Picture for Amisha Bhaskar

Amisha Bhaskar

VARP: Reinforcement Learning from Vision-Language Model Feedback with Agent Regularized Preferences

Add code
Mar 18, 2025
Viaarxiv icon

Sketch-to-Skill: Bootstrapping Robot Learning with Human Drawn Trajectory Sketches

Add code
Mar 14, 2025
Viaarxiv icon

Mitigating Memorization in LLMs using Activation Steering

Add code
Mar 08, 2025
Viaarxiv icon

IMRL: Integrating Visual, Physical, Temporal, and Geometric Representations for Enhanced Food Acquisition

Add code
Sep 18, 2024
Viaarxiv icon

NAVINACT: Combining Navigation and Imitation Learning for Bootstrapping Reinforcement Learning

Add code
Aug 07, 2024
Viaarxiv icon

Adaptive Visual Imitation Learning for Robotic Assisted Feeding Across Varied Bowl Configurations and Food Types

Add code
Mar 19, 2024
Figure 1 for Adaptive Visual Imitation Learning for Robotic Assisted Feeding Across Varied Bowl Configurations and Food Types
Figure 2 for Adaptive Visual Imitation Learning for Robotic Assisted Feeding Across Varied Bowl Configurations and Food Types
Figure 3 for Adaptive Visual Imitation Learning for Robotic Assisted Feeding Across Varied Bowl Configurations and Food Types
Figure 4 for Adaptive Visual Imitation Learning for Robotic Assisted Feeding Across Varied Bowl Configurations and Food Types
Viaarxiv icon

LAVA: Long-horizon Visual Action based Food Acquisition

Add code
Mar 19, 2024
Figure 1 for LAVA: Long-horizon Visual Action based Food Acquisition
Figure 2 for LAVA: Long-horizon Visual Action based Food Acquisition
Figure 3 for LAVA: Long-horizon Visual Action based Food Acquisition
Figure 4 for LAVA: Long-horizon Visual Action based Food Acquisition
Viaarxiv icon

REBEL: A Regularization-Based Solution for Reward Overoptimization in Reinforcement Learning from Human Feedback

Add code
Dec 22, 2023
Figure 1 for REBEL: A Regularization-Based Solution for Reward Overoptimization in Reinforcement Learning from Human Feedback
Figure 2 for REBEL: A Regularization-Based Solution for Reward Overoptimization in Reinforcement Learning from Human Feedback
Figure 3 for REBEL: A Regularization-Based Solution for Reward Overoptimization in Reinforcement Learning from Human Feedback
Figure 4 for REBEL: A Regularization-Based Solution for Reward Overoptimization in Reinforcement Learning from Human Feedback
Viaarxiv icon

AG-CVG: Coverage Planning with a Mobile Recharging UGV and an Energy-Constrained UAV

Add code
Oct 11, 2023
Figure 1 for AG-CVG: Coverage Planning with a Mobile Recharging UGV and an Energy-Constrained UAV
Figure 2 for AG-CVG: Coverage Planning with a Mobile Recharging UGV and an Energy-Constrained UAV
Figure 3 for AG-CVG: Coverage Planning with a Mobile Recharging UGV and an Energy-Constrained UAV
Figure 4 for AG-CVG: Coverage Planning with a Mobile Recharging UGV and an Energy-Constrained UAV
Viaarxiv icon