POPLIN | Arxiv Link Abstract Model-based reinforcement learning | Reinforcement Learning library

POPLIN is a Python library typically used in Artificial Intelligence, Reinforcement Learning, Deep Learning, Pytorch applications. POPLIN has no bugs, it has no vulnerabilities, it has build file available and it has low support. You can download it from GitHub.

Arxiv Link Abstract Model-based reinforcement learning (MBRL) with model-predictive control or online planning has shown great potential for locomotion control tasks in terms of both sample efficiency and asymptotic performance. However, the existing planning methods search from candidate sequences that are randomly generated in the action space. We argue that random action search is inefficient in complex high-dimensional environments. In this paper, we propose a novel MBRL algorithm, model-based policy planning (POPLIN), that combines policy networks with online planning. More specifically, we formulate action planning at each time-step as an optimization problem using neural networks. We experiment with both optimization w.r.t. the action sequences initialized from the policy network, and also online optimization directly w.r.t. the parameters of the policy network. We show that POPLIN obtains state-of-the-art performance in the MuJoCo benchmarking environments, being about 3x more sample efficient than the state-of-the-art algorithms, such as PETS, TD3 and SAC. To explain the effectiveness of our algorithm, we show that the optimization surface in parameter space is smoother than in action space. Further more, we found the distilled policy network can be effectively applied without the expansive model predictive control during test time for some environments such as Cheetah.