Search Results for author: David Meger

Found 49 papers, 25 papers with code

Constrained Robotic Navigation on Preferred Terrains Using LLMs and Speech Instruction: Exploiting the Power of Adverbs

no code implementations2 Apr 2024 Faraz Lotfi, Farnoosh Faraji, Nikhil Kakodkar, Travis Manderson, David Meger, Gregory Dudek

This paper explores leveraging large language models for map-free off-road navigation using generative AI, reducing the need for traditional data collection and annotation.

Language Modelling Large Language Model +1

Learning active tactile perception through belief-space control

no code implementations30 Nov 2023 Jean-François Tremblay, David Meger, Francois Hogan, Gregory Dudek

These robots will need to sense these properties through interaction prior to performing downstream tasks with the objects.


Generalizable Imitation Learning Through Pre-Trained Representations

no code implementations15 Nov 2023 Wei-Di Chang, Francois Hogan, David Meger, Gregory Dudek

In this paper we leverage self-supervised vision transformer models and their emergent semantic abilities to improve the generalization abilities of imitation learning policies.

Clustering Imitation Learning +1

Imitation Learning from Observation through Optimal Transport

no code implementations2 Oct 2023 Wei-Di Chang, Scott Fujimoto, David Meger, Gregory Dudek

Imitation Learning from Observation (ILfO) is a setting in which a learner tries to imitate the behavior of an expert, using only observational data and without the direct guidance of demonstrated actions.

Continuous Control Imitation Learning

Leveraging World Model Disentanglement in Value-Based Multi-Agent Reinforcement Learning

no code implementations8 Sep 2023 Zhizun Wang, David Meger

In this paper, we propose a novel model-based multi-agent reinforcement learning approach named Value Decomposition Framework with Disentangled World Model to address the challenge of achieving a common goal of multiple agents interacting in the same environment with reduced sample complexity.

Disentanglement Management +4

Efficient Epistemic Uncertainty Estimation in Regression Ensemble Models Using Pairwise-Distance Estimators

no code implementations25 Aug 2023 Lucas Berry, David Meger

This work introduces an efficient novel approach for epistemic uncertainty estimation for ensemble models for regression tasks using pairwise-distance estimators (PaiDEs).

Active Learning Decision Making +1

For SALE: State-Action Representation Learning for Deep Reinforcement Learning

2 code implementations NeurIPS 2023 Scott Fujimoto, Wei-Di Chang, Edward J. Smith, Shixiang Shane Gu, Doina Precup, David Meger

In the field of reinforcement learning (RL), representation learning is a proven tool for complex image-based tasks, but is often overlooked for environments with low-level states, such as physical control problems.

Continuous Control OpenAI Gym +3

Normalizing Flow Ensembles for Rich Aleatoric and Epistemic Uncertainty Modeling

1 code implementation2 Feb 2023 Lucas Berry, David Meger

In this work, we demonstrate how to reliably estimate epistemic uncertainty while maintaining the flexibility needed to capture complicated aleatoric distributions.

Active Learning

Hypernetworks for Zero-shot Transfer in Reinforcement Learning

no code implementations28 Nov 2022 Sahand Rezaei-Shoshtari, Charlotte Morissette, Francois Robert Hogan, Gregory Dudek, David Meger

In this paper, hypernetworks are trained to generate behaviors across a range of unseen task conditions, via a novel TD-based training objective and data from a set of near-optimal RL solutions for training tasks.

Continuous Control reinforcement-learning +2

NeurIPS 2022 Competition: Driving SMARTS

no code implementations14 Nov 2022 Amir Rasouli, Randy Goebel, Matthew E. Taylor, Iuliia Kotseruba, Soheil Alizadeh, Tianpei Yang, Montgomery Alban, Florian Shkurti, Yuzheng Zhuang, Adam Scibior, Kasra Rezaee, Animesh Garg, David Meger, Jun Luo, Liam Paull, Weinan Zhang, Xinyu Wang, Xi Chen

The proposed competition supports methodologically diverse solutions, such as reinforcement learning (RL) and offline learning methods, trained on a combination of naturalistic AD data and open-source simulation platform SMARTS.

