Questions tagged [reward-functions]
For questions about rewards functions (e.g. in the context of reinforcement learning, which may be denoted as $R(s, a)$).
88
questions
12
votes
3
answers
2k
views
Why is the reward in reinforcement learning always a scalar?
I'm reading Reinforcement Learning by Sutton & Barto, and in section 3.2 they state that the reward in a Markov decision process is always a scalar real number. At the same time, I've heard about ...
- 223
12
votes
4
answers
2k
views
Counterexamples to the reward hypothesis
On Sutton and Barto's RL book, the reward hypothesis is stated as
that all of what we mean by goals and purposes can be well thought of as the maximization of the expected value of the cumulative ...
- 221
8
votes
1
answer
6k
views
Suitable reward function for trading buy and sell orders
I am working to build a deep reinforcement learning agent which can place orders (i.e. limit buy and limit sell orders). The actions are ...
- 189
8
votes
2
answers
2k
views
How do we define the reward function for an environment?
How do you actually decide what reward value to give for each action in a given state for an environment?
Is this purely experimental and down to the programmer of the environment? So, is it a ...
- 279
8
votes
1
answer
2k
views
What are other ways of handling invalid actions in scenarios where all rewards are either 0 (best reward) or negative?
I created an OpenAI Gym environment, and I would like to check the performance of the agent from OpenAI Baselines DQN approach on it.
In my environment, the best possible outcome for the agent is 0 - ...
- 263
7
votes
2
answers
8k
views
What are some best practices when trying to design a reward function?
Generally speaking, is there a best-practice procedure to follow when trying to define a reward function for a reinforcement-learning agent? What common pitfalls are there when defining the reward ...
7
votes
1
answer
3k
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.
...
- 39.7k
6
votes
2
answers
1k
views
How are the reward functions $R(s)$, $R(s, a)$ and $R(s, a, s')$ equivalent?
In this video, the lecturer states that $R(s)$, $R(s, a)$ and $R(s, a, s')$ are equivalent representations of the reward function. Intuitively, this is the case, according to the same lecturer, ...
- 39.7k
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
6
votes
1
answer
2k
views
What are the pros and cons of sparse and dense rewards in reinforcement learning?
From what I understand, if the rewards are sparse the agent will have to explore more to get rewards and learn the optimal policy, whereas if the rewards are dense in time, the agent is quickly guided ...
- 1,131
6
votes
2
answers
2k
views
Why does shifting all the rewards have a different impact on the performance of the agent?
I am new to reinforcement learning. For my application, I have found out that if my reward function contains some negative and positive values, my model does not give the optimal solution, but the ...
- 61
6
votes
1
answer
733
views
How should I handle invalid actions in a grid world?
I'm building a really simple experiment, where I let an agent move from the bottom-left corner to the upper-right corner of a $3 \times 3$ grid world.
I plan to use DQN to do this. I'm having trouble ...
- 197
5
votes
1
answer
1k
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
5
votes
1
answer
185
views
How define a reward function for a humanoid agent whose goal is to stand up from the ground?
I'm trying to teach a humanoid agent how to stand up after falling. The episode starts with the agent lying on the floor with its back touching the ground, and its goal is to stand up in the shortest ...
- 151
4
votes
2
answers
970
views
Why does the definition of the reward function $r(s, a, s')$ involve the term $p(s' \mid s, a)$?
Sutton and Barto define the state–action–next-state reward function, $r(s, a, s')$, as follows (equation 3.6, p. 49)
$$
r(s, a, s^{\prime}) \doteq \mathbb{E}\left[R_{t} \mid S_{t-1}=s, A_{t-1}=a, S_{t}...
- 107
4
votes
1
answer
2k
views
How can I ensure convergence of DDQN, if the true Q-values for different actions in the same state are very close?
I am applying a Double DQN algorithm to a highly stochastic environment where some of the actions in the agent's action space have very similar "true" Q-values (i.e. the expected future ...
- 93
4
votes
2
answers
870
views
How to apply Q-learning when rewards is only available at the last state?
I have a scheduling problem in which there are $n$ slots and $m$ clients. I am trying to solve the problem using Q-learning so I have made the following state-action model.
A state $s_t$ is given by ...
- 301
4
votes
1
answer
670
views
Can the rewards be stochastic when the transition model is deterministic?
Suppose we have a deterministic environment where knowing $s,a$ determines $s'$. Is it possible to get two different rewards $r\neq r'$ in some state $s_{\text{fixed}}$? Assume that $s_{\text{fixed}}$ ...
