-Foe Q-learning intuitively work?

I read about Q-Learning and was reading about multi-agent environments. I tried to read the paper Friend-or-Foe Q-learning, but could not understand anything, except for a very vague idea. What does ...
0
votes
0answers
37 views

Encoding real valued inputs

I have the following issue: I want to train a network (used in a variation of deep q learning that I use for a pricing decision) to predict me the value of a certain state/action combination. The ...
0
votes
0answers
16 views

Why epsilon-greedy hyperparameter is annealed smoothly?

Regarding of DQN, or DQRNN, (reinforcement learning) To me, RL is a process that can be divided into 2 stages: Exploring wide range of paths (acting randomly) Refining the current optimal paths (...
6
votes
1answer
115 views

Does AlphaZero use Q-Learning?

I was reading the AlphaZero paper Mastering Chess and Shogi by Self-Play with a General Reinforcement Learning Algorithm, and it seems they don't mention Q-Learning anywhere. So does AZ use Q-...
2
votes
1answer
34 views

What is the difference between return and expected return?

At a time step $t$, for a state $S_{t}$, the return is defined as the discounted cumulative reward from that time step $t$. If an agent is following a policy (which in itself is a probability ...
2
votes
2answers
41 views

How to stop evaluation phase in reinforcement learning with epsilon-greedy Monte Carlo agent?

I have implemented an epsilon-greedy Monte Carlo reinforcement learning agent like suggested in Sutton and Barto's RL book (page 101). As far as I understood epsilon-greedy agents so far, the ...
-2
votes
1answer
44 views

Problem over DQN Algorithm not converging on snake

I'm using a DQN Algorithm to play Snake. The input of the neural network is a stack of 4 images taken from the games 80x80. The output is an array of 4 values, one for every direction. The problem ...
0
votes
1answer
44 views

Deep Reinforcement Learning: Rewards suddenly dip down

I am working on a deep reinforcement learning problem. The policy network has the same architecture as the one Deepmind published in 'Playing Atari with Deep Reinforcement Learning'. I am also using ...
3
votes
1answer
33 views

How do I represent a multi-dimensional state using a neural network?

I have a set of 15 unique playing cards from a deck of 52 playing cards. A given state is represented by the respective card values in the set of 15 cards, where the card value is a prime number ...
4
votes
1answer
87 views

Q-learning, am I interpreting correctly $Q(s,a) = r + \gamma \max_{a'} Q(s',a')$?

Ok, due to previous question I was pointed to use reinfrocement learning. So far what I understood from random websites is the following: there is a Q(s,a) function involved I can assume my neural ...
0
votes
0answers
14 views

Problems while training a DQN Agent on DSTC dataset

I am trying to create a dialogue policy model on DSTC data. This model takes in a state of the conversation and outputs an act the machine must take. I am creating this model using reinforcement ...
1
vote
1answer
82 views

Choice of inputs features for Snake game

I am designing a neural network using Deep Q-Learning, which teaches an agent how to play Snake (The classic Nokia game from the 90'ies). The goal of the game is to navigate the snake on a playing ...
1
vote
0answers
28 views

High variance in performance of q-learning agents trained with same parameters

I am training an agent to play a simple game using double deep q learning. However, the variance in agent performance is very high, even for agents trained with same model parameters. For example, I ...
1
vote
1answer
39 views

Static or dynamic learning rate (Q-learning)

I have the following code (below), where an agent uses Q-learning (RL) to play a simple game. What appears to be questionable for me in that code is the fixed learning rate. When it's set low, it's ...
4
votes
2answers
94 views

Deciding on a reward per each action in a given state (Q-learning)

I looked for existing posts on Stack Exchange, which kind of answer the questions about the reward system and reward function, but not specifically what I want to ask here, which is how do you ...
5
votes
2answers
97 views

Is Q-Learning suitable for continous (state or action) spaces?

Many examples work with a table based method for Q-Llearning. This may be suitable for discrete state(observation) or actions like a robot in a grid world but is there a way to use Q-Learning for ...
0
votes
0answers
16 views

Measure grid-world environments difference for reinforcement learning

I'd like to measure the difference between 2 grid-worlds to determine the generalization capacity of my agent using tabular Q-learning. Example (OpenAI Frozen Lake) : SFFF FHFH FFFH HFFG and : ...
3
votes
1answer
60 views

Experience Replay Not Always Giving Better Results

I have recently started working on a control problem using a Deep Q Network as proposed by DeepMind (https://arxiv.org/abs/1312.5602). Initially, I implemented it without Experience Replay. The ...
4
votes
0answers
48 views

Inconsistent definitions of the retrace

In Section 4.3 of paper Learning by Playing - Solving Sparse Reward Tasks from Scratch, the authors define Retrace as $$ Q^{ret}=\sum_{j=i}^\infty\left(\gamma^{j-i}\prod_{k=i}^jc_k\right)[r(s_j,a_j)+\...
1
vote
1answer
43 views

Picking a random move in exploitation in Q-Learning

I've been unsure about a principle of Q-Learning, I was hoping someone could clear it up. When a new state is encountered, and thus there are no existing Q values, and that the algorithm decides to ...
1
vote
3answers
47 views

How to stop DQN Q function from increasing during learning?

