Using Monte Carlo Tree Search As A Demonstrator Within Asynchronous Deep Rl
ASecurity**arXiv ID:** 1812.00045 **Authors:** Bilal Kartal, Pablo Hernandez-Leal, Matthew E. Taylor **Published:** 2018-11-30T20:37:17Z **Abstract:** Deep reinforcement learning (DRL) has achieved great successes in recent years with the help of novel methods and higher compute power. However, there are still several challenges to be addressed such as convergence to locally optimal policies and long training times. In this paper, firstly, we augment Asynchronous Advantage Actor-Critic (A3C) method wi...
- 3 stars
- 0 votes
- 0 copies
- 4 views
- Added September 11, 2026
Works with
Security analysis
100/100npx -y skills add hiyenwong/ai_collection --skill using-monte-carlo-tree-search-as-a-demonstrator-within-asynchronous-deep-rl --agent claude-codeAre you the author of Using Monte Carlo Tree Search As A Demonstrator Within Asynchronous Deep Rl?
Add the live security badge to your README. It updates with every re-scan.
[](https://www.skillsdirectory.com/skills/hiyenwong-using-monte-carlo-tree-search-as-a-demonstrator-wi)# Using Monte Carlo Tree Search as a Demonstrator within Asynchronous Deep RL
**arXiv ID:** 1812.00045
**Authors:** Bilal Kartal, Pablo Hernandez-Leal, Matthew E. Taylor
**Published:** 2018-11-30T20:37:17Z
**Abstract:**
Deep reinforcement learning (DRL) has achieved great successes in recent years with the help of novel methods and higher compute power. However, there are still several challenges to be addressed such as convergence to locally optimal policies and long training times. In this paper, firstly, we augment Asynchronous Advantage Actor-Critic (A3C) method with a novel self-supervised auxiliary task, i.e. \emph{Terminal Prediction}, measuring temporal closeness to terminal states, namely A3C-TP. Secondly, we propose a new framework where planning algorithms such as Monte Carlo tree search or other sources of (simulated) demonstrators can be integrated to asynchronous distributed DRL methods. Compared to vanilla A3C, our proposed methods both learn faster and converge to better policies on a two-player mini version of the Pommerman game.
## Skill Description
This skill is generated from the arXiv paper: Using Monte Carlo Tree Search as a Demonstrator within Asynchronous Deep RL (1812.00045).
## How to Use
[To be filled in by the user or by future automation]
## References
- [arXiv:1812.00045](http://arxiv.org/abs/1812.00045v1)
Attribution
Related skills
View all in tools →Comments
Loading comments…
Newsletter
Get the weekly list of safe new skills, and the ones we pulled.