-
Universidade Federal do Rio Grande Do Sul
- Brazil
Pinned Loading
-
MOparetoQlearning
MOparetoQlearning PublicMultiobjective Reinforcement Learning using Pareto dominating Policies in Discrete Problems
Python 8
-
Pareto-Deep-Q-Networks
Pareto-Deep-Q-Networks PublicImplementation of Pareto Deep Q Networks in a multi-objective Gym Reinforcement Learning Environment
-
Hand-written-Iterative-Closest-Point-in-Lidar-Sensor-Data
Hand-written-Iterative-Closest-Point-in-Lidar-Sensor-Data PublicThe purpose of this repository is to utilize a dataset of sensor scans obtained from LiDAR (Light Detection and Ranging) data and find a path using its Cloud Points and hand written ICP
Jupyter Notebook
-
Face-Recognition-with-Deep-Metric-Learning
Face-Recognition-with-Deep-Metric-Learning PublicThis repository uses Deep Metric Learning and a dataset of celebrities with and without masks to identify masked people.
Jupyter Notebook 1
-
rag-with-clusterization-of-embeddings
rag-with-clusterization-of-embeddings PublicArchiteture to create a RAG with a clusterization filter
Python 2
-
Pareto-Deep-Q-networks-in-Traffic-Environment-Gym-City-Flow
Pareto-Deep-Q-networks-in-Traffic-Environment-Gym-City-Flow PublicMulti Objective Reinforcement Learning algorithm Pareto Deep Q networks in Traffic Environment using City Flow Gym . WIP
Python 2
If the problem persists, check the GitHub status page or contact support.