Picture for George Konidaris

George Konidaris

MIT

Hierarchical Empowerment: Towards Tractable Empowerment-Based Skill-Learning

Add code
Jul 06, 2023
Figure 1 for Hierarchical Empowerment: Towards Tractable Empowerment-Based Skill-Learning
Figure 2 for Hierarchical Empowerment: Towards Tractable Empowerment-Based Skill-Learning
Figure 3 for Hierarchical Empowerment: Towards Tractable Empowerment-Based Skill-Learning
Figure 4 for Hierarchical Empowerment: Towards Tractable Empowerment-Based Skill-Learning
Viaarxiv icon

Flipping Coins to Estimate Pseudocounts for Exploration in Reinforcement Learning

Add code
Jun 05, 2023
Viaarxiv icon

Exploiting Contextual Structure to Generate Useful Auxiliary Tasks

Add code
Mar 09, 2023
Viaarxiv icon

A Domain-Agnostic Approach for Characterization of Lifelong Learning Systems

Add code
Jan 18, 2023
Figure 1 for A Domain-Agnostic Approach for Characterization of Lifelong Learning Systems
Figure 2 for A Domain-Agnostic Approach for Characterization of Lifelong Learning Systems
Figure 3 for A Domain-Agnostic Approach for Characterization of Lifelong Learning Systems
Figure 4 for A Domain-Agnostic Approach for Characterization of Lifelong Learning Systems
Viaarxiv icon

On the Geometry of Reinforcement Learning in Continuous State and Action Spaces

Add code
Dec 29, 2022
Figure 1 for On the Geometry of Reinforcement Learning in Continuous State and Action Spaces
Figure 2 for On the Geometry of Reinforcement Learning in Continuous State and Action Spaces
Figure 3 for On the Geometry of Reinforcement Learning in Continuous State and Action Spaces
Figure 4 for On the Geometry of Reinforcement Learning in Continuous State and Action Spaces
Viaarxiv icon

Effects of Data Geometry in Early Deep Learning

Add code
Dec 29, 2022
Figure 1 for Effects of Data Geometry in Early Deep Learning
Figure 2 for Effects of Data Geometry in Early Deep Learning
Figure 3 for Effects of Data Geometry in Early Deep Learning
Figure 4 for Effects of Data Geometry in Early Deep Learning
Viaarxiv icon

Evaluation Beyond Task Performance: Analyzing Concepts in AlphaZero in Hex

Add code
Nov 26, 2022
Viaarxiv icon

Constrained Dynamic Movement Primitives for Safe Learning of Motor Skills

Add code
Sep 28, 2022
Figure 1 for Constrained Dynamic Movement Primitives for Safe Learning of Motor Skills
Figure 2 for Constrained Dynamic Movement Primitives for Safe Learning of Motor Skills
Figure 3 for Constrained Dynamic Movement Primitives for Safe Learning of Motor Skills
Figure 4 for Constrained Dynamic Movement Primitives for Safe Learning of Motor Skills
Viaarxiv icon

RLang: A Declarative Language for Expression Prior Knowledge for Reinforcement Learning

Add code
Aug 16, 2022
Figure 1 for RLang: A Declarative Language for Expression Prior Knowledge for Reinforcement Learning
Figure 2 for RLang: A Declarative Language for Expression Prior Knowledge for Reinforcement Learning
Figure 3 for RLang: A Declarative Language for Expression Prior Knowledge for Reinforcement Learning
Figure 4 for RLang: A Declarative Language for Expression Prior Knowledge for Reinforcement Learning
Viaarxiv icon

Skill Transfer for Temporally-Extended Task Specifications

Add code
Jun 10, 2022
Figure 1 for Skill Transfer for Temporally-Extended Task Specifications
Figure 2 for Skill Transfer for Temporally-Extended Task Specifications
Figure 3 for Skill Transfer for Temporally-Extended Task Specifications
Figure 4 for Skill Transfer for Temporally-Extended Task Specifications
Viaarxiv icon