Most Popular
1500 questions
7
votes
1 answer
When does the selection phase exactly end in MCTS?
All sources I can find provide a similar explanation to each phase.
In the Selection Phase, we start at the root and choose child nodes until reaching a leaf. Once the leaf is reached (assuming the game is not terminated), we enter the Expansion…
Ralff
- 173
- 5
7
votes
1 answer
A* is similar to Dijkstra with reduced cost
According to this Wikipedia article
If the heuristic $h$ satisfies the additional condition $h(x) \leq d(x, y) + h(y)$ for every edge $(x, y)$ of the graph (where $d$ denotes the length of that edge), then $h$ is called monotone, or consistent. In…
Shrey Shrivastava
- 71
- 2
7
votes
1 answer
Do you know any examples of geometric deep learning used in industry?
I'm interested in the industrial use of GDL (see https://arxiv.org/abs/1611.08097). Is it used in industry? That is, does any company have access to non-Euclidean data and process it directly instead of converting it to a more standard format?
Guillermo Mosse
- 327
- 1
- 10
7
votes
2 answers
Which kind of prioritized experience replay should I use?
The Prioritized Experience Replay paper gives two different ways of sampling from the replay buffer. One, called "proportional prioritization", assigns each transition a priority proportional to its TD-error.
$$p_i = |\delta_i|+\epsilon$$
The…
Philip Raeisghasem
- 2,074
- 12
- 30
7
votes
4 answers
Is "AIAngel" (Patreon) a fake?
These guys here: https://www.patreon.com/AiAngel are saying that they've created a AI who can chat and stream. As the so-called administrator "Rogue" said:
this chat/streamer bot are no fake.
Also, there's more about the dynamics of this…
M.N.Raia
- 181
- 1
- 1
- 5
7
votes
1 answer
What loss function to use when labels are probabilities?
What loss function is most appropriate when training a model with target values that are probabilities? For example, I have a 3-output model. I want to train it with a feature vector $x=[x_1, x_2, \dots, x_N]$ and a target $y=[0.2, 0.3, 0.5]$.
It…
Thomas Johnson
- 173
- 4
7
votes
2 answers
How can fuzzy logic be used in creating AI?
Fuzzy logic is the logic where every statement can have any real truth value between 0 and 1.
How can fuzzy logic be used in creating AI? Is it useful for certain decision problems involving multiple inputs? Can you give an example of an AI that…
wythagoras
- 1,521
- 12
- 28
7
votes
2 answers
Why don't people use projected Bellman error with deep neural networks?
Projected Bellman error has shown to be stable with linear function approximation. The technique is not at all new. I can only wonder why this technique is not adopted to use with non-linear function approximation (e.g. DQN)? Instead, a less…
Phizaz
- 520
- 3
- 13
7
votes
1 answer
Concrete examples of OpenCog's functionality
Does anyone know what specific tasks the OpenCog environment is capable of performing? I have glanced though their wiki and a few of the pages on Goertzel's site and the AI.SE. So far I could only find some technical documentation regarding theory…
k.c. sayz 'k.c sayz'
- 2,121
- 13
- 27
7
votes
2 answers
In the n-step off-policy SARSA update, why do we multiply the entire update by $\rho$?
In Sutton & Barto's book (2nd ed) page 149, there is the equation 7.11
I am having a hard time understanding this equation.
I would have thought that we should be moving $Q$ towards $G$, where $G$ would be corrected by importance sampling, but only…
Antoine Savine
- 173
- 4
7
votes
2 answers
Reinforcement Learning with long term rewards and fixed states and actions
I have read a lot about RL algorithms, that update the action-value function at each step with the currently gained reward. The requirement here is, that the reward is obtained after each step.
I have a case, where I have three steps, that have to…
Jan
- 361
- 3
- 13
7
votes
2 answers
Do we have to use CNN for Deep Q Learning?
I read top articles on Google Search about Deep…
malioboro
- 2,859
- 3
- 23
- 47
7
votes
1 answer
2 Player Games in OpenAI Retro
I have been using OpenAI Retro for awhile, and I wanted to experiment with two player games. By two player games, I mean co-op games like "Tennis-Atari2600" or even Pong, where 2 agents are present in one environment.
There is a parameter for…
niallmandal
- 211
- 2
- 6
7
votes
2 answers
Would the people of the 19th Century call our conventional software today artificial intelligence?
It is possible that the view of what is impressive enough in computer behavior to be called intelligence changes with each decade as we adjust to what capabilities are made available in products and services.
Douglas Daseeco
- 7,543
- 1
- 28
- 63
7
votes
1 answer
How do we know if GPT-2 is a better language model?
You may have heard of GPT2, a new language model. It has recently attracted attention from the general public as the foundation that published the paper, OpenAI, ironically refused to share the whole model fearing dangerous implications. Along the…
Lucas Morin
- 262
- 2
- 13