# Curious Exploration and Return-based Memory Restoration for Deep Reinforcement Learning

arXiv: https://arxiv.org/abs/2105.00499 · HTML: https://mlsanity.com/paper/2105.00499/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 7 of its 21 references that are in the map.
- First posted on arXiv 2 May 2021.

## Builds on (most cited first, 7 of 7)

- [Continuous control with deep reinforcement learning](https://mlsanity.com/paper/1509.02971/) (2015)
- [Curiosity-driven Exploration by Self-supervised Prediction](https://mlsanity.com/paper/1705.05363/) (2017)
- [Hindsight Experience Replay](https://mlsanity.com/paper/1707.01495/) (2017)
- [Prioritized Experience Replay](https://mlsanity.com/paper/1511.05952/) (2015)
- [Deep Reinforcement Learning in Parameterized Action Space](https://mlsanity.com/paper/1511.04143/) (2015)
- [Reinforcement Learning with Parameterized Actions](https://mlsanity.com/paper/1509.01644/) (2015)
- [DeepSOCIAL: Social Distancing Monitoring and Infection Risk Assessment in COVID-19 Pandemic](https://mlsanity.com/paper/2008.11672/) (2020)

## Abstract (arXiv)

Reward engineering and designing an incentive reward function are non-trivial tasks to train agents in complex environments. Furthermore, an inaccurate reward function may lead to a biased behaviour which is far from an efficient and optimised behaviour. In this paper, we focus on training a single agent to score goals with binary success/failure reward function in Half Field Offense domain. As the major advantage of this research, the agent has no presumption about the environment which means it only follows the original formulation of reinforcement learning agents. The main challenge of using such a reward function is the high sparsity of positive reward signals. To address this problem, we use a simple prediction-based exploration strategy (called Curious Exploration) along with a Return-based Memory Restoration (RMR) technique which tends to remember more valuable memories. The proposed method can be utilized to train agents in environments with fairly complex state and action spaces. Our experimental results show that many recent solutions including our baseline method fail to learn and perform in complex soccer domain. However, the proposed method can converge easily to the nearly optimal behaviour. The video presenting the performance of our trained agent is available at http://bit.ly/HFO_Binary_Reward.