Picture for Paul Daoudi

Paul Daoudi

Enhancing Reinforcement Learning Agents with Local Guides

Add code
Feb 21, 2024
Viaarxiv icon

Improving a Proportional Integral Controller with Reinforcement Learning on a Throttle Valve Benchmark

Add code
Feb 21, 2024
Viaarxiv icon

A Trust Region Approach for Few-Shot Sim-to-Real Reinforcement Learning

Add code
Dec 24, 2023
Figure 1 for A Trust Region Approach for Few-Shot Sim-to-Real Reinforcement Learning
Figure 2 for A Trust Region Approach for Few-Shot Sim-to-Real Reinforcement Learning
Figure 3 for A Trust Region Approach for Few-Shot Sim-to-Real Reinforcement Learning
Figure 4 for A Trust Region Approach for Few-Shot Sim-to-Real Reinforcement Learning
Viaarxiv icon

Conservative Exploration for Policy Optimization via Off-Policy Policy Evaluation

Add code
Dec 24, 2023
Figure 1 for Conservative Exploration for Policy Optimization via Off-Policy Policy Evaluation
Figure 2 for Conservative Exploration for Policy Optimization via Off-Policy Policy Evaluation
Figure 3 for Conservative Exploration for Policy Optimization via Off-Policy Policy Evaluation
Figure 4 for Conservative Exploration for Policy Optimization via Off-Policy Policy Evaluation
Viaarxiv icon