Questions tagged [reinforcement-learning]

For questions related to learning controlled by external positive reinforcement or negative feedback signal or both, where learning and use of what has been thus far learned occur concurrently.

Filter by
Sorted by
Tagged with
31
votes
6answers
16k 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 ...
22
votes
4answers
6k views

How to handle invalid moves in reinforcement learning?

I want to create an AI which can play five-in-a-row/gomoku. As I mentioned in the title, I want to use reinforcement learning for this. I use policy gradient method, namely REINFORCE, with baseline. ...
21
votes
1answer
5k 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 ...
14
votes
2answers
4k views

What is sample efficiency, and how can importance sampling be used to achieve it?

For instance, the title of this paper reads: "Sample Efficient Actor-Critic with Experience Replay". What is sample efficiency, and how can importance sampling be used to achieve it?
14
votes
2answers
5k views

How to define states in reinforcement learning?

I am studying reinforcement learning and the variants of it. I am starting to get an understanding of how the algorithms work and how they apply to an MDP. What I don't understand is the process of ...
12
votes
1answer
2k views

Why do you not see dropout layers on reinforcement learning examples?

I've been looking at reinforcement learning, and specifically playing around with creating my own environments to use with the OpenAI Gym AI. I am using agents from the stable_baselines project to ...
12
votes
1answer
2k 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 ...
12
votes
3answers
3k views

How to implement a constrained action space in reinforcement learning?

I'm coding a reinforcement learning model with a PPO agent thanks to the very good Tensorforce library, built on top of Tensorflow. The first version was very simple and I'm now diving into a more ...
12
votes
1answer
902 views

When should I use Reinforcement Learning vs PID Control?

When designing solutions to problems such as the Lunar Lander on OpenAIGym, Reinforcement Learning is a tempting means of giving the agent adequate action control so as to successfully land. But ...
12
votes
3answers
7k 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 ...
11
votes
1answer
290 views

How to stay a up-to-date researcher in ML/RL community?

As a student who wants to work on machine learning, I would like to know how it is possible to start my studies and how to follow it to stay up-to-date. For example, I am willing to work on RL and MAB ...
11
votes
2answers
379 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 $\...
11
votes
1answer
5k views

How can policy gradients be applied in the case of multiple continuous actions?

Trusted Region Policy Optimization (TRPO) and Proximal Policy Optimization (PPO) are two cutting edge policy gradients algorithms. When using a single continuous action, normally, you would use some ...
10
votes
3answers
831 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 ...
10
votes
4answers
1k 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 ...
10
votes
4answers
406 views

Can a neural network work out the concept of distance?

Imagine a game where it is a black screen apart from a red pixel and a blue pixel. Given this game to a human, they will first see that pressing the arrow keys will move the red pixel. The next thing ...
9
votes
1answer
7k 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 ...
9
votes
3answers
511 views

Does Monte Carlo tree search qualify as machine learning?

To the best of my understanding, the Monte Carlo tree search (MCTS) algorithm is an alternative to minimax for searching a tree of nodes. It works by choosing a move (generally, the one with the ...
9
votes
2answers
3k views

Inconsistent action space in Reinforcement Learning

This question is regarding Reinforcement Learning and different/inconsistent action space for every/some states. What do I mean by inconsistent action space? Let say you have an MDP where the number ...
9
votes
2answers
588 views

Why is baseline conditional on state at some timestep unbiased?

In robotics, the reinforcement learning technique is used for finding the control pattern for a robot. Unfortunately, most policy gradient method are statistically biased which could bring the robot ...
9
votes
1answer
1k views

A few doubts regarding the application of reinforcement learning to games like chess

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 ...
8
votes
5answers
359 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 ...
8
votes
1answer
896 views

Why does the policy network in AlphaZero work?

In AlphaZero, the policy network (or head of the network) maps game states to a distribution of the likelihood of taking each action. This distribution covers all possible actions from that state. ...
8
votes
3answers
2k views

Why does is make sense to normalize rewards per episode in reinforcement learning?

In Open AI's actor-critic and in Open AI's REINFORCE, the rewards are being normalized like so rewards = (rewards - rewards.mean()) / (rewards.std() + eps) on ...
8
votes
1answer
357 views

Why is reinforcement learning not the answer to AGI?

I previously asked a question about How can an AI freely make decisions on a network?. I got a great answer about how current algorithms lack agency. The first thing I thought of was reinforcement ...
8
votes
2answers
4k views

What is the difference between Actor-Critic and Advantage Actor-Critic?

I'm struggling to understand the difference between Actor-Critic and Advantage Actor-Critic. At least I know they are different from Asynchronous Advantage Actor-Critic (A3C), as A3C adds ...
8
votes
1answer
2k 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 function where the domain ...
8
votes
1answer
219 views

Are there any other machine learning models apart from Reinforcement Learning and Q Learning to play video games?

