Questions tagged [reward-design]

For questions about designing (or defining) reward functions e.g. for reinforcement learning problems.

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

Reinforcement Learning with sparse/delayed reward - should intermediate rewards be decayed over time/training?

I'm thinking of a situation like a game (say, chess) where the real objective/reward is actually determined at the very end. I understand that it's important/helpful to do reward shaping with ...
0 votes
0 answers
12 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
23 views

When use positive or negative rewards in reinforcement learning? Is there anything in literature?

Let's say I can design a reward as function of a distance $d>0$ from the target in 2 ways: $r=\frac{1}{1+d}$ or $r=-d$. The first is defined in $(0,1]$ the second in $(-\infty,0]$. I would expect ...
  • 41
3 votes
1 answer
45 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 ...
0 votes
0 answers
29 views

Model learning only to not to trade in a static sequence

I am learning RL and using out-of-the-box Stable-Baselines 3 PPO algorithm, I made a custom environment with the following ...
0 votes
2 answers
43 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 ...
1 vote
0 answers
21 views

How to teach DRL agent to avoid erratic, high frequency behavior (when costs for taking actions are already included)?

I have a situation where an agent can take actions to enter a state where rewards can be obtained (or costs can be incurred), but the actions themselves have a small cost. In my reward function, I ...
0 votes
0 answers
73 views

Correct reward for trading applications. RL agent learns according to immediate reward instead of cumulative reward

I have coded a RL environment for trading. The action space is discrete with 3 components [0,1,2]; where 0 corresponds to selling an arbitrary amount of shares; 1 corresponds to holding; and 2 ...
  • 49
0 votes
0 answers
95 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
1 answer
90 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 ...
2 votes
1 answer
87 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 ...
1 vote
1 answer
86 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) ...
  • 111
0 votes
1 answer
43 views

Deep RL reward design for neuron centerline extraction task

As part of a bigger scope project, I'm training a RL agent that attempts to reconstruct, pixel by pixel, the trajectory of a neuron on a segmented image. To give a better insight on the task that I'm ...
1 vote
0 answers
42 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
0 votes
0 answers
33 views

dDQN converges, but makes suboptimal decisions that are mainly focused on retrieving short-term reward

I use a dDQN to dispatch drivers in a ride-hailing environment. The action space has size (#drivers + 1), which means we can choose one of the drivers or choose to refuse an order (and wait for the ...
  • 3
1 vote
1 answer
462 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 ...
0 votes
1 answer
93 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
0 answers
51 views

How to choose the reward in reinforcement learning? [duplicate]

I am solving a combinatorial optimization problem, where I do not have a global optimum, so the goal is to improve the objective function as much as possible. So, to do this, I was inspired by this ...
2 votes
1 answer
98 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
2 answers
552 views

Reinforcement Learning algorithm with rewards dependent both on previous action and current action

Problem description: Suppose we have an environment, where a reward at time step $t$ is dependent not only on the current action, but also on previous action in the following way: if current action ==...
  • 23
2 votes
0 answers
59 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 vote
1 answer
90 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
44 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. ...
2 votes
0 answers
27 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 ...
  • 683
2 votes
2 answers
342 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
103 views

How do I design the rewards and penalties for an agent whose goal it is to explore a map

I am trying to train an agent to explore an unknown two-dimensional map while avoiding circular obstacles (with varying radii). The agent has control over its steering angle and its speed. The ...
2 votes
0 answers
62 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 ...
  • 362
6 votes
2 answers
3k 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 ...
4 votes
1 answer
1k 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?
  • 1,223
3 votes
2 answers
99 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 ...
1 vote
0 answers
140 views

Designing a reward function for my reinforcement learning problem

I'm working on a project lately and I'm trying to solve a problem with reinforcement learning and I have serious issues with shaping the reward function. The problem is designing a device with maximum ...
  • 11
6 votes
1 answer
381 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
3 votes
1 answer
328 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
478 views

How should I design the reward function for racing game (where the goal is to reach finishing line before the opponent)?

I'm building an agent for a racing game. In this game, there is a randomized map where there are speed boosts for the player to pick up and obstacles that act to slow the player down. The goal of the ...
2 votes
1 answer
201 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 ...
4 votes
1 answer
258 views

How to avoid rapid actuator movements in favor of smooth movements in a continuous space and action space problem?

I'm working on a continuous state / continuous action controller. It shall control a certain roll angle of an aircraft by issuing the correct aileron commands (in $[-1, 1]$). To this end, I use a ...
  • 171
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
3 votes
1 answer
176 views

Are there any reliable ways of modifying the reward function to make the rewards less sparse?

If I am training an agent to try and navigate a maze as fast as possible, a simple reward would be something like \begin{align} R(\text{terminal}) &= N - \text{time}\ \ , \ \ N \gg \text{...
  • 133
3 votes
1 answer
695 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 ...
's user avatar
4 votes
0 answers
80 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 ...
  • 141
8 votes
2 answers
1k 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 ...
  • 269
2 votes
1 answer
1k views

Can reinforcement learning be used for tasks where only one final reward is received?

Is reinforcement learning problem adaptable to the setting when there is only one - final - reward. I am aware of problems with sparse and delayed rewards, but what about only one reward and a quite ...
  • 783
3 votes
1 answer
100 views

Expressing Arbitrary Reward Functions as Potential-Based Advice (PBA)

I am trying to reproduce the results for the simple grid-world environment in [1]. But it turns out that using a dynamically learned PBA makes the performance worse and I cannot obtain the results ...
  • 33
4 votes
1 answer
473 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 $s_{\text{fixed}}$ ...
8 votes
1 answer
5k 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
2 votes
1 answer
490 views

How should I define the reward function in the case of Connect Four?

I'm using RL to train a Network on the game Connect4. It learns quickly that 4 connected pieces is good. It gets a reward of 1 for this. A zero is rewarded for all other moves. It takes quite a time ...
2 votes
2 answers
182 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 ...
3 votes
2 answers
1k views

What should I do when the potential value of a state is too high?

I'm working on a Reinforcement Learning task where I use reward shaping as proposed in the paper Policy invariance under reward transformations: Theory and application to reward shaping (1999) by ...
11 votes
1 answer
3k views

How could I use reinforcement learning to solve a chess-like board game?

I invented a chess-like board game. I built an engine so that it can play autonomously. The engine is basically a decision tree. It's composed by: A search function that at each node finds all ...
  • 255
38 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 ...