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.

659 questions with no upvoted or accepted answers
Filter by
Sorted by
Tagged with
2
votes
0answers
77 views

Formulation of a Markov Decision Process Problem

Given a list of $N$ questions. If question $i$ is answered correctly (given probability $p_i$), we receive reward $R_i$; if not the quiz terminates. Find the optimal order of questions to maximize ...
2
votes
0answers
20 views

What effect does increasing the actions in RL have?

Consider a 2D snake game, where the snake has to eat food to become longer. It must avoid hitting walls and biting into her tail. Such a game could have a different amount of actions: 3 actions: go ...
2
votes
0answers
191 views

How does the update rule for the one-step actor-critic method work?

Can you please elucidate the math behind the update rule for the critic? I've seen in other places that just a squared distance of $R + \hat{v}(S', w) - \hat{v}(S,w)$ is used, but Sutton suggests an ...
2
votes
0answers
50 views

Can the importance sampling estimator have a non-stationary behaviour policy even if the target policy is stationary?

The inverse propensity score (IPS) estimator, which is used for off-policy evaluation in a contextual bandit problem, is well explained in the paper Doubly Robust Policy Evaluation and Optimization. ...
2
votes
0answers
41 views

Why is this Monte Carlo approach scalable for a growing number of states variables and action variables?

I am reading a research paper on the formulation of MDP problems to ICU treatment decision making: Treatment Recommendation in Critical Care: A Scalable and Interpretable Approach in Partially ...
2
votes
1answer
109 views

NoisyNet DQN with default parameters not exploring

I implemented a DQN algorithm that plays OpenAIs Cartpole environment. The NN architecture consists of 3 normal linear layers that encode the state, and one noisy linear layer, that predicts the Q ...
2
votes
0answers
44 views

Can we use imitation learning for on-policy algorithms?

Imitation learning uses experiences of an (expert) agent to train another agent, in my understanding. If I want to use an on-policy algorithm, for example, Proximal Policy Optimization, because of it'...
2
votes
0answers
39 views

What are some approaches to estimate the transition and observation probabilities in POMDP?

What are some common approaches to estimate the transition or observation probabilities, when the probabilities are not exactly known? When realizing a POMDP model, the state model needs additional ...
2
votes
0answers
47 views

Should I consider mean or sampled value for action selection in ppo algorithm?

When considering the policy network in PPO algorithm, we need to fit a Gaussian distribution to the neural network output (for a continuous action space problem). When I use this network to obtain ...
2
votes
0answers
48 views

What form of output would be needed to train a model on a connect 4 AI?

I've had a big interest in machine learning for a while, and I've followed along a few tutorials, but have never made my own project. After losing many games of connect 4 with my friends, I decided to ...
2
votes
0answers
79 views

How would one develop an action space for a game that is proprietary?

I'm currently trying to develop an RL that will teach itself to play the popular fighting game "Tekken 7". I initially had the idea of teaching it to play generally- against actual opponents with ...
2
votes
0answers
49 views

How to set the multiple continuous actions with constraints

I want to build a Deep Reinforcement Learning Model for Asset allocation. Background: I have 7 stock indexes from different markets, and I want to build a policy to produce the action (likes whether ...
2
votes
0answers
36 views

What could be the cause of the drop of the total reward when using DQN to solve the cart-pole environment?

I'm trying to use DQN to solve the cart-pole environment. I have 2 networks (target and behavior). Both of them have 3 hidden layers with 24 neurons, using the ReLU activation. The loss is MSE and the ...
2
votes
0answers
25 views

Finding total number of states in a POMDP

I've been working on a question that is posed in a document I've been reading, that models qualifying for a job as a POMDP. In this model, a person takes 3 exams, and must pass all of them in order to ...
2
votes
0answers
47 views

How to learn using DDPG in python solely using a timeseries datasets

I have a lengthy timeseries datasets which contains several variables (from sensors etc) to be classified as actions or states. Providing they are successfully done, I want to learn a control policy ...
2
votes
0answers
56 views

Is there any open source implementation of the SBEED learning algorithm?

