Curriculum Offline Imitating Learning

Minghuan Liu, Hanye Zhao, Zhengyu Yang, Jian Shen, Weinan Zhang, Li Zhao, Tie-Yan Liu

Keywords: reinforcement learning, offline reinforcement learning

TL;DR: In this paper, we propose Curriculum Offline Imitating Learning (COIL) that utilizes an experience picking strategy to improve the current policy with the data sampled by adaptive neighbor policies, and thus produce stages of curriculum.

Abstract:

Offline reinforcement learning (RL) tasks require the agent to learn from a pre-collected dataset with no further interactions with the environment.
Despite the potential to surpass the behavioral policies, RL-based methods are generally impractical due to the training instability and bootstrapping the extrapolation errors, which always require careful hyperparameter tuning via online evaluation.
In contrast, offline imitation learning (IL) has no such issues since it learns the policy directly without estimating the value function by bootstrapping.
However, IL is usually limited in the capability of the behavioral policy and tends to learn a mediocre behavior from the dataset collected by the mixture of policies.
In this paper, we aim to take advantage of IL but mitigate such a drawback.
Observing that behavior cloning is able to imitate neighboring policies with less data, we propose \textit{Curriculum Offline Imitation Learning (COIL)}, which utilizes an experience picking strategy to make the agent imitate from adaptive neighboring policies with a higher return, and improves the current policy along curriculum stages.
On continuous control benchmarks, we compare COIL against both imitation-based methods and RL-based methods, showing that COIL not only avoids just learning a mediocre behavior on mixed datasets but is also even competitive with state-of-the-art offline RL methods.

Code Of Conduct: I certify that all co-authors of this work have read and commit to adhering to the NeurIPS Statement on Ethics, Fairness, Inclusivity, and Code of Conduct.

Code: https://github.com/apexrl/COIL