Questions tagged [reward-functions]
For questions about rewards functions (e.g. in the context of reinforcement learning, which may be denoted as $R(s, a)$).
87
questions
0
votes
1
answer
52
views
Why is R(s) more restrictive than R(s, a) in an MDP?
I am quite new to RL. I would like to know why a state-dependent reward function R(s) is more restrictive than a state-action-dependent reward function R(s, a)? And why is it that a policy can be ...
- 11
0
votes
0
answers
45
views
How to handle penalty and reward occurring simultaneously
Assume the following scenario:
We have an agent that acts on an environment where the agent should never take an action that results in him leaving the environment. For example, imagine an agent ...
- 143
0
votes
0
answers
19
views
If the agent is at the same state but at different times and receives a different reward, wouldn't this be violating somehow the MDP assumption?
I've been trying to train an agent, I've received and read suggestions to improve its speed to reach the goal. The suggestion is to use a time penalty, for example, adding $-0.1$ to the reward each ...
0
votes
1
answer
34
views
Could you explain the derivation of the expectation equation of equation 3.6 in Sutton & Barto? [duplicate]
I don't understand the last equality.
Here is my derivation
$r(s,a,s')=\sum_{r\in R} r p(r|s,a,s')=\sum_{r\in R} r \frac{p(s,a,s'|r)p(r)}{p(s,a,s')}$
Could you give me the correct steps to derive them?...
- 195
0
votes
1
answer
79
views
Can a reward function have various cases?
I'm doing a Q-learning algorithm and I'm designing my reward function. Basically I'm working on optimizing a network while changing some parameters. My metric to measure its optimization is the delay ...
- 3
1
vote
0
answers
28
views
What does "shuffle the comparisons into one dataset" mean?
I couldn't understand the wording here.
What does "shuffle the comparisons into one dataset" mean?
How does the method they use don't have $K \choose 2$ forward passes for K completions? Do ...
1
vote
1
answer
56
views
How to setup a reinforcement learning model that changes the values of $x$ to maximize $y$ in $y = f(x)$?
Assuming a relation such that $y = f(x)$, where $y$ represents a scalar and $x \in 20 \times 1$ vector consisting of zeros and ones, I want to set up a reinforcement learning model that changes the ...
- 111
2
votes
0
answers
70
views
In RL, is the quantification of the reward function arbitrary? Does it affect the learning?
There are different ways to set the reward function, such as extrinsic (externally provided rewards), intrinsic (the rewards are generated by the agents themselves based on their internal state and ...
- 21
0
votes
1
answer
113
views
Will my Q values keep going up forever?
In Q-learning,the q values can be updated by the bellman equation. What happens with my Q values is that they keep going up forever, in accordance with the more I train. After 10,000 training episodes,...
- 1
1
vote
1
answer
183
views
Is it necessary to have a constant reward in the terminal state?
I have downloaded the grid world project form this link. I have executed the project multiple times using:
python gridworld.py -k 20 -a q -r -0.2 -s 90
I have ...
- 111
1
vote
0
answers
42
views
Would the optimal policy remain same, if I replace R with V*?
In the context of RL, say I'm performing Value Iteration on a reward function R1. And the converged optimal policy is P1 and values are V1.
Then, let's say I set rewards to be R2=V1 and perform value ...
1
vote
1
answer
168
views
Is there a reward function that would encourage exploration in this case?
I am new to Reinforcement Learning. I am trying to train PPO agent for citylearn. The goal is to lower two environmental variables from observations. The default reward function is
...
1
vote
1
answer
183
views
How to normalizing various elements of the reward function?
Suppose I have a reward function $R$ that I wish to penalize w.r.t two distinct phenomenons $A$ and $B$. $A$, for example, could represent the phenomenon of the state not crossing some boundary $[s_1,...
- 371
0
votes
0
answers
34
views
Reward Function for Reinforcement Learning model
I am trying to create a reinforcement learning model to control the acceleration of a car. I am designing the model such that initially the acceleration is provided and then deceleration is provided ...
0
votes
0
answers
29
views
Bouding the state using the reward in RL
I'm wondering what the common approaches are bounding out state $s\in\mathbf{R}$ to some values $\in[s_0,s_1]$ is required. So in my case, for example, the state represents an angle of rotation, that ...
- 371
0
votes
0
answers
124
views
Shaping reward so that it maximizes multiple components together
I am fairly new to RL and I compete in AWS DeepRacer student league. The main task there is to create a reward function. All the hyperparameters and action space are fixed. So far, I know how to shape ...
3
votes
1
answer
135
views
Reward design or Inverse reinforcement learning?
I'm working on a reinforcement learning project where I only have demonstrations (i.e. set of states and actions). During my research on how handle the reward signal, I noticed that research papers ...