Are there are any openly available implementations of the SBEED: Convergent Reinforcement Learning with Nonlinear Function Approximation paper?
2
votes
0answers
34 views

Best approach for online Machine Translation with few hundred of samples?

I want to implement a model that improves itself with the passage of time. My main task is to build a machine translator (from English to Urdu).. The problem I am facing is that I have very little ...
2
votes
0answers
193 views

how to use Softmax action selection algorithm in atari-like game

I'm currently writing a program using keras (python 3) to play a game similar to Atari games, only in this one there are objects moving in the screen in different angles and directions (in most of ...
2
votes
0answers
25 views

Loss reduction, but constant performance with CNN

I made a CNN with a reasonable loss curve, but the performance of the model does not improve. I have tried making the model larger, I am using three convolutional layers with batch norms. Thanks for ...
2
votes
0answers
53 views

Torch CNN not training

I am completely new to CNN's, and I do not quite know how to design or use them efficiently. That being said, I am attempting to build a CNN that learns to play Pac-man with reinforcement learning. I ...
2
votes
0answers
30 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 ...
2
votes
0answers
43 views

How to show Monte Carlo methods converge to an estimate which minimizes mean squared error?

In chapter six of Sutton and Barto (p.128), they claim Monte Carlo methods converge to an estimate minimizing the mean squared error. How can this be shown formally? Bump
2
votes
0answers
95 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 ...
2
votes
0answers
82 views

What is a high performing network architecture to use in a PPO2 MlpLnLstmPolicy RL model?

I am playing around with creating custom architectures in stable-baselines. Specifically I am training an agent using a PPO2 model. My question is, are there some rules of thumb or best practices in ...
2
votes
0answers
21 views

Why do these reward functions give different training curves?

Let's say our task is to pick and place a block, like: https://gym.openai.com/envs/FetchPickAndPlace-v0/ Reward function 1: -1 for block not placed, 0 for block placed Reward function 2: 0 for block ...
2
votes
0answers
46 views

How to solve optimal control problem with reinforcement learning

The problem I am trying to attack is a predator-prey pursuit problem. There are multiple predators that pursue multiple preys and preys tried to evade predators. I am trying to solve a simplified ...
2
votes
0answers
193 views

Coloring graphs with reinforcement learning

I am trying to build an RL agent to solve the NP-hard problem graph coloring. The problem is quite challenging. This how I addressed it. The environment To preserve the scalability of the ...
2
votes
0answers
109 views

What is ratio of the objective function in the case of continuous action spaces?

I'm trying to implement the proximal policy optimization (PPO) algorithm. I'm confused on how to make it work with continuous action space. For discrete action space, the output of the network is the ...
2
votes
0answers
70 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-...
2
votes
0answers
92 views

How does Friend-or-Foe Q-learning intuitively work?

I read about Q-Learning and was reading about multi-agent environments. I tried to read the paper Friend-or-Foe Q-learning, but could not understand anything, except for a very vague idea. What does ...
2
votes
0answers
46 views

Does coarse coding with radial basis function generate fewer features?

I am learning about discretization of the state space when applying reinforcement learning to continuous state space. In this video the instructor, at 2:02, the instructor says that one benefit of ...
2
votes
0answers
390 views

Gym dict space as keras DQN agent input

I'm trying to make an AI to play my own card game. I have an OpenAI gym for the game with Dict as an observation space. It is nested dict, so I can't easily replace it with a tuple. I want to pass ...
2
votes
0answers
49 views

Inverse Reinforcement Learning for Markov Games

This is an Inverse Reinforcement Learning (IRL) problem. I have data (observations) on actions taken by a (real) agent. Given this data I want to estimate the likelihood of the observed actions in a Q-...
2
votes
0answers
91 views

Infinite horizon in Reinforcement Learning

I read this article: "Towards Autonomous Data Ferry Route Design through Reinforcement Learning" by Daniel Henkel and Timothy X Brown. It specifies an infinite horizon problem where they use as a ...
2
votes
0answers
57 views

Reinforcement Learning in Real Life/Practical Terms

In every day life, it seems that we all have various habits and actions that we perform. For example, we wake up and check our email/facebook etc. on our phones. We don't look at are current state ...
2
votes
0answers
74 views

Are there reinforcement learning algorithms that ensure convergence for continuous state space problems?