Autonomous Driving Reinforcement Learning (RL)

Uncertainty-Driven Active Vision for Implicit Scene Reconstruction

1 code implementation3 Oct 2022 Edward J. Smith, Michal Drozdzal, Derek Nowrouzezahrai, David Meger, Adriana Romero-Soriano

We evaluate our proposed approach on the ABC dataset and the in the wild CO3D dataset, and show that: (1) we are able to obtain high quality state-of-the-art occupancy reconstructions; (2) our perspective conditioned uncertainty definition is effective to drive improvements in next best view selection and outperforms strong baseline approaches; and (3) we can further improve shape understanding by performing a gradient-based search on the view selection candidates.

Scene Understanding

Bayesian Q-learning With Imperfect Expert Demonstrations

no code implementations1 Oct 2022 Fengdi Che, Xiru Zhu, Doina Precup, David Meger, Gregory Dudek

Guided exploration with expert demonstrations improves data efficiency for reinforcement learning, but current algorithms often overuse expert information.

Atari Games Q-Learning +2

Continuous MDP Homomorphisms and Homomorphic Policy Gradient

1 code implementation15 Sep 2022 Sahand Rezaei-Shoshtari, Rosie Zhao, Prakash Panangaden, David Meger, Doina Precup

Abstraction has been widely studied as a way to improve the efficiency and generalization of reinforcement learning algorithms.

Continuous Control Policy Gradient Methods +2

Why Should I Trust You, Bellman? The Bellman Error is a Poor Replacement for Value Error

no code implementations28 Jan 2022 Scott Fujimoto, David Meger, Doina Precup, Ofir Nachum, Shixiang Shane Gu

In this work, we study the use of the Bellman equation as a surrogate objective for value prediction accuracy.

Value prediction

Trajectory-Constrained Deep Latent Visual Attention for Improved Local Planning in Presence of Heterogeneous Terrain

no code implementations9 Dec 2021 Stefan Wapnick, Travis Manderson, David Meger, Gregory Dudek

We present a reward-predictive, model-based deep learning method featuring trajectory-constrained visual attention for local planning in visual navigation tasks.

Visual Navigation

Multi-batch Reinforcement Learning via Sample Transfer and Imitation Learning

no code implementations29 Sep 2021 Di wu, Tianyu Li, David Meger, Michael Jenkin, Xue Liu, Gregory Dudek

Unfortunately, most online reinforcement learning algorithms require a large number of interactions with the environment to learn a reliable control policy.

Continuous Control Imitation Learning +3

Why Should I Trust You, Bellman? Evaluating the Bellman Objective with Off-Policy Data

no code implementations29 Sep 2021 Scott Fujimoto, David Meger, Doina Precup, Ofir Nachum, Shixiang Shane Gu

In this work, we analyze the effectiveness of the Bellman equation as a proxy objective for value prediction accuracy in off-policy evaluation.

Off-policy evaluation Value prediction

Generalizing Successor Features to continuous domains for Multi-task Learning

no code implementations29 Sep 2021 Melissa Mozifian, Dieter Fox, David Meger, Fabio Ramos, Animesh Garg

In this paper, we consider the problem of continuous control for various robot manipulation tasks with an explicit representation that promotes skill reuse while learning multiple tasks, related through the reward function.

Continuous Control Decision Making +3

Active 3D Shape Reconstruction from Vision and Touch

2 code implementations NeurIPS 2021 Edward J. Smith, David Meger, Luis Pineda, Roberto Calandra, Jitendra Malik, Adriana Romero, Michal Drozdzal

In this paper, we focus on this problem and introduce a system composed of: 1) a haptic simulator leveraging high spatial resolution vision-based tactile sensors for active touching of 3D objects; 2)a mesh-based 3D shape reconstruction model that relies on tactile or visuotactile signals; and 3) a set of data-driven solutions with either tactile or visuotactile priors to guide the shape exploration.

