Picture for Shivam Goel

Shivam Goel

NovelGym: A Flexible Ecosystem for Hybrid Planning and Learning Agents Designed for Open Worlds

Add code
Jan 07, 2024
Viaarxiv icon

A Framework for Few-Shot Policy Transfer through Observation Mapping and Behavior Cloning

Add code
Oct 13, 2023
Viaarxiv icon

RAPid-Learn: A Framework for Learning to Recover for Handling Novelties in Open-World Environments

Add code
Jun 24, 2022
Figure 1 for RAPid-Learn: A Framework for Learning to Recover for Handling Novelties in Open-World Environments
Figure 2 for RAPid-Learn: A Framework for Learning to Recover for Handling Novelties in Open-World Environments
Figure 3 for RAPid-Learn: A Framework for Learning to Recover for Handling Novelties in Open-World Environments
Figure 4 for RAPid-Learn: A Framework for Learning to Recover for Handling Novelties in Open-World Environments
Viaarxiv icon

SPOTTER: Extending Symbolic Planning Operators through Targeted Reinforcement Learning

Add code
Dec 24, 2020
Figure 1 for SPOTTER: Extending Symbolic Planning Operators through Targeted Reinforcement Learning
Figure 2 for SPOTTER: Extending Symbolic Planning Operators through Targeted Reinforcement Learning
Figure 3 for SPOTTER: Extending Symbolic Planning Operators through Targeted Reinforcement Learning
Figure 4 for SPOTTER: Extending Symbolic Planning Operators through Targeted Reinforcement Learning
Viaarxiv icon