Questions tagged [reinforcement-learning]

For questions related to reinforcement learning, i.e. a machine learning technique where we imagine an agent that interacts with an environment (composed of states) in time steps by taking actions and receiving rewards (or reinforcements), then, based on these interactions, the agent tries to find a policy (i.e. a behavioural strategy) that maximizes the cumulative reward (in the long run), so the goal of the agent is to maximize the reward.

Filter by
Sorted by
Tagged with
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 ...
7 votes
1 answer
439 views

Can supervised learning be recast as reinforcement learning problem?

Let's assume that there is a sequence of pairs $(x_i, y_i), (x_{i+1}, y_{i+1}), \dots$ of observations and corresponding labels. Let's also assume that the $x$ is considered as independent variable ...
  • 803
22 votes
3 answers
4k 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 (the Robbins-Monro conditions) regarding the learning rate are satisfied $\...
  • 35.5k
8 votes
3 answers
11k views

What is the difference between a stochastic and a deterministic policy?

In reinforcement learning, there are the concepts of stochastic (or probabilistic) and deterministic policies. What is the difference between them?
  • 35.5k
74 votes
6 answers
77k views

What's the difference between model-free and model-based reinforcement learning?

What's the difference between model-free and model-based reinforcement learning? It seems to me that any model-free learner, learning through trial and error, could be reframed as model-based. In ...
5 votes
2 answers
904 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, ...
  • 35.5k
25 votes
1 answer
11k views

What is the Bellman operator in reinforcement learning?

In mathematics, the word operator can refer to several distinct but related concepts. An operator can be defined as a function between two vector spaces, it can be defined as a function where the ...
  • 35.5k
2 votes
1 answer
3k views

What is an agent in Artificial Intelligence?

While studying artificial intelligence, I have often encountered the term "agent" (often autonomous, intelligent). For instance, in fields such as Reinforcement Learning, Multi-Agent Systems, Game ...
  • 725
14 votes
3 answers
5k views

Why exactly do neural networks require i.i.d. data?

In reinforcement learning, successive states (actions and rewards) can be correlated. An experience replay buffer was used, in the DQN architecture, to avoid training the neural network (NN), which ...
  • 35.5k
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 ...
  • 279
16 votes
1 answer
4k views

Why does DQN require two different networks?

I was going through this implementation of DQN and I see that on line 124 and 125 two different Q networks have been initialized. From my understanding, I think one network predicts the appropriate ...
6 votes
1 answer
387 views

What is the relation between a policy which is the solution to a MDP and a policy like $\epsilon$-greedy?

In the context of reinforcement learning, a policy, $\pi$, is often defined as a function from the space of states, $\mathcal{S}$, to the space of actions, $\mathcal{A}$, that is, $\pi : \mathcal{S} \...
  • 35.5k
3 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 ...
  • 803
2 votes
1 answer
320 views

Reinforcement learning applicable to a scheduling problem?

I have a certain scheduling problem and I would like to know in general whether I can use Reinforcement learning (and if so what kind of RL) to solve it. Basically my problem is a mixed-integer linear ...
  • 212
24 votes
2 answers
10k views

Are there other approaches to deal with variable action spaces?

This question is about Reinforcement Learning and variable action spaces for every/some states. Variable action space Let's say you have an MDP, where the number of actions varies between states (for ...
18 votes
1 answer
16k views

How does LSTM in deep reinforcement learning differ from experience replay?

In the paper Deep Recurrent Q-Learning for Partially Observable MDPs, the author processed the Atari game frames with an LSTM layer at the end. My questions are: How does this method differ from the ...
12 votes
2 answers
1k views

Why is reinforcement learning not the answer to AGI?

I previously asked a question about How can an AI freely make decisions?. I got a great answer about how current algorithms lack agency. The first thing I thought of was reinforcement learning, since ...
  • 355
8 votes
2 answers
731 views

What is experience replay in laymen's terms?

I've been reading Google's DeepMind Atari paper and I'm trying to understand the concept of "experience replay". Experience replay comes up in a lot of other reinforcement learning papers (...
6 votes
2 answers
4k 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
2 answers
337 views

What introductory books to reinforcement learning do you know, and how do they approach this topic?

Currently, I'm only going through these two books Reinforcement Learning: An Introduction, by Sutton and Barto: RL explained on an engineering level (mathematical, but readable for a non-...
  • 372
2 votes
2 answers
386 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 ...
1 vote
2 answers
1k views

How can we estimate the transition model and reward function?

In reinforcement learning (RL), there are model-based and model-free algorithms. In short, model-based algorithms use a transition model $p(s' \mid s, a)$ and the reward function $r(s, a)$, even ...
  • 35.5k
22 votes
1 answer
19k views

What is the credit assignment problem?

In reinforcement learning (RL), the credit assignment problem (CAP) seems to be an important problem. What is the CAP? Why is it relevant to RL?
  • 35.5k
18 votes
2 answers
10k views

What is the difference between reinforcement learning and optimal control?

Coming from a process (optimal) control background, I have begun studying the field of deep reinforcement learning. Sutton & Barto (2015) state that particularly important (to the writing of the ...
16 votes
3 answers
6k views

How to implement a variable action space in Proximal Policy Optimization?

I'm coding a Proximal Policy Optimization (PPO) agent with the Tensorforce library (which is built on top of TensorFlow). The first environment was very simple. Now, I'm diving into a more complex ...
  • 163
14 votes
3 answers
3k views

Is the optimal policy always stochastic if the environment is also stochastic?

Is the optimal policy always stochastic (that is, a map from states to a probability distribution over actions) if the environment is also stochastic? Intuitively, if the environment is ...
  • 35.5k
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
10 votes
1 answer
4k 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 ...
  • 298
9 votes
5 answers
774 views

What's a good resource for getting familiar with reinforcement learning?

