Picture for Erwan Renaudo

Erwan Renaudo

Unsupervised Learning of Effective Actions in Robotics

Add code
Apr 03, 2024
Viaarxiv icon

Action Noise in Off-Policy Deep Reinforcement Learning: Impact on Exploration and Performance

Add code
Jun 08, 2022
Figure 1 for Action Noise in Off-Policy Deep Reinforcement Learning: Impact on Exploration and Performance
Figure 2 for Action Noise in Off-Policy Deep Reinforcement Learning: Impact on Exploration and Performance
Figure 3 for Action Noise in Off-Policy Deep Reinforcement Learning: Impact on Exploration and Performance
Figure 4 for Action Noise in Off-Policy Deep Reinforcement Learning: Impact on Exploration and Performance
Viaarxiv icon

How do Offline Measures for Exploration in Reinforcement Learning behave?

Add code
Oct 29, 2020
Figure 1 for How do Offline Measures for Exploration in Reinforcement Learning behave?
Viaarxiv icon

Improving the Exploration of Deep Reinforcement Learning in Continuous Domains using Planning for Policy Search

Add code
Oct 24, 2020
Figure 1 for Improving the Exploration of Deep Reinforcement Learning in Continuous Domains using Planning for Policy Search
Figure 2 for Improving the Exploration of Deep Reinforcement Learning in Continuous Domains using Planning for Policy Search
Figure 3 for Improving the Exploration of Deep Reinforcement Learning in Continuous Domains using Planning for Policy Search
Figure 4 for Improving the Exploration of Deep Reinforcement Learning in Continuous Domains using Planning for Policy Search
Viaarxiv icon

Coping with the variability in humans reward during simulated human-robot interactions through the coordination of multiple learning strategies

Add code
May 06, 2020
Figure 1 for Coping with the variability in humans reward during simulated human-robot interactions through the coordination of multiple learning strategies
Figure 2 for Coping with the variability in humans reward during simulated human-robot interactions through the coordination of multiple learning strategies
Figure 3 for Coping with the variability in humans reward during simulated human-robot interactions through the coordination of multiple learning strategies
Figure 4 for Coping with the variability in humans reward during simulated human-robot interactions through the coordination of multiple learning strategies
Viaarxiv icon

How to reduce computation time while sparing performance during robot navigation? A neuro-inspired architecture for autonomous shifting between model-based and model-free learning

Add code
Apr 30, 2020
Figure 1 for How to reduce computation time while sparing performance during robot navigation? A neuro-inspired architecture for autonomous shifting between model-based and model-free learning
Figure 2 for How to reduce computation time while sparing performance during robot navigation? A neuro-inspired architecture for autonomous shifting between model-based and model-free learning
Figure 3 for How to reduce computation time while sparing performance during robot navigation? A neuro-inspired architecture for autonomous shifting between model-based and model-free learning
Figure 4 for How to reduce computation time while sparing performance during robot navigation? A neuro-inspired architecture for autonomous shifting between model-based and model-free learning
Viaarxiv icon

Action Representations in Robotics: A Taxonomy and Systematic Classification

Add code
Sep 12, 2018
Figure 1 for Action Representations in Robotics: A Taxonomy and Systematic Classification
Figure 2 for Action Representations in Robotics: A Taxonomy and Systematic Classification
Figure 3 for Action Representations in Robotics: A Taxonomy and Systematic Classification
Figure 4 for Action Representations in Robotics: A Taxonomy and Systematic Classification
Viaarxiv icon