3D Reconstruction 3D Shape Reconstruction

A Deep Reinforcement Learning Approach to Marginalized Importance Sampling with the Successor Representation

1 code implementation12 Jun 2021 Scott Fujimoto, David Meger, Doina Precup

We bridge the gap between MIS and deep reinforcement learning by observing that the density ratio can be computed from the successor representation of the target policy.

Off-policy evaluation reinforcement-learning

Learning Intuitive Physics with Multimodal Generative Models

1 code implementation12 Jan 2021 Sahand Rezaei-Shoshtari, Francois Robert Hogan, Michael Jenkin, David Meger, Gregory Dudek

Predicting the future interaction of objects when they come into contact with their environment is key for autonomous agents to take intelligent and anticipatory actions.

Object STS

Practical Marginalized Importance Sampling with the Successor Representation

no code implementations1 Jan 2021 Scott Fujimoto, David Meger, Doina Precup

We bridge the gap between MIS and deep reinforcement learning by observing that the density ratio can be computed from the successor representation of the target policy.

Off-policy evaluation reinforcement-learning

Intervention Design for Effective Sim2Real Transfer

1 code implementation3 Dec 2020 Melissa Mozifian, Amy Zhang, Joelle Pineau, David Meger

The goal of this work is to address the recent success of domain randomization and data augmentation for the sim2real setting.

Causal Inference Data Augmentation

Learning the Latent Space of Robot Dynamics for Cutting Interaction Inference

1 code implementation22 Jul 2020 Sahand Rezaei-Shoshtari, David Meger, Inna Sharf

Utilization of latent space to capture a lower-dimensional representation of a complex dynamics model is explored in this work.


An Equivalence between Loss Functions and Non-Uniform Sampling in Experience Replay

1 code implementation NeurIPS 2020 Scott Fujimoto, David Meger, Doina Precup

Prioritized Experience Replay (PER) is a deep reinforcement learning technique in which agents learn from transitions sampled with non-uniform probability proportionate to their temporal-difference error.

reinforcement-learning Reinforcement Learning (RL)

3D Shape Reconstruction from Vision and Touch

1 code implementation NeurIPS 2020 Edward J. Smith, Roberto Calandra, Adriana Romero, Georgia Gkioxari, David Meger, Jitendra Malik, Michal Drozdzal

When a toddler is presented a new toy, their instinctual behaviour is to pick it upand inspect it with their hand and eyes in tandem, clearly searching over its surface to properly understand what they are playing with.

3D Shape Reconstruction

Learning to Drive Off Road on Smooth Terrain in Unstructured Environments Using an On-Board Camera and Sparse Aerial Images

no code implementations9 Apr 2020 Travis Manderson, Stefan Wapnick, David Meger, Gregory Dudek

We present a method for learning to drive on smooth terrain while simultaneously avoiding collisions in challenging off-road and unstructured outdoor environments using only visual inputs.

Detecting GAN generated errors

no code implementations2 Dec 2019 Xiru Zhu, Fengdi Che, Tianzi Yang, Tzuyang Yu, David Meger, Gregory Dudek

This is because the task of evaluating the quality of a generated image differs from deciding if an image is real or fake.

Unifying Variational Inference and PAC-Bayes for Supervised Learning that Scales

1 code implementation23 Oct 2019 Sanjay Thakur, Herke van Hoof, Gunshi Gupta, David Meger

PAC Bayes is a generalized framework which is more resistant to overfitting and that yields performance bounds that hold with arbitrarily high probability even on the unjustified extrapolations.

Variational Inference

Deep learning for Aerosol Forecasting

no code implementations14 Oct 2019 Caleb Hoyne, S. Karthik Mukkavilli, David Meger

Reanalysis datasets combining numerical physics models and limited observations to generate a synthesised estimate of variables in an Earth system, are prone to biases against ground truth.

Cascaded Gaussian Processes for Data-efficient Robot Dynamics Learning

no code implementations5 Oct 2019 Sahand Rezaei-Shoshtari, David Meger, Inna Sharf

Motivated by the recursive Newton-Euler formulation, we propose a novel cascaded Gaussian process learning framework for the inverse dynamics of robot manipulators.

