Picture for Kai Arulkumaran

Kai Arulkumaran

Scaling Law in Neural Data: Non-Invasive Speech Decoding with 175 Hours of EEG Data

Add code
Jul 10, 2024
Viaarxiv icon

Preference-Learning Emitters for Mixed-Initiative Quality-Diversity Algorithms

Add code
Oct 25, 2022
Figure 1 for Preference-Learning Emitters for Mixed-Initiative Quality-Diversity Algorithms
Figure 2 for Preference-Learning Emitters for Mixed-Initiative Quality-Diversity Algorithms
Figure 3 for Preference-Learning Emitters for Mixed-Initiative Quality-Diversity Algorithms
Figure 4 for Preference-Learning Emitters for Mixed-Initiative Quality-Diversity Algorithms
Viaarxiv icon

Surrogate Infeasible Fitness Acquirement FI-2Pop for Procedural Content Generation

Add code
May 12, 2022
Figure 1 for Surrogate Infeasible Fitness Acquirement FI-2Pop for Procedural Content Generation
Figure 2 for Surrogate Infeasible Fitness Acquirement FI-2Pop for Procedural Content Generation
Figure 3 for Surrogate Infeasible Fitness Acquirement FI-2Pop for Procedural Content Generation
Figure 4 for Surrogate Infeasible Fitness Acquirement FI-2Pop for Procedural Content Generation
Viaarxiv icon

On the link between conscious function and general intelligence in humans and machines

Add code
Mar 24, 2022
Figure 1 for On the link between conscious function and general intelligence in humans and machines
Figure 2 for On the link between conscious function and general intelligence in humans and machines
Figure 3 for On the link between conscious function and general intelligence in humans and machines
Viaarxiv icon

All You Need Is Supervised Learning: From Imitation Learning to Meta-RL With Upside Down RL

Add code
Feb 24, 2022
Figure 1 for All You Need Is Supervised Learning: From Imitation Learning to Meta-RL With Upside Down RL
Viaarxiv icon

Learning Relative Return Policies With Upside-Down Reinforcement Learning

Add code
Feb 23, 2022
Figure 1 for Learning Relative Return Policies With Upside-Down Reinforcement Learning
Figure 2 for Learning Relative Return Policies With Upside-Down Reinforcement Learning
Viaarxiv icon

Diversity-based Trajectory and Goal Selection with Hindsight Experience Replay

Add code
Aug 17, 2021
Figure 1 for Diversity-based Trajectory and Goal Selection with Hindsight Experience Replay
Figure 2 for Diversity-based Trajectory and Goal Selection with Hindsight Experience Replay
Figure 3 for Diversity-based Trajectory and Goal Selection with Hindsight Experience Replay
Figure 4 for Diversity-based Trajectory and Goal Selection with Hindsight Experience Replay
Viaarxiv icon

A Pragmatic Look at Deep Imitation Learning

Add code
Aug 04, 2021
Figure 1 for A Pragmatic Look at Deep Imitation Learning
Figure 2 for A Pragmatic Look at Deep Imitation Learning
Figure 3 for A Pragmatic Look at Deep Imitation Learning
Viaarxiv icon

Privileged Information Dropout in Reinforcement Learning

Add code
May 19, 2020
Figure 1 for Privileged Information Dropout in Reinforcement Learning
Figure 2 for Privileged Information Dropout in Reinforcement Learning
Figure 3 for Privileged Information Dropout in Reinforcement Learning
Figure 4 for Privileged Information Dropout in Reinforcement Learning
Viaarxiv icon

Analysing Deep Reinforcement Learning Agents Trained with Domain Randomisation

Add code
Dec 18, 2019
Figure 1 for Analysing Deep Reinforcement Learning Agents Trained with Domain Randomisation
Figure 2 for Analysing Deep Reinforcement Learning Agents Trained with Domain Randomisation
Figure 3 for Analysing Deep Reinforcement Learning Agents Trained with Domain Randomisation
Figure 4 for Analysing Deep Reinforcement Learning Agents Trained with Domain Randomisation
Viaarxiv icon