- 133
2
votes
1
answer
741
views
How to deal with small reward values
In my environment rewards are generally small, e.g. [-0.01, 0.01]. My concern is that small reward values might get dominated or distorted by the noise during the training. Does it make sense to scale ...
- 341
0
votes
2
answers
138
views
Is there a way to form a reward function so that it would take into account the order of the actions?
I want to design a multi-arm bandit system for a multi-step, multi-location system. Locations are dynamic, so I can not design the system based on them. In each location, the alternative actions that ...
0
votes
0
answers
210
views
How to solve a reinforcement learning problem with a stochastic reward function?
In a discrete time system, an environment has an unknown reward probability $p(r|s,a)$. However, the transition probability $p(s'\mid s,a)$ is deterministic.
In my case, the reward for the same action ...
2
votes
0
answers
252
views
How to solve a reinforcement learning problem with changing rewards?
I'm working on a problem with non-stationary environments. The state space is discrete and limited. The action is limited too. But the reward for the same action $a$ can change. Even the reward for ...
2
votes
1
answer
408
views
In RL, is it possible to design a multiplicative/exponential reward function? A reward func that depends on current accumulated reward?
In the context of my problem, the "true" reward is not additive. Realistically, the more reward the agent has already accumulated, the easier it becomes to accumulate even more. That's to ...
- 342
1
vote
0
answers
25
views
If we have a working reward function, would adding another action have a significant effect on the agent performance if task remains the same?
If we have a working reward function, providing the desired behavior and optimal policy in a continuous action/state-space problem, would adding another action significantly affect the possible ...
- 11
2
votes
1
answer
134
views
How to construct a reward function for a "wait and see" problem
I'm working on a problem that I think could probably be represented as a reinforcement learning task, but I'm uncertain about how to design the reward function. The core task is essentially a ...
- 21
1
vote
1
answer
238
views
How should I write the reward function to teach the agent the rules of this card game?
I'm quite new to reinforcement learning. I've been training the model for the following problem but the mean reward is stuck.
In a 5 by 5 board, each position can contain a card with a color (0-4) ...
- 113
1
vote
0
answers
658
views
What is commonly done for standardization/normalization of the targets in Deep Q-Learning?
I have been searching a lot about standardization/normalization of rewards and targets for the DQN algorithm. For the rewards, I now use the gym wrapper, which only scales but not shifts the rewards ...
- 55
0
votes
1
answer
53
views
Does $R_{s}=E[R_{t}|S_{t}=s]$ indicate the reward we might expect on getting on average moving from any other state to $s$?
I'm trying to understand correctly what each "variable" in RL is and I'm not sure about $R_{s}$ the reward function. I used to think that it's the reward we may expect on average after ...
- 573
1
vote
0
answers
95
views
Normalisation of reward function
Problem
Currently, I have some problems defining a reward function for my RL project and mainly with how to normalise the score such that the highest possible score for all instances of the ...
- 31
1
vote
0
answers
63
views
How to teach Machine Learning Agent to destroy replicating objects in a puzzle game?
I have an unusual but very interesting problem. I have a game that is very similar to Toon Blast (a puzzle mobile game). It's based on a Match-2 mechanic in which you can destroy 2 or more connected ...
- 153
2
votes
1
answer
94
views
Is there a mathematical formalism to deal with a missing reward signal?
Typically, a Reinforcement Learning learning problem is formalized as finding an optimal policy for a Markov Decision Process (MDP). In many real-life situations, however, an agent can only get ...
- 173
0
votes
1
answer
867
views
Is it a bad practice to use cumulative rewards in reinforcement learning
I am using a DDPG agent for doing prediction on the position on an asset in a stock trading-like environment. I am using the cumulative reward as the reward for each timestep. Since it is trained over ...
- 69
1
vote
1
answer
1k
views
How should I define the reward function for a stock trading-like game?
Problem setting
Consider a game like trading a stock
At each step, the agent can buy / sell a stock.
Trade is a pair of ...
2
votes
1
answer
1k
views
How to encourage the reinforcement-learning agent to reach the goal as quickly as possible, and what's the effect of discount factor?
I am trying to use reinforcement learning to solve a task and compare its performance to humans.
The task is to find a single target in a fixed number of locations. At each step, the agent will pick ...
- 213
1
vote
1
answer
441
views
How do I compute the value function when the reward is only at the end in the context of actor-critic algorithms?
Consider the actor-critic reinforcement learning setting (actor and critic parameterized by a neural network). The reward is given only at the end of the episode (or when there is a timeout there is ...
- 141
1
vote
0
answers
83
views
Are there any deep RL algorithms that work well on finite MDPs and non-trivial terminal rewards?
