Adversarial imitation learning from visual observations using latent information
We focus on the problem of imitation learning from visual observations, where the learning
agent has access to videos of experts as its sole learning source. The challenges of this …
agent has access to videos of experts as its sole learning source. The challenges of this …
Visually robust adversarial imitation learning from videos with contrastive learning
We propose C-LAIfO, a computationally efficient algorithm designed for imitation learning
from videos in the presence of visual mismatch between agent and expert domains. We …
from videos in the presence of visual mismatch between agent and expert domains. We …
A Model-Based Approach for Improving Reinforcement Learning Efficiency Leveraging Expert Observations
This paper investigates how to incorporate expert observations (without explicit information
on expert actions) into a deep reinforcement learning setting to improve sample efficiency …
on expert actions) into a deep reinforcement learning setting to improve sample efficiency …
Reliable deep reinforcement learning: stable training and robust deployment
J Queeney - 2023 - search.proquest.com
Deep reinforcement learning (RL) represents a data-driven framework for sequential
decision making that has demonstrated the ability to solve challenging control tasks. This …
decision making that has demonstrated the ability to solve challenging control tasks. This …
On the use of expert data to imitate behavior and accelerate Reinforcement Learning
V Giammarino - 2024 - search.proquest.com
This dissertation examines the integration of expert datasets to enhance the data efficiency
of online Deep Reinforcement Learning (DRL) algorithms in large state and action space …
of online Deep Reinforcement Learning (DRL) algorithms in large state and action space …