Pinned Repositories
acrobot
RL agent for Gym acrobot environment
CMC_MoCo
Implementation of the algorithm Contrastive Multiview Coding (CMC) combined with Momentum Contrast (MoCo) for self-supervised learning of images.
connectx
Intelligent player of Tictactoe Game. Brief introduction to reinforcement learning by development of a agent applying policy iteration algorithm
farmdroid_arduino
Ce projet est la partie "microcontroleur" du projet Farmdroid qui est un système électronique permettant à une plantation de s'auto-alimenter et d'informer l'agriculteur de toutes les activités de sa plantation.
gaifo
Generative adversarial Imitation from Observation
gym-duckietown
Self-driving car simulator for the Duckietown universe
ifobl
Imitation from observation using behavioral learning
imitation-from-observation
Imitation from Observation using context translation. An algorithm to train agents to imitate experts based on demonstrations.
semantic_analyzer
A semantic analyzer of sentences and questions based on NLP.
w_distances
Just some implementations of word distance functions.
medric49's Repositories
medric49/gaifo
Generative adversarial Imitation from Observation
medric49/imitation-from-observation
Imitation from Observation using context translation. An algorithm to train agents to imitate experts based on demonstrations.
medric49/w_distances
Just some implementations of word distance functions.
medric49/acrobot
RL agent for Gym acrobot environment
medric49/atbswp
A minimalist macro recorder
medric49/CMC_MoCo
Implementation of the algorithm Contrastive Multiview Coding (CMC) combined with Momentum Contrast (MoCo) for self-supervised learning of images.
medric49/gym-duckietown
Self-driving car simulator for the Duckietown universe
medric49/ifobl
Imitation from observation using behavioral learning
medric49/semantic_analyzer
A semantic analyzer of sentences and questions based on NLP.
medric49/adversarial-imitation
Experimentation on recent advances of Adversarial Imitation from Observation algorithms
medric49/drqv2
DrQ-v2: Improved Data-Augmented Reinforcement Learning
medric49/embeddings
Just another word embedding algorithm
medric49/gym-maze
A basic 2D maze environment where an agent start from the top left corner and try to find its way to the bottom left corner.
medric49/habitat
medric49/holodeck
medric49/holodeck-1
High Fidelity Simulator for Reinforcement Learning and Robotics Research.
medric49/holodeck-engine
High Fidelity Simulator for Reinforcement Learning and Robotics Research.
medric49/ifo_virl
Imitation from Observation by synchronization with expert actions
medric49/ift6163_homeworks
medric49/lab
A customisable 3D platform for agent-based AI research
medric49/ngram
Just another test about n-gram models
medric49/NLTK_POS_tagging
medric49/plan2explore
Experiments on Plan2Explore algorithm
medric49/playground
medric49/spacy_parser
Parsing with Spacy
medric49/SupContrast
PyTorch implementation of "Supervised Contrastive Learning" (and SimCLR incidentally)
medric49/syntactic_analyzer
A syntactic analyzer based on analyses of probabilistic grammars
medric49/translator
medric49/word_orderer
Word orderer
medric49/wordcounter
Just some experimentation on a word counting task