Siddharth Reddy

We propose a deep reinforcement learning framework for model-free shared autonomy that lifts these assumptions. Expand

We propose combining the standard maximum-likelihood objective of BC, which encourages the agent to imitate the expert in demonstrated states, with a penalty on the soft Bellman error of the soft Q function. Expand

We propose a simple alternative that still uses RL, but does not require learning a reward function, and achieves competitive results compared to GAIL on a variety of image-based and low-dimensional tasks. Expand

We propose an algorithm that safely and interactively learns a model of the user's reward function in a reinforcement learning setting with unknown dynamics, an unknown reward function, and unknown unsafe states. Expand

Autonomous robots often encounter challenging situations where their control policies fail and an expert human operator must briefly intervene, e.g., through teleoperation. Expand