Deep reinforcement learning has learned to play many games well, but failed on others. To better characterize the modes and reasons of failure of deep reinforcement learners, we test the widely used Asynchronous Actor-Critic (A2C) algorithm on four deceptive games, which are specially designed to provide challenges to game-playing agents. These games are implemented in the General Video Game AI framework, which allows us to compare the behavior of reinforcement learning-based agents with planning agents based on tree search. We find that several of these games reliably deceive deep reinforcement learners, and that the resulting behavior highlights the shortcomings of the learning algorithm. The particular ways in which agents fail differ from how planning-based agents fail, further illuminating the character of these algorithms. We propose an initial typology of deceptions which could help us better understand pitfalls and failure modes of (deep) reinforcement learning.
University of Strathclyde（斯特拉斯克莱德大学）；Australian National University（澳大利亚国立大学）；New York University（纽约大学）
Deceptive games are games where the reward structure or other aspects of the game are designed to lead the agent away from a globally optimal policy. While many games are already deceptive to some extent, we designed a series of games in the Video Game Description Language (VGDL) implementing specific types of deception, classified by the cognitive biases they exploit. VGDL games can be run in the General Video Game Artificial Intelligence (GVGAI) Framework, making it possible to test a variety of existing AI agents that have been submitted to the GVGAI Competition on these deceptive games. Ou…
The Australian National University（澳大利亚国立大学）；Maastricht University（马斯特里赫特大学）
The Angry Birds AI competition has been held over many years to encourage the development of AI agents that can play Angry Birds game levels better than human players. Many different agents with various approaches have been employed over the competition's lifetime to solve this task. Even though the performance of these agents has increased significantly over the past few years, they still show major drawbacks in playing deceptive levels. This is because most of the current agents try to identify the best next shot rather than planning an effective sequence of shots. In order to encourage adva…
While neural networks demonstrate a remarkable ability to model linguistic content, capturing contextual information related to a speaker's conversational role is an open area of research. In this work, we analyze the effect of speaker role on language use through the game of Mafia, in which participants are assigned either an honest or a deceptive role. In addition to building a framework to collect a dataset of Mafia game records, we demonstrate that there are differences in the language produced by players with different roles. We confirm that classification models are able to rank deceptiv…
Maynooth University（梅努斯大学）；National Autonomous University of Mexico（墨西哥国立自治大学）
Monte Carlo Tree Search (MCTS) is a relatively new sampling method with multiple variants in the literature. They can be applied to a wide variety of challenging domains including board games, video games, and energy-based problems to mention a few. In this work, we explore the use of the vanilla MCTS and the MCTS with Rapid Action Value Estimation (MCTS-RAVE) in the game of Carcassonne, a stochastic game with a deceptive scoring system where limited research has been conducted. We compare the strengths of the MCTS-based methods with the Star2.5 algorithm, previously reported to yield competit…
Georgia Institute of Technology（佐治亚理工学院）；Microsoft Research（微软研究院）
Text-based games are long puzzles or quests, characterized by a sequence of sparse and potentially deceptive rewards. They provide an ideal platform to develop agents that perceive and act upon the world using a combinatorially sized natural language state-action space. Standard Reinforcement Learning agents are poorly equipped to effectively explore such spaces and often struggle to overcome bottlenecks---states that agents are unable to pass through simply because they do not see the right action sequence enough times to be sufficiently reinforced. We introduce Q*BERT, an agent that learns t…
In this paper we present a Reinforcement Learning environment that leverages agent cooperation and communication, aimed at detection, learning and ultimately penalizing betrayal patterns that emerge in the behavior of self-interested agents. We provide a description of game rules, along with interesting cases of betrayal and trade-offs that arise. Preliminary experimental investigations illustrate a) betrayal emergence, b) deceptive agents outperforming honest baselines and b) betrayal detection based on classification of behavioral features, which surpasses probabilistic detection baselines. …
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 demonstrator to improve sample efficiency in a domain with sparse, delayed, and possibly deceptive rewards: the recently-proposed multi-agent benchmark of Pommerman. We propose a new framework where even a non-expert simulated demonstrator, e.g., planning algorithms such as Monte Carlo tree search with a small number rollouts, can be integrated within asynchronous distributed deep reinfor…
A grand challenge in reinforcement learning is intelligent exploration, especially when rewards are sparse or deceptive. Two Atari games serve as benchmarks for such hard-exploration domains: Montezuma's Revenge and Pitfall. On both games, current RL algorithms perform poorly, even those with intrinsic motivation, which is the dominant method to improve performance on hard-exploration domains. To address this shortfall, we introduce a new algorithm called Go-Explore. It exploits the following principles: (1) remember previously visited states, (2) first return to a promising state (without exp…
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 eve…
The promise of reinforcement learning is to solve complex sequential decision problems autonomously by specifying a high-level reward function only. However, reinforcement learning algorithms struggle when, as is often the case, simple and intuitive rewards provide sparse and deceptive feedback. Avoiding these pitfalls requires thoroughly exploring the environment, but creating algorithms that can do so remains one of the central challenges of the field. We hypothesise that the main impediment to effective exploration originates from algorithms forgetting how to reach previously visited states…
The University of Western Ontario（西安大略大学）；Vector Institute（向量研究所）
Reinforcement learning (RL) problems often feature deceptive local optima, and learning methods that optimize purely for reward signal often fail to learn strategies for overcoming them. Deep neuroevolution and novelty search have been proposed as effective alternatives to gradient-based methods for learning RL policies directly from pixels. In this paper, we introduce and evaluate the use of novelty search over agent action sequences by string edit metric distance as a means for promoting innovation. We also introduce a method for stagnation detection and population resampling inspired by rec…
