ACDER: Augmented Curiosity-Driven Experience Replay

Abstract

Exploration in environments with sparse feedback remains a challenging research problem in reinforcement learning (RL). When the RL agent explores the environment randomly, it results in low exploration efficiency, especially in robotic manipulation tasks with high dimensional continuous state and action space. In this paper, we propose a novel method, called Augmented Curiosity-Driven Experience Replay (ACDER), which leverages (i) a new goal-oriented curiosity-driven exploration to encourage the agent to pursue novel and task-relevant states more purposefully and (ii) the dynamic initial states selection as an automatic exploratory curriculum to further improve the sample-efficiency. Our approach complements Hindsight Experience Replay (HER) by introducing a new way to pursue valuable states. Experiments conducted on four challenging robotic manipulation tasks with binary rewards, including Reach, Push, Pick&Place and Multi-step Push. The empirical results show that our proposed method significantly outperforms existing methods in the first three basic tasks and also achieves satisfactory performance in multi-step robotic task learning.

References in corpus (18)

• Continuous control with deep reinforcement learning
• Prioritized Experience Replay
• QT-Opt: Scalable Deep Reinforcement Learning for Vision-Based Robotic Manipulation
• Large-Scale Study of Curiosity-Driven Learning
• Count-Based Exploration with Neural Density Models
• Hindsight Experience Replay
• #Exploration: A Study of Count-Based Exploration for Deep Reinforcement Learning
• Learning by Playing - Solving Sparse Reward Tasks from Scratch
• Exploration by Random Network Distillation
• Sample Efficient Actor-Critic with Experience Replay
• Episodic Curiosity through Reachability
• Data-efficient Deep Reinforcement Learning for Dexterous Manipulation
• Learning Gentle Object Manipulation with Curiosity-Driven Deep Reinforcement Learning
• Computational Theories of Curiosity-Driven Learning
• Energy-Based Hindsight Experience Prioritization
• ARCHER: Aggressive Rewards to Counter bias in Hindsight Experience Replay
• Deep Curiosity Search: Intra-Life Exploration Can Improve Performance on Challenging Deep Reinforcement Learning Problems
• Never Forget: Balancing Exploration and Exploitation via Learning Optical Flow