- 41
4
votes
1
answer
2k
views
Is a reward given at every step or only given when the RL agent fails or succeeds?
In reinforcement learning, an agent can receive a positive reward for correct actions and a negative reward for wrong actions, but does the agent also receive rewards for every other step/action?
- 1,283
4
votes
0
answers
71
views
What research has been done on learning non-Markovian reward functions?
Recently, some work has been done planning and learning in Non-Markovian Decision Processes, that is, decision-making with temporally extended rewards. In these settings, a particular reward is ...
- 41
3
votes
2
answers
108
views
Can rewards be decomposed into components?
I'm training a robot to walk to a specific $(x, y)$ point using TD3, and, for simplicity, I have something like ...
- 35
3
votes
1
answer
1k
views
How does the initialization of the value function and definition of the reward function affect the performance of the RL agent?
Is there any empirical/theoretical evidence on the effect of initial values of state-action and state values on the training of an RL agent (the values an RL agent assigns to visited states) via MC ...
user9947
3
votes
1
answer
633
views
Why is the reward function $\text{reward} = 1/{(\text{cost}+1)^2}$ better than $\text{reward} =1/(\text{cost}+1)$?
I have implemented a simple Q-learning algorithm to minimize a cost function by setting the reward to the inverse of the cost of the action taken by the agent. The algorithm converges nicely, but ...
- 77
3
votes
1
answer
136
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
3
votes
1
answer
312
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
3
votes
3
answers
943
views
Is the policy really invariant under affine transformations of the reward function?
In the context of a Markov decision process, this paper says
it is well-known that the optimal policy is invariant to positive affine transformation of the reward function
On the other hand, ...
- 171
3
votes
0
answers
137
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
2
votes
1
answer
751
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
2
votes
1
answer
158
views
Why is the equation $r(s', a, s') =\sum_{r \in \mathcal{R}} r \frac{p\left(s^{\prime}, r \mid s, a\right)}{p\left(s^{\prime} \mid s, a\right)}$true?
I am referring to eq. 3.6 (page 49) based on Sutton's online book and can be found in an image below.
I could not make sense of the final derivation of the equation $r(s, a, s')$. My question is ...
- 123
2
votes
1
answer
410
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
2
votes
1
answer
188
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
135
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
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
2
votes
1
answer
670
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,...
2
votes
2
answers
526
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 ...
2
votes
1
answer
521
views
Why does potential-based reward shaping seem to alter the optimal policy in this case?
It is known that every potential function won't alter the optimal policy [1]. I lack of understanding why is that.
The definition:
$$R' = R + F,$$ with $$F = \gamma\Phi(s') - \Phi(s),$$
where, let's ...
2
votes
1
answer
176
views
Where are the parentheses in the definition of $r(s,a)$?
I am new to RL and I am trying to work through the book Reinforcement Learning: An Introduction I (Sutton & Barto, 2018). In chapter 3 on Finite Markov Decision Processes, the authors write the ...
- 255
2
votes
1
answer
489
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 ...
- 531
2
votes
1
answer
243
views
What is the difference between success rate and reward when dealing with binary and sparse rewards?
In OpenAI Gym "reward" is defined as:
reward (float): amount of reward achieved by the previous action. The
scale varies between environments, but the ...
- 263
2
votes
2
answers
294
views
How to define a reward function in POMDPs?
How do I define a reward function for my POMDP model?
In the literature, it is common to use one simple number as a reward, but I am not sure if this is really how you define a function. Because this ...
- 431
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
2
votes
0
answers
253
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
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
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
2
votes
0
answers
33
views
How can I discourage the RL agent from drawing in a zero-sum game?
My agent receives $1, 0, -1$ rewards for winning, drawing, and losing the game, respectively. What would be the consequences of setting reward to $-1$ for draws? Would that encourage the agent to win ...
- 763
2
votes
0
answers
103
views
How to combine two differently equally important signals into the reward function, that have different scales?
I have two signals that I want to use to model my reward.
The first one is the CPU TIME: running mean from this diagram:
The second one is the MAX RESIDUAL from this diagram:
Since they are both ...
- 382
2
votes
1
answer
352
views
How can I implement the reward function for an 8-DOF robot arm with TRPO?
I need to get an 8-DOF (degrees of freedom) robot arm to move a specified point. I need to implement the TRPO RL code using OpenAI gym. I already have the gazebo environment. But I am unsure of how to ...
- 21
1
vote
1
answer
184
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
1
answer
172
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
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