Dimensionality Reduction Gaussian Processes

Learning Domain Randomization Distributions for Training Robust Locomotion Policies

no code implementations2 Jun 2019 Melissa Mozifian, Juan Camilo Gamboa Higuera, David Meger, Gregory Dudek

We explore the use of gradient-based search methods to learn a domain randomization with the following properties: 1) The trained policy should be successful in environments sampled from the domain randomization distribution 2) The domain randomization distribution should be wide enough so that the experience similar to the target robot system is observed during training, while addressing the practicality of training finite capacity models.

Human Motion Prediction via Pattern Completion in Latent Representation Space

no code implementations18 Apr 2019 Yi Tian Xu, Yaqiao Li, David Meger

Inspired by ideas in cognitive science, we propose a novel and general approach to solve human motion understanding via pattern completion on a learned latent representation space.

Action Classification General Classification +4

Uncertainty Aware Learning from Demonstrations in Multiple Contexts using Bayesian Neural Networks

1 code implementation13 Mar 2019 Sanjay Thakur, Herke van Hoof, Juan Camilo Gamboa Higuera, Doina Precup, David Meger

Learned controllers such as neural networks typically do not have a notion of uncertainty that allows to diagnose an offset between training and testing conditions, and potentially intervene.

Off-Policy Deep Reinforcement Learning without Exploration

10 code implementations7 Dec 2018 Scott Fujimoto, David Meger, Doina Precup

Many practical applications of reinforcement learning constrain agents to learn from a fixed batch of data which has already been gathered, without offering further possibility for data collection.

Continuous Control reinforcement-learning +1

Where Off-Policy Deep Reinforcement Learning Fails

no code implementations27 Sep 2018 Scott Fujimoto, David Meger, Doina Precup

This work examines batch reinforcement learning--the task of maximally exploiting a given batch of off-policy data, without further data collection.

Continuous Control reinforcement-learning +1

Addressing Function Approximation Error in Actor-Critic Methods

67 code implementations ICML 2018 Scott Fujimoto, Herke van Hoof, David Meger

In value-based reinforcement learning methods such as deep Q-learning, function approximation errors are known to lead to overestimated value estimates and suboptimal policies.

Continuous Control OpenAI Gym +3

Bayesian Policy Gradients via Alpha Divergence Dropout Inference

1 code implementation6 Dec 2017 Peter Henderson, Thang Doan, Riashat Islam, David Meger

Policy gradient methods have had great success in solving continuous control tasks, yet the stochastic nature of such problems makes deterministic value estimation difficult.

Continuous Control Policy Gradient Methods

Cost Adaptation for Robust Decentralized Swarm Behaviour

1 code implementation21 Sep 2017 Peter Henderson, Matthew Vertescher, David Meger, Mark Coates

To allay this problem, we use a meta-learning process -- cost adaptation -- which generates the optimization objective for D-RHC to solve based on a set of human-generated priors (cost and constraint functions) and an auxiliary heuristic.


Deep Reinforcement Learning that Matters

4 code implementations19 Sep 2017 Peter Henderson, Riashat Islam, Philip Bachman, Joelle Pineau, Doina Precup, David Meger

In recent years, significant progress has been made in solving challenging problems across various domains using deep reinforcement learning (RL).

Atari Games Continuous Control +2

Benchmark Environments for Multitask Learning in Continuous Domains

1 code implementation14 Aug 2017 Peter Henderson, Wei-Di Chang, Florian Shkurti, Johanna Hansen, David Meger, Gregory Dudek

As demand drives systems to generalize to various domains and problems, the study of multitask, transfer and lifelong learning has become an increasingly important pursuit.

OpenAI Gym

Improved Adversarial Systems for 3D Object Generation and Reconstruction

3 code implementations29 Jul 2017 Edward Smith, David Meger

This paper describes a new approach for training generative adversarial networks (GAN) to understand the detailed 3D shape of objects.


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