Safer Deep RL with Shallow MCTS: A Case Study in Pommerman

2019-04-10 · Bilal Kartal, Pablo Hernandez-Leal, Chao GAO, Matthew E. Taylor

Safe reinforcement learning has many variants and it is still an open research problem. Here, we focus on how to use action guidance by means of a non-expert demonstrator to avoid catastrophic events in a domain with sparse, delayed, and deceptive rewards: the recently-proposed multi-agent benchmark of Pommerman. This domain is very challenging for reinforcement learning (RL) --- past work has shown that model-free RL algorithms fail to achieve significant learning. In this paper, we shed light into the reasons behind this failure by exemplifying and analyzing the high rate of catastrophic events (i.e., suicides) that happen under random exploration in this domain. While model-free random exploration is typically futile, we propose a new framework where even a non-expert simulated demonstrator, e.g., planning algorithms such as Monte Carlo tree search with small number of rollouts, can be integrated to asynchronous distributed deep reinforcement learning methods. Compared to vanilla deep RL algorithms, our proposed methods both learn faster and converge to better policies on a two-player mini version of the Pommerman game.

📄 PDF Abstract BibTeX arXiv:1904.05759

Code (0)

등록된 구현이 없습니다.

Tasks

Deep Reinforcement Learningreinforcement-learning Reinforcement Learning Reinforcement Learning (RL)Safe Reinforcement Learning

A Fast Evolutionary adaptation for MCTS in Pommerman

2021-11-26 · Harsh Panwar, Saswata Chatterjee, Wil Dube

Artificial Intelligence, when amalgamated with games makes the ideal structure for research and advancing the field. Multi-agent games have multiple controls for each agent which generates huge amounts of data while incr…

On Hard Exploration for Reinforcement Learning: a Case Study in Pommerman

2019-07-26 · Chao Gao, Bilal Kartal, Pablo Hernandez-Leal, Matthew E. Taylor

How to best explore in domains with sparse, delayed, and deceptive rewards is an important open problem for reinforcement learning (RL). This paper considers one such domain, the recently-proposed multi-agent benchmark o…

reinforcement-learning Reinforcement Learning Reinforcement Learning (RL)

Action Guidance with MCTS for Deep Reinforcement Learning

2019-07-25 · Bilal Kartal, Pablo Hernandez-Leal, Matthew E. Taylor

Deep reinforcement learning has achieved great successes in recent years, however, one main challenge is the sample inefficiency. In this paper, we focus on how to use action guidance by means of a non-expert demonstrato…

Deep Reinforcement Learning reinforcement-learning Reinforcement Learning Reinforcement Learning (RL)

Deep Multi-Agent Reinforcement Learning with Relevance Graphs

2018-11-30 · Aleksandra Malysheva, Tegg Taekyong Sung, Chae-Bong Sohn, Daniel Kudenko 외

Over recent years, deep reinforcement learning has shown strong successes in complex single-agent tasks, and more recently this approach has also been applied to multi-agent domains. In this paper, we propose a novel app…

Deep Reinforcement Learning Multi-agent Reinforcement Learning reinforcement-learning Reinforcement Learning+1

Continual Match Based Training in Pommerman: Technical Report

2018-12-18 · Peng Peng, Liang Pang, Yufeng Yuan, Chao GAO

Continual learning is the ability of agents to improve their capacities throughout multiple tasks continually. While recent works in the literature of continual learning mostly focused on developing either particular los…

Continual Learning