I am familiar with supervised and unsupervised learning. I did the SaaS course done by Andrew Ng on Coursera.org. I am looking for something similar for reinforcement learning. Can you recommend ...
  • 213
8 votes
1 answer
482 views

What are the different approaches used in Machine Learning?

There seem to be so many sub-fields, so I'm interested in getting a better understanding of the approaches. I'm looking for information on a single framework per answer, in order to allow for ...
  • 261
7 votes
2 answers
3k views

What is a time-step in a Markov Decision Process?

The "discounted sum of future rewards" (or return) using discount factor $\gamma$ is $$\gamma^1 r_1 +\gamma^2 r_2 + \gamma^3 r_2 + \dots \tag{1}\label{1}$$ where $r_i$ is the reward received ...
7 votes
1 answer
5k views

What is the difference between a stationary and a non-stationary policy?

In reinforcement learning, there are deterministic and non-deterministic (or stochastic) policies, but there are also stationary and non-stationary policies. What is the difference between a ...
  • 35.5k
7 votes
2 answers
415 views

What are some online courses for deep reinforcement learning?

What are some (good) online courses for deep reinforcement learning? I would like the course to be both programming and theoretical. I really liked David Silver's course, but the course dates from ...
  • 81
6 votes
1 answer
1k views

What are the conditions of convergence of temporal-difference learning?

In reinforcement learning, temporal difference seem to update the value function in each new iteration of experience absorbed from the environment. What would be the conditions for temporal-...
  • 163
5 votes
2 answers
799 views

Are bandits considered an RL approach?

If a research paper uses multi-armed bandits (either in their standard or contextual form) to solve a particular task, can we say that they solved this task using a reinforcement learning approach? Or ...
5 votes
2 answers
2k views

How can I handle overfitting in reinforcement learning problems?

So this is my current result (loss and score per episode) of my RL model in a simple two players game: I use DQN with CNN as a policy and target networks. I train my model using Adam optimizer and ...
  • 2,589
4 votes
4 answers
3k views

What is the difference between training and testing in reinforcement learning?

In reinforcement learning (RL), what is the difference between training and testing an algorithm/agent? If I understood correctly, testing is also referred to as evaluation. As I see it, both imply ...
4 votes
1 answer
422 views

Is there any difference between a control and an action in reinforcement learning?

There are reinforcement learning papers (e.g. Metacontrol for Adaptive Imagination-Based Optimization) that use (apparently, interchangeably) the term control or action to refer to the effect of the ...
  • 35.5k
3 votes
1 answer
139 views

Why is the state value function sufficient to determine the policy if a model is available?

In section "5.2 Monte Carlo Estimation of Action Values" of the second edition of the reinforcement learning book by Sutton and Barto, this is stated: If a model is not available, then it is ...
  • 311
2 votes
1 answer
225 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 ...
1 vote
1 answer
169 views

What is meant by "two action selections" in SARSA?

I have some difficulties understanding the difference between Q-learning and SARSA. Here (What are the differences between SARSA and Q-learning?) the following updating formulas are given: Q-Learning $...
  • 212
40 votes
2 answers
19k views

What is the relation between Q-learning and policy gradients methods?

As far as I understand, Q-learning and policy gradients (PG) are the two major approaches used to solve RL problems. While Q-learning aims to predict the reward of a certain action taken in a certain ...
  • 525
20 votes
2 answers
15k views

What is the difference between First-Visit Monte-Carlo and Every-Visit Monte-Carlo Policy Evaluation?

I came across these 2 algorithms, but I cannot understand the difference between these 2, both in terms of implementation as well as intuitionally. So, what difference does the second point in both ...
user avatar
16 votes
4 answers
2k views

Why does the discount rate in the REINFORCE algorithm appear twice?

I was reading the book Reinforcement Learning: An Introduction by Richard S. Sutton and Andrew G. Barto (complete draft, November 5, 2017). On page 271, the pseudo-code for the episodic Monte-Carlo ...
16 votes
2 answers
11k views

Can Q-learning be used for continuous (state or action) spaces?

Many examples work with a table-based method for Q-learning. This may be suitable for a discrete state (observation) or action space, like a robot in a grid world, but is there a way to use Q-learning ...
16 votes
3 answers
8k views

Are there any applications of reinforcement learning other than games?

Is there a way to teach reinforcement learning in applications other than games? The only examples I can find on the Internet are of game agents. I understand that VNC's control the input to the ...
12 votes
1 answer
5k views

What is the relation between online (or offline) learning and on-policy (or off-policy) algorithms?

In the context of RL, there is the notion of on-policy and off-policy algorithms. I understand the difference between on-policy and off-policy algorithms. Moreover, in RL, there's also the notion of ...
  • 35.5k
10 votes
4 answers
3k views

Are there any online competitions for Reinforcement Learning?

Kaggle is limited to only supervised learning problems. There used to be www.rl-competition.org but they've stopped. Is there anything else I can do other than locally trying out different algorithms ...
9 votes
2 answers
905 views

Reinforcement Learning with asynchronous feedback

I want suggestions on literature on Reinforcement Learning algorithms that perform well with asynchronous feedback from the environment. What I mean by asynchronous feedback is, when an agent performs ...
8 votes
3 answers
3k views

How can you represent the state and action spaces for a card game in the case of a variable number of cards and actions?

I know how a machine can learn to play Atari games (Breakout): Playing Atari with Reinforcement Learning. With the same technique, it is even possible to play FPS games (Doom): Playing FPS Games with ...

1
2 3 4 5