Search Results for author:
Found 15 papers, 2 papers with code
The Ungrounded Alignment Problem
This paper examines a simplified version of the general problem, where an unsupervised learner is presented with a sequence of images for the characters in a text corpus, and this learner is later evaluated on its ability to recognize specific (possibly rare) sequential patterns.
Towards model-free RL algorithms that scale well with unstructured data
RL practitioners lack a systematic way to study how well a single RL algorithm performs when instantiated across a range of problem scales, and they lack function approximation techniques that scale well with unstructured observations.
Loss of Plasticity in Continual Deep Reinforcement Learning
The ability to learn continually is essential in a complex and changing world.
The Frost Hollow Experiments: Pavlovian Signalling as a Path to Coordination and Communication Between Agents
Our results showcase the speed of learning for Pavlovian signalling, the impact that different temporal representations do (and do not) have on agent-agent coordination, and how temporal aliasing impacts agent-agent and human-agent interactions differently.
Pavlovian Signalling with General Value Functions in Agent-Agent Temporal Decision Making
We further show how to computationally build this adaptive signalling process out of a fixed signalling process, characterized by fast continual prediction learning and minimal constraints on the nature of the agent receiving signals.
Assessing Human Interaction in Virtual Reality With Continually Learning Prediction Agents Based on Reinforcement Learning Algorithms: A Pilot Study
Additionally, we compare two different agent architectures to assess how representational choices in agent design affect the human-agent interaction.
Adapting the Function Approximation Architecture in Online Reinforcement Learning
However, prevailing optimization techniques are not designed for strictly-incremental online updates.
On Inductive Biases in Deep Reinforcement Learning
These inductive biases can take many forms, including domain knowledge and pretuned hyper-parameters.
Ray Interference: a Source of Plateaus in Deep Reinforcement Learning
Rather than proposing a new method, this paper investigates an issue present in existing learning algorithms.
Deep Reinforcement Learning and the Deadly Triad
In this work, we investigate the impact of the deadly triad in practice, in the context of a family of popular deep reinforcement learning models - deep Q-networks trained with experience replay - analysing how the components of this system play a role in the emergence of the deadly triad, and in the agent's performance
The Barbados 2018 List of Open Issues in Continual Learning
We want to make progress toward artificial general intelligence, namely general-purpose agents that autonomously learn how to competently act in complex environments.
Natural Value Approximators: Learning when to Trust Past Estimates
Neural networks have a smooth initial inductive bias, such that small changes in input do not lead to large changes in output.
Rainbow: Combining Improvements in Deep Reinforcement Learning
The deep reinforcement learning community has made several independent improvements to the DQN algorithm.
Universal Option Models
We prove that the UOM of an option can construct a traditional option model given a reward function, and the option-conditional return is computed directly by a single dot-product of the UOM with the reward function.
Multi-timescale Nexting in a Reinforcement Learning Robot
The term "nexting" has been used by psychologists to refer to the propensity of people and many other animals to continually predict what will happen next in an immediate, local, and personal sense.
