desert_ranger's user avatar
desert_ranger's user avatar
desert_ranger's user avatar
desert_ranger
  • Member for 4 years, 2 months
  • Last seen more than a month ago
6 votes
5 answers
11k views

How is GPT 4 able to solve math?

4 votes
1 answer
2k views

What's the relationship between number of heads and embedding dimension in Transformers?

3 votes
1 answer
376 views

Why do Q-values diverge without a target network?

3 votes
1 answer
3k views

Why do my rewards reduce after extensive training using D3QN?

3 votes
1 answer
76 views

Can a convolutional network predict states for a RL Agent

3 votes
1 answer
188 views

Is it always a good idea to use deterministic policies during testing?

2 votes
1 answer
194 views

How does one normalize observations in online reinforcement learning

2 votes
1 answer
82 views

What do simulations mean in the context of the AlphaGoZero paper?

2 votes
1 answer
132 views

How does replacing states with latent representations help RL agents?

2 votes
0 answers
367 views

How does one stack multiple observations in the input layer of a convolutional neural network?

2 votes
1 answer
233 views

What do equations 1 and 3 describe in the "Image Augmentation Is All You Need: Regularizing Deep Reinforcement Learning from Pixels" paper?

2 votes
0 answers
68 views

How does one detect training instabilities in DQN?

2 votes
1 answer
167 views

Why does Advantage Learning help function approximators?

2 votes
0 answers
144 views

What is the difference between Probabilistic Graphical models and Graph Neural networks?

1 vote
0 answers
89 views

What do state features mean in the context of inverse RL?

1 vote
0 answers
52 views

Alternatives to using RL to explore an environment

1 vote
1 answer
279 views

Does it make sense to provide a DQN with negative rewards for a network with relu and sigmoid activations?

1 vote
0 answers
67 views

How does having zero advantage help with identifiability?

1 vote
1 answer
50 views

Why do some techniques use random augmentations during convolution processes

1 vote
1 answer
444 views

How can I use a ResNet as a function approximator for pixel based reinforcement learning?

1 vote
1 answer
138 views

Should my agent be taking varying number of steps?

1 vote
1 answer
175 views

How does the neural network learn when used in the REINFORCE algorithm?

1 vote
1 answer
47 views

Why did Distributional Q Learning go out of popularity?

1 vote
0 answers
1k views

What is the difference between derivation and entailment?

1 vote
0 answers
63 views

How do I set up rewards to account for unmanned aerial vehicle crashes?

1 vote
1 answer
618 views

What are the variables that need to be saved and loaded, so that a DQN model starts where it left off?

1 vote
1 answer
128 views

How would one normalize observations in off-policy online reinforcement learning?

0 votes
1 answer
367 views

How do I add Entropy to a PPO algorithm?

0 votes
1 answer
119 views

Understanding KL Stopping and KL Cutoff for the PPO algorithm

0 votes
1 answer
66 views

How does CURL extract labels from logits? [closed]