Related papers: Does DQN really learn? Exploring adversarial train…
In this work, an advanced deep reinforcement learning architecture is used to train neural network agents playing atari games. Given only the raw game pixels, action space, and reward information, the system can train agents to play any…
This study conducts a comparative analysis of three advanced Deep Reinforcement Learning models: Deep Q-Networks (DQN), Proximal Policy Optimization (PPO), and Advantage Actor-Critic (A2C), within the BreakOut Atari game environment. Our…
Reinforcement learning policies based on deep neural networks are vulnerable to imperceptible adversarial perturbations to their inputs, in much the same way as neural network image classifiers. Recent work has proposed several methods to…
Recent work in reinforcement learning demonstrated that learning solely through self-play is not only possible, but could also result in novel strategies that humans never would have thought of. However, optimization methods cast as a game…
Modeling personality is a challenging problem with applications spanning computer games, virtual assistants, online shopping and education. Many techniques have been tried, ranging from neural networks to computational cognitive…
Advances in deep reinforcement learning have allowed autonomous agents to perform well on Atari games, often outperforming humans, using only raw pixels to make their decisions. However, most of these games take place in 2D environments…
Recent developments have established the vulnerability of deep Reinforcement Learning (RL) to policy manipulation attacks via adversarial perturbations. In this paper, we investigate the robustness and resilience of deep RL to training-time…
We train an agent to compete in the game of Gardner minichess, a downsized variation of chess played on a 5x5 board. We motivated and applied a SOTA actor-critic method Proximal Policy Optimization with Generalized Advantage Estimation. Our…
Multiagent systems appear in most social, economical, and political situations. In the present work we extend the Deep Q-Learning Network architecture proposed by Google DeepMind to multiagent environments and investigate how two agents…
Deep reinforcement learning algorithms have shown an impressive ability to learn complex control policies in high-dimensional tasks. However, despite the ever-increasing performance on popular benchmarks, policies learned by deep…
Opponent modeling is necessary in multi-agent settings where secondary agents with competing goals also adapt their strategies, yet it remains challenging because strategies interact with each other and change. Most previous work focuses on…
We introduce the first deep reinforcement learning agent that learns to beat Atari games with the aid of natural language instructions. The agent uses a multimodal embedding between environment observations and natural language to…
This paper investigates the effectiveness of adversarial training in enhancing the robustness of Deep Q-Network (DQN) policies to state-space perturbations. We first present a formal analysis of adversarial training in DQN agents and its…
This paper proposes new, end-to-end deep reinforcement learning algorithms for learning two-player zero-sum Markov games. Different from prior efforts on training agents to beat a fixed set of opponents, our objective is to find the Nash…
We present the first reinforcement-learning model to self-improve its reward-modulated training implemented through a continuously improving "intuition" neural network. An agent was trained how to play the arcade video game Pong with two…
In deep reinforcement learning (RL), adversarial attacks can trick an agent into unwanted states and disrupt training. We propose a system called Robust Student-DQN (RS-DQN), which permits online robustness training alongside Q networks,…
This paper presents an algorithmic framework for learning robust policies in asymmetric imperfect-information games, where the joint reward could depend on the uncertain opponent type (a private information known only to the opponent itself…
We propose a new method to study the internal memory used by reinforcement learning policies. We estimate the amount of relevant past information by estimating mutual information between behavior histories and the current action of an…
Reinforcement learning has exceeded human-level performance in game playing AI with deep learning methods according to the experiments from DeepMind on Go and Atari games. Deep learning solves high dimension input problems which stop the…
In the past few years, deep reinforcement learning has been proven to solve problems which have complex states like video games or board games. The next step of intelligent agents would be able to generalize between tasks, and using prior…