Neural programmer-interpreters
S Reed, N De Freitas - arxiv preprint arxiv:1511.06279, 2015 - arxiv.org
We propose the neural programmer-interpreter (NPI): a recurrent and compositional neural
network that learns to represent and execute programs. NPI has three learnable …
network that learns to represent and execute programs. NPI has three learnable …
Pac-Man Conquers Academia: Two Decades of Research Using a Classic Arcade Game
P Rohlfshagen, J Liu, D Perez-Liebana… - IEEE Transactions on …, 2017 - ieeexplore.ieee.org
Pac-Man and its equally popular successor Ms. Pac-Man are often attributed to being the
frontrunners of the golden age of arcade video games. Their impact goes well beyond the …
frontrunners of the golden age of arcade video games. Their impact goes well beyond the …
[PDF][PDF] Reinforcement learning from simultaneous human and MDP reward.
As computational agents are increasingly used beyond research labs, their success will
depend on their ability to learn new skills and adapt to their dynamic, complex environments …
depend on their ability to learn new skills and adapt to their dynamic, complex environments …
Tsc-dl: Unsupervised trajectory segmentation of multi-modal surgical demonstrations with deep learning
The growth of robot-assisted minimally invasive surgery has led to sizable datasets of fixed-
camera video and kinematic recordings of surgical subtasks. Segmentation of these …
camera video and kinematic recordings of surgical subtasks. Segmentation of these …
A conceptual framework for externally-influenced agents: An assisted reinforcement learning review
A long-term goal of reinforcement learning agents is to be able to perform tasks in complex
real-world scenarios. The use of external information is one way of scaling agents to more …
real-world scenarios. The use of external information is one way of scaling agents to more …
Learning from human-generated reward
WB Knox - 2012 - repositories.lib.utexas.edu
Robots and other computational agents are increasingly becoming part of our daily lives.
They will need to be able to learn to perform new tasks, adapt to novel situations, and …
They will need to be able to learn to perform new tasks, adapt to novel situations, and …
Discovering multimodal behavior in Ms. Pac-Man through evolution of modular neural networks
J Schrum, R Miikkulainen - IEEE transactions on computational …, 2015 - ieeexplore.ieee.org
Ms. Pac-Man is a challenging video game in which multiple modes of behavior are required:
Ms. Pac-Man must escape ghosts when they are threats and catch them when they are …
Ms. Pac-Man must escape ghosts when they are threats and catch them when they are …
Learning via human feedback in continuous state and action spaces
This paper considers the problem of extending Training an Agent Manually via Evaluative
Reinforcement (TAMER) in continuous state and action spaces. Investigative research using …
Reinforcement (TAMER) in continuous state and action spaces. Investigative research using …
Performance evaluation of machine learning algorithms in Apache spark for intrusion detection
As the Internet continues to get stronger, so does the potential risk of malicious users trying
to harm others. An intrusion detection system (IDS) can be used to alert the appropriate …
to harm others. An intrusion detection system (IDS) can be used to alert the appropriate …
[PDF][PDF] Efficient exploration in monte carlo tree search using human action abstractions
K Subramanian, J Scholz, CL Isbell… - Proceedings of the …, 2016 - kausubbu.github.io
Abstract Monte Carlo Tree Search (MCTS) is a family of methods for planning in large
domains. It focuses on finding a good action for a particular state, making its complexity …
domains. It focuses on finding a good action for a particular state, making its complexity …