Picture for Thommen Karimpanal George

Thommen Karimpanal George

EMOTE: An Explainable architecture for Modelling the Other Through Empathy

Add code
Jun 01, 2023
Viaarxiv icon

Memory-Constrained Policy Optimization

Add code
Apr 20, 2022
Figure 1 for Memory-Constrained Policy Optimization
Figure 2 for Memory-Constrained Policy Optimization
Figure 3 for Memory-Constrained Policy Optimization
Figure 4 for Memory-Constrained Policy Optimization
Viaarxiv icon

Model-Based Episodic Memory Induces Dynamic Hybrid Controls

Add code
Nov 06, 2021
Figure 1 for Model-Based Episodic Memory Induces Dynamic Hybrid Controls
Figure 2 for Model-Based Episodic Memory Induces Dynamic Hybrid Controls
Figure 3 for Model-Based Episodic Memory Induces Dynamic Hybrid Controls
Figure 4 for Model-Based Episodic Memory Induces Dynamic Hybrid Controls
Viaarxiv icon

Plug and Play, Model-Based Reinforcement Learning

Add code
Aug 20, 2021
Figure 1 for Plug and Play, Model-Based Reinforcement Learning
Figure 2 for Plug and Play, Model-Based Reinforcement Learning
Figure 3 for Plug and Play, Model-Based Reinforcement Learning
Figure 4 for Plug and Play, Model-Based Reinforcement Learning
Viaarxiv icon

A New Representation of Successor Features for Transfer across Dissimilar Environments

Add code
Jul 18, 2021
Figure 1 for A New Representation of Successor Features for Transfer across Dissimilar Environments
Figure 2 for A New Representation of Successor Features for Transfer across Dissimilar Environments
Figure 3 for A New Representation of Successor Features for Transfer across Dissimilar Environments
Figure 4 for A New Representation of Successor Features for Transfer across Dissimilar Environments
Viaarxiv icon