The Q-learning does not guarantee convergence for continuous state space problems (Why doesn't Q-learning converge when using function approximation?). In that case, is there an algorithm which ...
2
votes
0answers
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 ...
2
votes
0answers
63 views

How does the TRPO surrogate loss account for the error in the policy?

In the Trust Region Policy Optimization (TRPO) paper, on page 10, it is stated An informal overview is as follows. Our proof relies on the notion of coupling, where we jointly define the ...
2
votes
0answers
256 views

Why overfitting is bad in DQN?

It is mentioned by Fu 2019 that overfitting might have a negative effect on training DQN. They showed that with either early stopping or experience replay this effect could be reduced. The first is ...
2
votes
0answers
183 views

Why experience reply memory in DQN instead of a RNN memory?

I was trying to implement a DQN without experience reply memory, and the agent is not learning anything at all. I know from readings that experience reply is used for stabilizing gradients. But how ...
2
votes
0answers
431 views

Difficulty understanding Monte Carlo policy evaluation (state-value) for gridworld

I've been trying to read Sutton & Barto book chapter 5.1, but I'm still a bit confused about the procedure of using Monte Carlo policy evaluation (p.92), and now I just cant proceed anymore coding ...
2
votes
2answers
105 views

Running 2 NEAT nets on the same observations

So i have been playing around with neat-python. I made a program, applying neat, to play pinball on the Atari 2600. The code for that can be found in the file ...
2
votes
0answers
47 views

How does Hindsight Experience Replay cope with multiple goals?

What if there are multiple goals? For example, let's consider the bit-flipping environment as described in the paper HER with one small change: now, the goal is not some specific configuration, but ...
2
votes
0answers
89 views

Reinforcement learning for inventory management with dynamic changes to available products

Consider a shop owner who has to deal with having to buy for one week from a different supplier with several different brands. Another week a brand is removed or added from the market. Yet another ...
2
votes
0answers
164 views

Is Reinforcement Learning the future of Natural Language Processing?

I was reading about the grounding problem after seeing it mentioned in another answer today. The article states that, in order to avoid the "infinite regress" of defining all words with other words, ...
2
votes
0answers
73 views

Eligibility trace In Model-based Reinforcement Learning

In model-based reinforcement learning algorithms, the model of the environment is constructed to efficiently use samples, models such as Dyna, and Prioritize Sweeping. Moreover, eligibility trace ...
2
votes
0answers
40 views

How to include exploration in Gaussian policy

When dealing with continuous action spaces, a common choice when designing a policy in policy gradient methods is to learn mean and variance of actions for a specific state and then simply sample from ...
2
votes
0answers
170 views

Reward discounting in reinforcement learning for a Pong game

I am trying to understand how to train a neural network to win a Pong game using reinforcement learning, by following the blog post Spinning up a Pong AI with deep reinforcement learning. The ...
2
votes
1answer
466 views

Why does Q-learning converge to the optimal policy, even if the agent acts sub-optimally?

In Q-learning, during training, it doesn't matter how the agent selects actions. The algorithm always converges to the optimal policy. Why does this happen? What's the intuition?
2
votes
0answers
433 views

How many episodes does it take for a vanilla one-step actor-critic agent to master the OpenAI BipedalWalker-v2 problem?

I'm trying to solve the OpenAI BipedalWalker-v2 by using a one-step actor-critic agent. I'm implementing the solution using python and tensorflow. I'm following this pseudo-code taken from the book ...

1
3 4
5
6 7
14