I notice that most Deep Reinforcement Learning (DRL) works focus on Markov Decision Process (MDP) with an infinite time horizon.
Are there any algorithms that work well on finite MDP and non-trivial ...
- 111
1
vote
1
answer
360
views
How are rewards calculated for episodic tasks like playing chess or tic-tac-toe?
I am new to Reinforcement Learning and trying to understand the concept of reaping rewards during episodic tasks. I think in games like tic-tac-toe, rewards will be in terms of a win or lose. But does ...
- 11
1
vote
1
answer
185
views
How are these two versions of the Bellman optimality equation related?
I saw two versions of the optimality equation for $V_{*}(s)$ and $Q_{*}(s,a)$.
The first one is:
$$
V_{*}(s)=\max _{a} \sum_{s^{\prime}} P_{s s^{\prime}}^{a}\left(r(s, a)+\gamma V_{*}\left(s^{\prime}\...
- 49
1
vote
1
answer
90
views
In addition to the reward function, which other functions do I need to implement Q-learning?
In general, $Q$ function is defined as
$$Q : S \times A \rightarrow \mathbb{R}$$
$$Q(s_t,a_t) = Q(s_t,a_t) + \alpha[r_{t+1} + \gamma \max\limits_{a} Q(s_{t+1},a) - Q(s_t,a_t)] $$
$\alpha$ and $\gamma$...
- 187
0
votes
1
answer
267
views
How would you shape a reward function if there was four quantities to optimize?
I found this article quite useful on how to shape a reward function in RL. However, the example they gave is quite simple, where the goal is to minimize only two quantities (velocity and distance).
...
- 36
0
votes
1
answer
219
views
How do we get the value of this state of an MDP, at time-step $h-2$, using dynamic programming?
I am trying to understand the problem below, represented as an MDP with four states (PU, PF, RU, and RF) and two actions (AS).
Let's consider V(RF), the value of the state RF. At time-step $h$, V(RF) ...
- 61
2
votes
1
answer
668
views
What happens with policy gradient methods if rewards are differentiable?
I would like some help with understanding why there is no explicit flow of information from the reward gradient to the parameters of the policy in policy gradient methods.
What I mean is the following,...
1
vote
1
answer
591
views
How to scale all positive continuous reward?
My RL project has all positive continuous rewards for every step and the goal is to have the maximum cumulative reward (episodic reward). The problem is that the rewards are too close and all between ...
3
votes
1
answer
309
views
Intuition behind $1-\gamma$ and $\frac{1}{1-\gamma}$ for calculating discounted future state distribution and discounted reward
In the appendix of the Constrained Policy Optimization (CPO) paper (Arxiv), the authors denote the discounted future state distribution $d^\pi$ as:
$$d^\pi(s) = (1-\gamma) \sum_{t=0}^\infty{\gamma^t P(...
- 215
6
votes
1
answer
1k
views
How to improve the reward signal when the rewards are sparse?
In cases where the reward is delayed, this can negatively impact a models ability to do proper credit assignment. In the case of a sparse reward, are there ways in which this can be negated?
In a ...
- 385
2
votes
1
answer
187
views
Can the rewards be matrices when using DQN?
I have a basic question. I'm working towards developing a reward function for my DQN. I'd like to train an RL agent to edit pixels on an image. I understand that convolutions are ideal for working ...
- 323
2
votes
1
answer
133
views
How can I go from $R(s)$ to $R(s,a)$ in this specific MDP?
I'm trying to implement a research paper, as explained in this other post, here the author of the paper assumed R as a function of both states and actions, while the code (and the MDP) I'm using to ...
- 141
3
votes
0
answers
136
views
Is better to reward short- or long-term progress in Q-learning?
I have been training some kind of agent to reach a target using a Q-learning based approach, and I have tried two different types of rewards:
Long-term reward: $\mathrm{reward} = - \mathrm{distance}(\...
- 1,197
0
votes
0
answers
213
views
Is my reward function non-Markovian?
I am working on an RL problem where the time when the agent obtains the reward for taking action $a$ in time step $t$ is stochastic. In fact, there is no immediate reward for taking action $a$ in time ...
1
vote
1
answer
211
views
If the reward function of an environment depends on some initial conditions, should I create a separate environment for each condition?
I would like some guidance on how to design an Environment for a Reinforcement Learning agent where the stopping conditions and rewards for the environment change based on an initial set of input ...
- 15
0
votes
0
answers
53
views
Thompson sampling with Bernoulli prior and non-binary reward update
I am solving a problem for which I have to select the best possible servers (level 1) to hit for a given data. These servers (level 1) in turn hit some other servers (level 2) to complete the request. ...
