ChristosPeridis
Research Assistant in Lifelong Deep Reinforcement Learning at Loughborough University
Loughborough UniversityLoughborough
Pinned Repositories
agenthive-R3L
AgentHive provides the primitives and helpers for a seamless usage of robohive within TorchRL.
Automatic-Image-Colorization-Matlab
Automatic Image Colorization using Machine Learning techniques.
BiomedParse_UnimatrixZero_Research
BiomedParse: A Foundation Model for Joint Segmentation, Detection, and Recognition of Biomedical Objects Across Nine Modalities
CompoSuite-R3L
Official release of CompoSuite, a compositional RL benchmark
CompoSuite-spinningup-R3L
Spinning Up adaptation to train on CompoSuite via mulit-task and compositional PPO
Example
Gymnasium-Robotics-R3L
A collection of robotics simulation environments for reinforcement learning
R3L
Leveraging the combined forces of the Gymnasium API and MuJoCo simulator to perform experiments with DRL SOTA algorithms on Robotic scenarios using the highly scalable and distributed Ray API
L2D2-C_baselines
DMIU-ShELL Baselines Experiments
CT-graph
ChristosPeridis's Repositories
ChristosPeridis/BiomedParse_UnimatrixZero_Research
BiomedParse: A Foundation Model for Joint Segmentation, Detection, and Recognition of Biomedical Objects Across Nine Modalities
ChristosPeridis/agenthive-R3L
AgentHive provides the primitives and helpers for a seamless usage of robohive within TorchRL.
ChristosPeridis/Automatic-Image-Colorization-Matlab
Automatic Image Colorization using Machine Learning techniques.
ChristosPeridis/CompoSuite-R3L
Official release of CompoSuite, a compositional RL benchmark
ChristosPeridis/CompoSuite-spinningup-R3L
Spinning Up adaptation to train on CompoSuite via mulit-task and compositional PPO
ChristosPeridis/Example
ChristosPeridis/Exploration
Attempt to work with PyCharm and Git for ML porjects
ChristosPeridis/Exploration02
Attempting to work with PyCharm and GitHub for ML projects
ChristosPeridis/Gymnasium-Robotics-R3L
A collection of robotics simulation environments for reinforcement learning
ChristosPeridis/LIBERO-R3L
Benchmarking Knowledge Transfer in Lifelong Robot Learning tailored to R3L workloads
ChristosPeridis/R3L
Leveraging the combined forces of the Gymnasium API and MuJoCo simulator to perform experiments with DRL SOTA algorithms on Robotic scenarios using the highly scalable and distributed Ray API
ChristosPeridis/RL_with_UR5_Robot
ChristosPeridis/stable-baselines3-R3L
An Ehanced edition of PyTorch version of Stable Baselines, reliable implementations of reinforcement learning algorithms that incorporates lifelong learning for the need of the R3L project