Ryuki Tachibana

OptLayer - Practical Constrained Optimization for Deep Reinforcement Learning in the Real World

2017 · arXiv (Cornell University)

While deep reinforcement learning techniques have recently produced considerable achievements on many decision-making problems, their use in robotics has largely been limited to simulated worlds or restricted motions, since unconstrained trial-and-error interactions in the real …

Internal Model from Observations for Reward Shaping

2018 · arXiv (Cornell University)

Reinforcement learning methods require careful design involving a reward function to obtain the desired action policy for a given task. In the absence of hand-crafted reward functions, prior work on the topic has proposed several …

Constrained Exploration and Recovery from Experience Shaping

2018 · arXiv (Cornell University)

We consider the problem of reinforcement learning under safety requirements, in which an agent is trained to complete a given task, typically formalized as the maximization of a reward signal over time, while concurrently avoiding …