Questions tagged [rewards]

For questions related to the concept of reward, for example, in the context of reinforcement learning and Markov decision processes. For questions related to reward functions, reward design, reward shaping, reward hacking, etc., there are also those specific tags, so you use them instead of this generic one, unless your question is also about the concept of reward.

33 questions with no upvoted or accepted answers
Filter by
Sorted by
Tagged with
4 votes
1 answer
217 views

What could be the cause of the drop in the reward in A3C?

The mean episodic reward is generally increasing, but it has spontaneous drops, and I'm not sure of their cause. The problem has a sparse reward, batch size=2000, <...
user avatar
  • 163
3 votes
0 answers
115 views

How does normalization of the inputs work in the context of PPO?

What does the normalization of the inputs mean in the context of PPO? At each time step of an episode, I only know the values of this time step and of the previous ones, if I take track of them. This ...
user avatar
  • 161
3 votes
0 answers
111 views

What are the guidelines for defining a reward function in reinforcement learning (bandit problem)?

I'm working currently on a problem and I'm using RL (bandit problem). In my system, I have an agent that chooses an action among $k$ possible actions, and a user that decides whether the agent ...
user avatar
  • 31
2 votes
0 answers
77 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 ...
user avatar
2 votes
0 answers
63 views

What is the dimensionality of these derivatives in the paper "Active Learning for Reward Estimation in Inverse Reinforcement Learning"?

I'm trying to implement in code part of the following paper: Active Learning for Reward Estimation in Inverse Reinforcement Learning. I'm specifically referring to section 2.3 of the paper. Let's ...
user avatar
2 votes
0 answers
86 views

Should I use the discounted average reward as objective in a finite-horizon problem?

I am new to reinforcement learning, but, for a finite horizon application problem, I am considering using the average reward instead of the sum of rewards as the objective. Specifically, there are a ...
user avatar
  • 121
2 votes
0 answers
41 views

How should I design a reward function for a NLP problem where two models interoperate?

I would like to design a reward function. I am training two models from the first model that classify set of texts (paragraphs and keywords) and I also got some hidden states. The second model is ...
user avatar
  • 21
2 votes
0 answers
35 views

How was the DQN trained to play many games?

Some people claim that DQN was used to play many Atari games. But what actually happened? Was DQN trained only once (with some data from all games) or was it trained separately for each game? What was ...
user avatar
  • 583
2 votes
0 answers
32 views

How should I define the reward function for the Connect Four game?

I'm creating an RL application for the game Connect Four. I've researched the different strategies for the game and which positions are more favourable to lead to a win. Should I be assigning ...
user avatar
  • 583
2 votes
0 answers
31 views

Developmental systems that try to explain or understand the reward value in the reinforcement learning?

Are there methods (possibly logical or (how they are called in the literature) relational) that allows for the developmental systems to understand or explain the value of the received reward during ...
user avatar
  • 773
2 votes
0 answers
127 views

Is it possible to use Reward Function of type R(s, a, s') if more than one action is applied?

I am applying a reinforcement learning agent (PPO2, stable baselines implementation) to a custom built environment using OpenAI Gym. One reward function (formualted as loss function, that is, all ...
user avatar
  • 81
2 votes
0 answers
83 views

Will the RL agent implemented as a neural network fine-tune itself?

Normally, when you develop a neural network, train it for object recognition (on normal objects like bike, car, plane, dog, cloud, etc.), and it turns out to perform very well, you would like to fine-...
user avatar
  • 141
2 votes
0 answers
45 views

Can $\Phi$ measure of Integrated Information Theory serve as reward for reinforcement learning system?

Can $\Phi$ measure (computed rigorously or approximately) of Integrated Information Theory serve as reward for self-evolving/learning reinforcement learning system and hence we let this system to ...
user avatar
  • 773
2 votes
0 answers
18 views

How is GARB implemented in PGRD-DL to calculate gradients w.r.t. internal rewards?

In section 3 of this paper the author outlines how GARB was adapted to reduce the variance in updating parameters to an internal reward function estimator. I have read it a number of times and ...
user avatar
  • 499
1 vote
0 answers
93 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 ...
user avatar
  • 33
1 vote
0 answers
35 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 ...
user avatar
  • 21
1 vote
0 answers
37 views

Generative systems based on Schmidhuber's compression framework

In Driven by Compression Progress: A Simple Principle Explains Essential Aspects of Subjective Beauty, Novelty, Surprise, Interestingness, Attention, Curiosity, Creativity, Art, Science, Music, Jokes ...
user avatar
  • 121
1 vote
0 answers
114 views

Why would DDPG with Hindsight Experience Replay not converge?