Following the DQN algorithm with experience replay: We calculate the $loss=(Q(s,a)-(r+Q(s+1,a)))^2$. Assume I have positive but changing rewards. Meaning, $r>0$. Thus, since the rewards are ...
0
votes
1answer
38 views

Encourage Deep Q to seek short-term reward

I understand that gamma is an important factor in determining the rewards for a deep Q agent, however during testing of my network I am noticing that the agent is outputting more actions to "do ...
2
votes
1answer
40 views

Maximum Q value for new state in Q-Learning never exists

I'm working on implementing a Q-Learning algorithm for a 2 player board game. I encountered what I think may be a problem. When it comes time to update the Q value with the Bellman equation (above), ...
3
votes
0answers
37 views

Deep Q-Learning agent poor performing actions. Need help optimizing

I'm trying to make deep q-learning agent from https://keon.io/deep-q-learning My environment looks like this: https://imgur.com/a/OnbiCtV As you can see my agent is a circle and there is one gray ...
4
votes
2answers
72 views

Can DQN perform better than Double DQN?

I'm training both kind of agents against an environment but DQN performs significantly better than Double DQN. As I've saw here, Double DQN use to perform better than DQN. Am I doing something wrong ...
1
vote
2answers
43 views

Can gamma be greater than 1 in a DQN?

If I have a DQN, and I care A LOT about future rewards (moreso than current rewards), can I set gamma to a number greater than 1? Like 1.1 perhaps?
8
votes
2answers
175 views

Why doesn't Q-learning converge when using function approximation?

The tabular Q-learning algorithm is guaranteed to find the optimal $Q$ function, $Q^*$, provided the following conditions regarding the learning rate are satisfied $\sum_{t} \alpha_t(s, a) = \infty$ $...
3
votes
2answers
86 views

Can Q-learning be used in a POMDP?

Can Q-learning (and SARSA) be directly used in a Partially Observable Markov Decision Process (POMDP)? If not, why not? My intuition is that the policies learned will be terrible because of partial ...
1
vote
1answer
41 views

DQN Q-values are static

I am working on a DDQN with 5 LSTM layers and 3 actions as output and state space of 21 features. I am dividing the dataset into episodes of 720 timesteps, for each episode the agent acts greedily for ...
0
votes
0answers
21 views

How to limit actions based on a state [duplicate]

I'm trying to implement DQN using tf-agents for simple environment. So far I have ...
0
votes
0answers
74 views

DQN Q-mean values converge negatively

I'm trying to implement my own DQN. So far I think my code is good, but my Q-values (I'm getting the mean of all the values for every episode) tends to converge near-zero but negatively. It is normal? ...
1
vote
1answer
45 views

How to build a DQN agent which can be trained through interactive learning?

I am trying to create a chatbot whose dialogue policy model will be trained through reinforcement learning. Dialogue Policy is responsible for selecting the action to take based on the given state of ...
1
vote
0answers
47 views

Do we need to reset the DQN network after every episode?

I was going through this implementation of Reinforcement learning where model is being trained to manage the number of bikes at a station. Here, line 78 represents the loop over all episodes (if I ...
1
vote
0answers
53 views

Reinforcement Learning with limited number of episodes

I try to implement RL to a case something like this: This game consist of several rounds. Every round the players need to generate a maze that consists of rooms. There are around 1000 different ...
3
votes
1answer
43 views

Why Q2 is a more or less independant estimate in Twin Delayed DDPG (TD3)?

TD3 is inspired from both double Q-learning and double DQN. In double Q-learning, I understand that Q1 and Q2 are independent because they are trained on different samples. In double DQN, I understand ...
2
votes
1answer
67 views

What are the differences between the DQN variants?

There are several variants of the DQN model. For example, double DQN, duelling DQN, prioritized DQN, distributed prioritized DQN, episodic memory DQN, asynchronous n-step DQN and multiple DQN. What ...
2
votes
0answers
22 views

Hindsight Experience Replay with multiple goals

What if there are multiple goals? For example, let's consider Bit-flipping environment as described in the paper HER with one small change: Now, goal is not some specific configuration, but let's say ...
3
votes
1answer
40 views

Why is the max a non-expansive operator?

In certain reinforcement learning (RL) proofs, the operators involved are assumed to be non-expansive. Why is the $\max$ (and the $\min$), which is e.g. used in Q-learning, a non-expansive operator? ...
0
votes
0answers
17 views

How to serve a deep q network using tensorflow serving?

How to Serve a Deep Q Network using Tensorflow Serving. I have built a Deep Q Network using Multilayer Perceptron. Is it possible to serve it?
1
vote
0answers
28 views

Comparison and understanding of different version of DDQN?

There are several version of DDQN floating around. Sutton gives one that is a simple symmetric random update of the two Q functions. I think other papers (Silver paper for example) use a kind of ...
3
votes
1answer
43 views

How to apply or extend the $Q(\lambda)$ algorithm to semi-MDPs?

I want to model an SMDP such that time is discretized and the transition time between the two states follows an exponential distribution and there would be no reward between the transition. Can I ...
2
votes
1answer
40 views

Is there any grid world dataset or generator for reinforcement learning?

I would like to start programming a multi task reinforcement learning model. For this, I need not just one maze or grid world (or just model-based), but many with different reward functions. So, I am ...
2
votes
1answer
87 views

Is there a way to train an RL agent without any environment?

Following Deep Q-learning from Demonstrations, I'd like to avoid potentially unsafe behavior during early learning by making use of supervised learning with demonstration data. However, the ...