# ARCHER: Aggressive Rewards to Counter bias in Hindsight Experience Replay

arXiv: https://arxiv.org/abs/1809.02070 · HTML: https://mlsanity.com/paper/1809.02070/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 6 Sep 2018.

## Built on by (most cited first, 9 of 9)

- [Universal Value Density Estimation for Imitation Learning and Goal-Conditioned Reinforcement Learning](https://mlsanity.com/paper/2002.06473/) (2020)
- [Unbiased Methods for Multi-Goal Reinforcement Learning](https://mlsanity.com/paper/2106.08863/) (2021)
- [Understanding when Dynamics-Invariant Data Augmentations Benefit Model-Free Reinforcement Learning Updates](https://mlsanity.com/paper/2310.17786/) (2023)
- [USHER: Unbiased Sampling for Hindsight Experience Replay](https://mlsanity.com/paper/2207.01115/) (2022)
- [Null Counterfactual Factor Interactions for Goal-Conditioned Reinforcement Learning](https://mlsanity.com/paper/2505.03172/) (2025)
- [Spinning Straw into Gold: Relabeling LLM Agent Trajectories in Hindsight for Successful Demonstrations](https://mlsanity.com/paper/2607.04235/) (2026)
- [Hindsight Generative Adversarial Imitation Learning](https://mlsanity.com/paper/1903.07854/) (2019)
- [On the Convergence and Stability of Upside-Down Reinforcement Learning, Goal-Conditioned Supervised Learning, and Online Decision Transformers](https://mlsanity.com/paper/2502.05672/) (2025)
- [Adaptable Hindsight Experience Replay for Search-Based Learning](https://mlsanity.com/paper/2511.03405/) (2025)

## Abstract (arXiv)

Experience replay is an important technique for addressing sample-inefficiency in deep reinforcement learning (RL), but faces difficulty in learning from binary and sparse rewards due to disproportionately few successful experiences in the replay buffer. Hindsight experience replay (HER) was recently proposed to tackle this difficulty by manipulating unsuccessful transitions, but in doing so, HER introduces a significant bias in the replay buffer experiences and therefore achieves a suboptimal improvement in sample-efficiency. In this paper, we present an analysis on the source of bias in HER, and propose a simple and effective method to counter the bias, to most effectively harness the sample-efficiency provided by HER. Our method, motivated by counter-factual reasoning and called ARCHER, extends HER with a trade-off to make rewards calculated for hindsight experiences numerically greater than real rewards. We validate our algorithm on two continuous control environments from DeepMind Control Suite - Reacher and Finger, which simulate manipulation tasks with a robotic arm - in combination with various reward functions, task complexities and goal sampling strategies. Our experiments consistently demonstrate that countering bias using more aggressive hindsight rewards increases sample efficiency, thus establishing the greater benefit of ARCHER in RL applications with limited computing budget.