Actrce Augmenting Experience Via Teachers Advice For Multigoal Reinforcement Learning
ASecurity**arXiv ID:** 1902.04546 **Authors:** Harris Chan, Yuhuai Wu, Jamie Kiros, Sanja Fidler, Jimmy Ba **Published:** 2019-02-12T18:43:56Z **Abstract:** Sparse reward is one of the most challenging problems in reinforcement learning (RL). Hindsight Experience Replay (HER) attempts to address this issue by converting a failed experience to a successful one by relabeling the goals. Despite its effectiveness, HER has limited applicability because it lacks a compact and universal goal representation. ...
- 3 stars
- 0 votes
- 0 copies
- 4 views
- Added September 11, 2026
Security analysis
100/100npx -y skills add hiyenwong/ai_collection --skill actrce-augmenting-experience-via-teachers-advice-for-multigoal-reinforcement-learning --agent claude-codeAre you the author of Actrce Augmenting Experience Via Teachers Advice For Multigoal Reinforcement Learning?
Add the live security badge to your README. It updates with every re-scan.
[](https://www.skillsdirectory.com/skills/hiyenwong-actrce-augmenting-experience-via-teachers-advice-f)# ACTRCE: Augmenting Experience via Teacher's Advice For Multi-Goal Reinforcement Learning
**arXiv ID:** 1902.04546
**Authors:** Harris Chan, Yuhuai Wu, Jamie Kiros, Sanja Fidler, Jimmy Ba
**Published:** 2019-02-12T18:43:56Z
**Abstract:**
Sparse reward is one of the most challenging problems in reinforcement learning (RL). Hindsight Experience Replay (HER) attempts to address this issue by converting a failed experience to a successful one by relabeling the goals. Despite its effectiveness, HER has limited applicability because it lacks a compact and universal goal representation. We present Augmenting experienCe via TeacheR's adviCE (ACTRCE), an efficient reinforcement learning technique that extends the HER framework using natural language as the goal representation. We first analyze the differences among goal representation, and show that ACTRCE can efficiently solve difficult reinforcement learning problems in challenging 3D navigation tasks, whereas HER with non-language goal representation failed to learn. We also show that with language goal representations, the agent can generalize to unseen instructions, and even generalize to instructions with unseen lexicons. We further demonstrate it is crucial to use hindsight advice to solve challenging tasks, and even small amount of advice is sufficient for the agent to achieve good performance.
## Skill Description
This skill is generated from the arXiv paper: ACTRCE: Augmenting Experience via Teacher's Advice For Multi-Goal Reinforcement Learning (1902.04546).
## How to Use
[To be filled in by the user or by future automation]
## References
- [arXiv:1902.04546](http://arxiv.org/abs/1902.04546v1)
Attribution
Related skills
View all in tools →Comments
Loading comments…
Newsletter
Get the weekly list of safe new skills, and the ones we pulled.