6 papers
Reward Structure Shapes the Interaction Between Episodic Exploration and Neural Memory in Reinforcement Learning
Jai Malegaonkar, Rohan Patil, Henrik I. Christensen
In partially observable reinforcement learning, agents face a dual bottleneck: they must explore to encounter rewarding states and retain that experience in memory to optimize thei…
Randomness is sometimes necessary for coordination
Rohan Patil, Jai Malegaonkar, Henrik I. Christensen
Full parameter sharing is standard in cooperative multi-agent reinforcement learning (MARL) for homogeneous agents. Under permutation-symmetric observations, however, a shared dete…
BOIL: Learning Environment Personalized Information
Rohan Patil, Henrik I. Christensen
Navigating complex environments poses challenges for multi-agent systems, requiring efficient extraction of insights from limited information. In this paper, we introduce the Black…
Squint: Fast Visual Reinforcement Learning for Sim-to-Real Robotics
Abdulaziz Almuzairee, Henrik I. Christensen
Visual reinforcement learning is appealing for robotics but expensive -- off-policy methods are sample-efficient yet slow; on-policy methods parallelize well but waste samples. Rec…
GAMMS: Graph based Adversarial Multiagent Modeling Simulator
Rohan Patil, Jai Malegaonkar, Xiao Jiang +3
As intelligent systems and multi-agent coordination become increasingly central to real-world applications, there is a growing need for simulation tools that are both scalable and…
Merging and Disentangling Views in Visual Reinforcement Learning for Robotic Manipulation
Abdulaziz Almuzairee, Rohan Patil, Dwait Bhatt +1
Vision is well-known for its use in manipulation, especially using visual servoing. Due to the 3D nature of the world, using multiple camera views and merging them creates better r…