VittorioGiammarino

traffic_flow_on_a_ring_with_a_single_autonomous_vehicle

Code used to write the journal "Traffic Flow on a Ring with a Single Autonomous Vehicle: an Interconnected Stability Perspective"

AIL_from_visual_obs

Offline_RL_pytorch

EC503_Learning_policy_for_MDP

Project on learning policy for an MDP stochastic shorthest path problem.

Grid_World

Hierarchical_extensions_of_RL_algortihms_in_the_options_framework

HIL_mountainCar

Hierarchical imitation learning for the MountainCar openAI-Gym environment

Human-like-with-DHRL

Code used to generate the results for the paper "Human-like Performance on a Foraging Task with Deep Hierarchical Reinforcement Learning using Human Priors"

Learning-from-humans-combining-imitation-and-deep-on-policy-reinforcement-learning-to-accomplish-su

MPC-RL

MPC-RL

Provable_Hierarchical_Imitation_Learning_via_EM

Code for "Provable_Hierarchical_Imitation_Learning_via_EM"

Bootstrapping-RL-4-Sequential-Picking

DDPG_bipedalWalk

Solving the BipedalWalker OpenAIGym using Deep Deterministic Policy Gradient

HIL_humanForagingData

HIL_toy_examples

HIL_toy_python

Code for HIL in python

HTRPO-RAT

Htrpo, HUAtrpo and different imitations tested on the rat experiment

human_level_performance_without_preprocessing_obs_and_explicit_imitation

Online_BWforHIL

Opportunities-and-Challenges-of-Using-Animal-Videos-in-Reinforcement-Learning-for-Navigation

RL-for-unloading-from-pixels

VRL3