Episodic Self-Imitation Learning with Hindsight

TL;DR

This paper introduces episodic self-imitation learning with a trajectory selection module and adaptive loss, significantly improving reinforcement learning efficiency in continuous control tasks with sparse rewards.

Contribution

It proposes a novel episodic self-imitation algorithm that leverages entire episodes with hindsight and includes a selection module to filter uninformative samples, outperforming standard methods.

Findings

Outperforms baseline on-policy algorithms in experiments.

Achieves comparable results to state-of-the-art off-policy algorithms.

Effectively handles sparse reward problems in continuous control environments.

Abstract

Episodic self-imitation learning, a novel self-imitation algorithm with a trajectory selection module and an adaptive loss function, is proposed to speed up reinforcement learning. Compared to the original self-imitation learning algorithm, which samples good state-action pairs from the experience replay buffer, our agent leverages entire episodes with hindsight to aid self-imitation learning. A selection module is introduced to filter uninformative samples from each episode of the update. The proposed method overcomes the limitations of the standard self-imitation learning algorithm, a transitions-based method which performs poorly in handling continuous control environments with sparse rewards. From the experiments, episodic self-imitation learning is shown to perform better than baseline on-policy algorithms, achieving comparable performance to state-of-the-art off-policy algorithms in several simulated robot control tasks. The trajectory selection module is shown to prevent the agent learning undesirable hindsight experiences. With the capability of solving sparse reward problems in continuous control settings, episodic self-imitation learning has the potential to be applied to real-world problems that have continuous action spaces, such as robot guidance and manipulation.