Skip to search formSkip to main contentSkip to account menu

Deep Recurrent Q-Learning for Partially Observable MDPs

TLDR
The effects of adding recurrency to a Deep Q-Network is investigated by replacing the first post-convolutional fully-connected layer with a recurrent LSTM, which successfully integrates information through time and replicates DQN's performance on standard Atari games and partially observed equivalents featuring flickering game screens.
View PDF on arXiv (opens in a new tab)

Beyond short snippets: Deep networks for video classification

TLDR
This work proposes and evaluates several deep neural network architectures to combine image information across a video over longer time periods than previously attempted, and proposes two methods capable of handling full length videos.
View on IEEE (opens in a new tab)

Revisiting the Arcade Learning Environment: Evaluation Protocols and Open Problems for General Agents

TLDR
This paper takes a big picture look at how the ALE is being used by the research community and focuses on how diverse the evaluation methodologies in the ALE have become and highlights some key concerns when evaluating agents in this platform.
View PDF on arXiv (opens in a new tab)

TextWorld: A Learning Environment for Text-based Games

TLDR
TextWorld is a Python library that handles interactive play-through of text games, as well as backend functions like state tracking and reward assignment, and comes with a curated list of games whose features and challenges the authors have analyzed.
View PDF on arXiv (opens in a new tab)

Deep Reinforcement Learning in Parameterized Action Space

TLDR
This paper represents a successful extension of deep reinforcement learning to the class of parameterized action space MDPs within the domain of simulated RoboCup soccer, which features a small set of discrete action types each of which is parameterized with continuous variables.
View PDF on arXiv (opens in a new tab)

Leveraging Grammar and Reinforcement Learning for Neural Program Synthesis

TLDR
Reinforcement learning is performed on top of a supervised model with an objective that explicitly maximizes the likelihood of generating semantically correct programs, which leads to improved accuracy of the models, especially in cases where the training data is limited.
View PDF on arXiv (opens in a new tab)

Interactive Fiction Games: A Colossal Adventure

TLDR
This work argues that IF games are an excellent testbed for studying language-based autonomous agents and introduces Jericho, a learning environment for man-made IF games and conducts a comprehensive study of text-agents across a rich set of games, highlighting directions in which agents can improve.
View PDF on arXiv (opens in a new tab)

Counting to Explore and Generalize in Text-based Games

TLDR
A recurrent RL agent with an episodic exploration mechanism that helps discovering good policies in text-based game environments and observes that the agent learns policies that generalize to unseen games of greater difficulty.
View PDF on arXiv (opens in a new tab)

A Neuroevolution Approach to General Atari Game Playing

TLDR
Results suggest that neuroevolution is a promising approach to general video game playing (GVGP) and achieved state-of-the-art results, even surpassing human high scores on three games.
View on IEEE (opens in a new tab)

Graph Constrained Reinforcement Learning for Natural Language Action Spaces

TLDR
KG-A2C, an agent that builds a dynamic knowledge graph while exploring and generates actions using a template-based action space is presented, arguing that the dual uses of the knowledge graph to reason about game state and to constrain natural language generation are the keys to scalable exploration of combinatorially large natural language actions.
View PDF on arXiv (opens in a new tab)
By clicking accept or continuing to use the site, you agree to the terms outlined in our Privacy Policy (opens in a new tab), Terms of Service (opens in a new tab), and Dataset License (opens in a new tab)