Search Results for author: Martin Klissarov

Found 8 papers, 7 papers with code

Code as Reward: Empowering Reinforcement Learning with VLMs

no code implementations7 Feb 2024 David Venuto, Sami Nur Islam, Martin Klissarov, Doina Precup, Sherry Yang, Ankit Anand

Pre-trained Vision-Language Models (VLMs) are able to understand visual concepts, describe and decompose complex tasks into sub-tasks, and provide feedback on task completion.

Code Generation reinforcement-learning +1

Deep Laplacian-based Options for Temporally-Extended Exploration

1 code implementation26 Jan 2023 Martin Klissarov, Marlos C. Machado

In this paper we address these limitations and show how recent results for directly approximating the eigenfunctions of the Laplacian can be leveraged to truly scale up options-based exploration.

Reinforcement Learning (RL)

Flexible Option Learning

1 code implementation NeurIPS 2021 Martin Klissarov, Doina Precup

Temporal abstraction in reinforcement learning (RL), offers the promise of improving generalization and knowledge transfer in complex environments, by propagating information more efficiently over time.

Hierarchical Reinforcement Learning reinforcement-learning +2

Reward Propagation Using Graph Convolutional Networks

1 code implementation NeurIPS 2020 Martin Klissarov, Doina Precup

Potential-based reward shaping provides an approach for designing good reward functions, with the purpose of speeding up learning.

Graph Representation Learning

Options of Interest: Temporal Abstraction with Interest Functions

3 code implementations1 Jan 2020 Khimya Khetarpal, Martin Klissarov, Maxime Chevalier-Boisvert, Pierre-Luc Bacon, Doina Precup

Temporal abstraction refers to the ability of an agent to use behaviours of controllers which act for a limited, variable amount of time.

Learnings Options End-to-End for Continuous Action Tasks

3 code implementations30 Nov 2017 Martin Klissarov, Pierre-Luc Bacon, Jean Harb, Doina Precup

We present new results on learning temporally extended actions for continuoustasks, using the options framework (Suttonet al.[1999b], Precup [2000]).

When Waiting is not an Option : Learning Options with a Deliberation Cost

1 code implementation14 Sep 2017 Jean Harb, Pierre-Luc Bacon, Martin Klissarov, Doina Precup

Recent work has shown that temporally extended actions (options) can be learned fully end-to-end as opposed to being specified in advance.

Atari Games

Cannot find the paper you are looking for? You can Submit a new open access paper.