Skip to search formSkip to main contentSkip to account menu

Rainbow: Combining Improvements in Deep Reinforcement Learning

This paper examines six extensions to the DQN algorithm and empirically studies their combination, showing that the combination provides state-of-the-art performance on the Atari 2600 benchmark, both in terms of data efficiency and final performance.
View PDF on arXiv (opens in a new tab)

Horde: a scalable real-time architecture for learning knowledge from unsupervised sensorimotor interaction

Results using Horde on a multi-sensored mobile robot to successfully learn goal-oriented behaviors and long-term predictions from off-policy experience are presented.
View Paper (opens in a new tab)

Vector-based navigation using grid-like representations in artificial agents

These findings show that emergent grid-like representations furnish agents with a Euclidean spatial metric and associated vector operations, providing a foundation for proficient navigation, and support neuroscientific theories that see grid cells as critical for vector-based navigation.
View on Springer (opens in a new tab)

Deep Reinforcement Learning and the Deadly Triad

This work investigates 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.
View PDF on arXiv (opens in a new tab)

Local metrical and global topological maps in the hybrid spatial semantic hierarchy

This work describes how a local perceptual map is analyzed to identify a local topology description and is abstracted to a topological place and creates a set of topological map hypotheses that are consistent with travel experience.
View on IEEE (opens in a new tab)

Factoring the Mapping Problem: Mobile Robot Map-building in the Hybrid Spatial Semantic Hierarchy

This paper describes how to abstract a symbolic description of the robot’s immediate surround from local metrical models, how to combine these local symbolic models in order to build global symbolic models, and how to create a globally consistent metrical map from a topological skeleton by connecting local frames of reference.
View on SAGE (opens in a new tab)

Multi-timescale nexting in a reinforcement learning robot

This paper presents results with a robot that learns to next in real time, making thousands of predictions about sensory input signals at timescales from 0.1 to 8 seconds, and extends nexting beyond simple timescale by letting the discount rate be a function of the state.
View on SAGE (opens in a new tab)

Improving the recognition of interleaved activities

The Interleaved Hidden Markov Models for recognizing multitasked activities are introduced and an approximation that is both effective and efficient is described that significantly reduces the error rate.
View on ACM (opens in a new tab)

Bootstrap learning for object discovery

This work shows how a robot can autonomously learn an ontology of objects to explain aspects of its sensor input from an unknown dynamic world, and makes it possible for the robot to describe a cluttered dynamic world with symbolic object descriptions along with a static environment model, both models grounded in sensory experience, and learned without external supervision.
View on IEEE (opens in a new tab)

The initial development of object knowledge by a learning robot

View on PubMed (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)