I am trying to train a DDPG agent augmented with Hindsight Experience Replay (HER) to solve the KukaGymEnv environment. The actor and critic are simple neural networks with two hidden layers (as in ...
user avatar
1 vote
0 answers
46 views

Does importance sampling for off-policy estimation also apply to the case of negative rewards?

Importance sampling is a common method for calculating off-policy estimates in RL. I have been reading through some of the original documentation (D.G. Horvitz and D.J. Thompson, Powell, M.J. and ...
user avatar
1 vote
0 answers
51 views

State-of-the-art algorithms not working on a custom RL environment

I'm trying to train a RL agent on a custom, highly stochastic environment (MDP). In order to do so I'm using existing implementations of state-of-the-art RL algorithms as provided by Stable Baselines. ...
user avatar
  • 129
1 vote
0 answers
34 views

How can I find the appropriate reward value for my reinforcement learning problem?

I am wondering how can I find the appropriate reward value for each specific problem. I know this is a highly empirical process, but I am sure that the value is not set totally at random. I want to ...
user avatar
1 vote
0 answers
49 views

Which model should I choose to maximise reward of having chosen two numbers from a list?

I am looking for a technique to train a machine learning model to choose two items from a list. So, given a list $x=[x_1, x_2, x_3, x_4, \dots, x_n]$, the model needs to choose two elements $(x_i, ...
user avatar
1 vote
0 answers
27 views

Does apprenticeship learning require prospective data?

I am thinking of applying apprenticeship learning on retrospective data. From looking at this paper by Ng https://ai.stanford.edu/~ang/papers/icml04-apprentice.pdf which talks about apprenticeship ...
user avatar
  • 1,221
1 vote
0 answers
85 views

Should an RL agent directly observe the reward?

I am training an A2C reinforcement learning agent in a dense reward environment (where rewards are known and explicit at every timestep). Is it redundant to include the previous reward in the current ...
user avatar
1 vote
0 answers
84 views

Finding optimal Value function and Policy for an MDP

I am solving an RL MDP problem which is model based. I have an MDP which has four possible states S1-S4 and four different actions A1-A4, with S4 being terminal state and S1 is the beginning state. ...
user avatar
  • 83
1 vote
0 answers
182 views

Reward problem in A2C with multiple simultaneous discrete actions

I've built an A2C model whose actor's network has two different kinds of discrete actions, so the critic would take state and action (note that critic takes 2 actions because in each timestep we will ...
user avatar
  • 21
1 vote
0 answers
80 views

Deciding the rewards for different actions in Pong for a DQN agent

I am attempting to implement an agent that learns to play in the Pong environment, the environment was created in PyGame and I return the pixel data and score at each frame. I use a CNN to take a ...
user avatar
  • 11
0 votes
0 answers
73 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 ...
user avatar
0 votes
0 answers
88 views

PPO: how to scale rewards

I have a custom PPO implementation and a problem that has costs rather than rewards, so I basically need to take the negative value for PPO to work. As the values are somewhat large, I've tried ...
user avatar
0 votes
0 answers
65 views

How to pass the rewards in zero-sum multiplayer context when using REINFORCE?

Suppose there are two players in my zero-sum game and they play in a row like chess. And I want to learn the policy function using the REINFORCE algorithm. I have doubts about passing reward values in ...
user avatar
  • 3,191
0 votes
0 answers
174 views

How to normalize rewards in REINFORCE?

I'm trying to solve a reinforcement learning problem using a Monte Carlo policy gradient algorithm and, more specifically, REINFORCE, with rewards attributed to individual moves instead of applied to ...
user avatar
  • 121
0 votes
0 answers
29 views

Curiosity Driven Learning affect optimal policy

I am trying to understand some of the different approaches used to overcome sparse rewards in a reinforcement learning setting for a research project. Particularly, I have looked at curiosity driven ...
user avatar
  • 1,221
0 votes
1 answer
73 views

Is is not possible to achieve average reward of more than 20-40 with simple Q-Learning

I have implemented the simple Q-Learning based solution for AI-gym's Cartpole-v0. However, despite changing hyper-parameters, and rechecking my code, I cannot get an average reward (N-running reward) ...
user avatar
  • 331