OpenAI's Universe utilises RL algorithms and I have heard of some game-training projects using Q learning, but are there any others which are used to master/win games? Can genetic algorithms be used ...
8
votes
1answer
263 views

Getting to understand continuous state/action spaces MDPs and Reinforcement Learning

Most introductions to the field of MDPs and Reinforcement learning focus exclusively on domains where space and action variables are integers (and finite). This way we are introduced quickly to Value ...
7
votes
3answers
10k views

What are different actions in action space of environment of 'Pong-v0' game from openai gym?

Printing actionspace for Pong-v0 gives 'Discrete(6)' as output, i.e.0,1,2,3,4,5 are actions defined in environment as per documentation, but game needs only two controls. Why this discrepency? Further ...
7
votes
1answer
2k 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?
7
votes
3answers
2k views

What is a “trajectory” in reinforcement learning?

I'm now learning about reinforcement learning, but I just found the word "trajectory" in this answer. However, I'm not sure what it means. I read a few books on the Reinforcement Learning but none of ...
7
votes
1answer
3k views

What is the difference between an observation and a state in reinforcement learning?

I'm studying reinforcement learning. It seems that "state" and "observation" mean exactly the same thing. They both capture the current state of the game. Is there a difference between the two terms?...
7
votes
1answer
121 views

Are there reinforcement learning algorithms that scale to large problems?

Given a large problem, value iteration and other table based approaches seem to require too many iterations before they start to converge. Are there other reinforcement learning approaches that better ...
7
votes
2answers
644 views

What does “stationary” mean in the context of reinforcement learning?

I think I've seen the expressions "stationary data", "stationary dynamics" and "stationary policy", among others, in the context of reinforcement learning. What does it mean? I think stationary policy ...
7
votes
1answer
2k views

Do off-policy policy gradient methods exist?

Do off-policy policy gradient methods exist? I know that policy gradient methods themselves using the policy function for sampling rollouts. But can't we easily have a model for sampling from the ...
7
votes
2answers
88 views

How can alpha zero learn if the tree search stops and restarts before finishing a game?

I am trying to understand how alpha zero works, but there is one point that I have problems understanding, even after reading several different explanations. As I understand it (see for example https:/...
7
votes
1answer
371 views

What is the relationship between these two taxonomies for machine learning with neural networks?

Could you please let me know which of the following classification of Neural Network's learning algorithm is correct? The first one classifies it into: supervised, unsupervised and reinforcement ...
7
votes
1answer
319 views

Is there a difference in the architecture of deep reinforcement learning when multiple actions are performed instead of a single action?

I've built a deep deterministic policy gradient reinforcement learning agent to be able to handle any games / tasks that have only one action. However, the agent seems to fail horribly when there are ...
7
votes
2answers
458 views

Reinforcement Learning in Commercial Strategy Games

I'm a professional game developer investigating the potential for using reinforcement learning to build strategy game AI opponents that have more creative behavior compared to traditional techniques ...
6
votes
2answers
174 views

What does the symbol $\mathbb E$ mean in these equations?

I came across some papers that use $\mathbb E$ in equations, in particular, this paper: https://arxiv.org/pdf/1511.06581.pdf. Here is some equations from the paper that uses it: $Q^\pi \left(s,a \...
6
votes
3answers
858 views

Board/Card Game AI - Questions concerning state/action space - Deep Reinforcement Learning

Ok, I now know how a machine can learn to play to play Atari games (Breakout): Playing Atari with Reinforcement Learning With the same technique it is even possible to play FPS games (Doom): Playing ...
6
votes
2answers
321 views

What are 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 ...
6
votes
2answers
985 views

What algorithms are considered reinforcement learning algorithms?

What are the areas that belong to the Reinforcement Learning? TD(0), Q-Learning and SARSA are all temporal-difference algorithms, which belong to the reinforcement learning area, but is there more to ...
6
votes
1answer
628 views

How do we prove the n-step return error reduction property?

In section 7.1 (about the n-step bootstrapping) of the book Reinforcement Learning: An Introduction (2nd edition), by Andrew Barto and Richard S. Sutton, the authors write about what they call the "n-...
6
votes
1answer
890 views

Learning Rate Decay and Exploration Rate Decay

Should I be decaying the learning rate and the exploration rate in the same manner? What's too slow and too fast of an exploration and learning rate decay? Or is it specific from model to model?
6
votes
1answer
182 views

Is Experience Replay like dreaming?

Drawing parallels between Machine Learning techniques and a human brain is a dangerous operation. When it is done successfully, it can be a powerful tool for vulgarisation, but when it is done with no ...
6
votes
2answers
461 views

How should I handle action selection in the terminal state when implementing SARSA?

I recently started learning about reinforcement learning and currently I am trying to implement the SARSA algorithm, however I do not know how to deal with $Q(s', a')$, when $s'$ is the terminal state....
6
votes
1answer
113 views

Benchmarks for reinforcement learning in discrete MDPs

To compare the performance of various algorithms for perfect information games, reasonable benchmarks include reversi and m,n,k-games (generalized tic-tac-toe). For imperfect information games, ...
6
votes
1answer
180 views

Does AlphaZero use Q-Learning?

I was reading the AlphaZero paper Mastering Chess and Shogi by Self-Play with a General Reinforcement Learning Algorithm, and it seems they don't mention Q-Learning anywhere. So does AZ use Q-...