New answers tagged open-ai
1
vote
How to disapprove some who says that AI is capable of irrational thought and emotions
AI are based on the idea of distribution matching, no matter what you are doing.
Is it a discriminative problem? then match $p_\theta(y|x)$ with the true one, using examples
Is it a generative problem?...
1
vote
Dynamic text completion
That is achieved usually via web-socket, however it is not available yet
I see some workaround like https://github.com/cookeem/chatgpt-service, which just get's the full answer and then streams word ...
1
vote
How to prompt Open AI for a variable list length?
The behavior you're observing is likely due to the nature of how GPT-3.5 generates text. It's a complex model trained on a large dataset, but it doesn't have an inherent understanding of the concepts ...
1
vote
How do open source LLMs compare to GPT-4?
How do open source LLMs compare to GPT-4?
https://huggingface.co/spaces/lmsys/chatbot-arena-leaderboard has a leaderboard containing both open source LLMs and GPT-4 (and GPT-3.5-turbo):
Model
⭐ ...
6
votes
Accepted
How do you deal with movement inertia in an environment after a step?
The simplest answer is that the inertia (or velocity, if the mass of the ball is not a variable) should be part of the observable state that the agent has access to. In RL there are usually two parts ...
4
votes
How do you deal with movement inertia in an environment after a step?
In RL usually a "discretized" time MDP is used in case of continuous time problems, with the idea that if we evaluate enough time the policy, we can approximate it the continuous case. This ...
Top 50 recent answers are included
Related Tags
open-ai × 107reinforcement-learning × 51
gym × 26
chatgpt × 16
machine-learning × 13
deep-learning × 11
python × 11
gpt-3 × 11
q-learning × 8
deep-rl × 8
embeddings × 8
ai-design × 7
transformer × 6
gpt × 6
large-language-models × 6
natural-language-processing × 5
chat-bots × 5
tensorflow × 4
dqn × 4
game-ai × 4
environment × 4
fine-tuning × 4
rewards × 3
deepmind × 3
neural-networks × 2