Skip to main content
Share Your Experience: Take the 2024 Developer Survey
DeepQZero's user avatar
DeepQZero's user avatar
DeepQZero's user avatar
DeepQZero
  • Member for 3 years, 11 months
  • Last seen more than a week ago
9 votes
Accepted

Why is exploitation necessary during training?

5 votes
Accepted

What is the probability of selecting the greedy action in a 0.5-greedy selection method for the 2-armed bandit problem?

5 votes
Accepted

Does the AlphaZero algorithm keep the subtree statistics after each move during MCTS?

4 votes
Accepted

In Value Iteration, why can we initialize the value function arbitrarily?

4 votes

Bellman equation and inverse matrix method

4 votes

Why does the state-action value function, defined as an expected value of the reward and state value function, not need to follow a policy?

4 votes
Accepted

How do I recognise a bandit problem?

3 votes
Accepted

Why do we also need to normalize the action's values on continuous action spaces?

3 votes

Is there any difference between reward and return in reinforcement learning?

3 votes
Accepted

How to train a reinforcement learning agent from raw pixels?

3 votes
Accepted

Why does AlphaGo Zero select move based on exponentiated visit count?

3 votes
Accepted

How to convert sequences of images into state in DQN?

3 votes
Accepted

Why isn't it wise for us to completely erase our old Q value and replace it with the calculated Q value?

3 votes
Accepted

Should illegal moves be excluded from loss calculation in DQN algorithm?

3 votes

How does an episode end in OpenAI Gym's "MountainCar-v0" environment?

3 votes
Accepted

What is the purpose of a replay/memory buffer in Deep Q-Learning networks?

2 votes

Are there better loss functions than MSE for maze solver using deep learning?

2 votes
Accepted

Is it necessary to have a constant reward in the terminal state?

2 votes
Accepted

Confused about Monte Carlo first visit algorithm

2 votes

What happens when the probability of either one of the policies is 0 in Importance Sampling?

2 votes

Why is there no exploration-optimality trade-off in Q-learning?

2 votes

Why do we use $X_{I_t,t}$ and $v_{I_t}$ to denote the reward received and the at time step $t$ and the distribution of the chosen arm $I_t$?

2 votes

Comparing Reinforcement Learning models

2 votes

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

2 votes

Help with deep Q learning for 2048 game getting stuck

2 votes
Accepted

What is the value of a state when there is a certain probability that agent will die after each step?

1 vote
Accepted

How does policy evaluation work for continuous state space model-free approaches?

1 vote
Accepted

What's the right way of building a deep Q-network?

1 vote
Accepted

What should the action space for the card game Crib be?

1 vote

DQN arXiv 10-year anniversary: What are the outstanding problems being actively researched in deep Q-learning since 2019?