5 citations · 16 across the 15 of their papers we have counts for
16 papers
CopyQuad: Quadrupedal Skill Transfer from a Single Side-View Video Without a Depth Model
Mohamad H. Danesh, Raina Hu, Mengxue Xu +1
Video-to-robot pipelines for quadrupedal imitation insert a learned lifting stage, either a monocular depth model or a per-clip 3D reconstruction, to recover the one axis a side-vi…
Drift Q-Learning
Anas Houssaini, Mohamad H. Danesh, Amin Abyaneh +3
Offline reinforcement learning requires improving a policy from fixed data while avoiding out-of-distribution actions with unreliable value estimates. Diffusion and flow policies h…
Morphology-Conditioned World Model for Cross-Embodiment Quadrupedal Locomotion
Mohamad H. Danesh, Chenhao Li, Amin Abyaneh +5
World models promise a paradigm shift in robotics, where an agent learns the physics of its environment once and then acquires behaviors efficiently. Yet the learned dynamics model…
Contractive Diffusion Policies: Robust Action Diffusion via Contractive Score-Based Sampling with Differential Equations
Amin Abyaneh, Charlotte Morissette, Mohamad H. Danesh +4
Diffusion policies have emerged as powerful generative models for offline policy learning, whose sampling process can be rigorously characterized by a score function guiding a stoc…
VOCALoco: Viability-Optimized Cost-aware Adaptive Locomotion
Stanley Wu, Mohamad H. Danesh, Simon Li +5
Recent advancements in legged robot locomotion have facilitated traversal over increasingly complex terrains. Despite this progress, many existing approaches rely on end-to-end dee…
Safe Domain Randomization via Uncertainty-Aware Out-of-Distribution Detection and Policy Adaptation
Mohamad H. Danesh, Maxime Wabartha, Stanley Wu +2
Deploying reinforcement learning (RL) policies in real-world involves significant challenges, including distribution shifts, safety concerns, and the impracticality of direct inter…
YRC-Bench: A Benchmark for Learning to Coordinate with Experts
Mohamad H. Danesh, Nguyen X. Khanh, Tu Trinh +1
When deployed in the real world, AI agents will inevitably face challenges that exceed their individual capabilities. A critical component of AI safety is an agent's ability to rec…
Getting By Goal Misgeneralization With a Little Help From a Mentor
Tu Trinh, Mohamad H. Danesh, Nguyen X. Khanh +1
While reinforcement learning (RL) agents often perform well during training, they can struggle with distribution shift in real-world deployments. One particularly severe risk of di…
Open RL Benchmark: Comprehensive Tracked Experiments for Reinforcement Learning
Shengyi Huang, Quentin Gallouédec, Florian Felten +30
In many Reinforcement Learning (RL) papers, learning curves are useful indicators to measure the effectiveness of RL algorithms. However, the complete raw data of the learning curv…
Taming the Tail in Class-Conditional GANs: Knowledge Sharing via Unconditional Training at Lower Resolutions
Saeed Khorram, Mingqi Jiang, Mohamad Shahbazi +2
Despite extensive research on training generative adversarial networks (GANs) with limited training data, learning to generate images from long-tailed training distributions remain…
Contextual Pre-planning on Reward Machine Abstractions for Enhanced Transfer in Deep Reinforcement Learning
Guy Azran, Mohamad H. Danesh, Stefano V. Albrecht +1
Recent studies show that deep reinforcement learning (DRL) agents tend to overfit to the task on which they were trained and fail to adapt to minor environment changes. To expedite…
LEADER: Learning Attention over Driving Behaviors for Planning under Uncertainty
Mohamad H. Danesh, Panpan Cai, David Hsu
Uncertainty on human behaviors poses a significant challenge to autonomous driving in crowded urban environments. The partially observable Markov decision processes (POMDPs) offer…
Out-of-Distribution Dynamics Detection: RL-Relevant Benchmarks and Results
Mohamad H Danesh, Alan Fern
We study the problem of out-of-distribution dynamics (OODD) detection, which involves detecting when the dynamics of a temporal process change compared to the training-distribution…
Stochastic Block-ADMM for Training Deep Networks
Saeed Khorram, Xiao Fu, Mohamad H. Danesh +2
In this paper, we propose Stochastic Block-ADMM as an approach to train deep neural networks in batch and online settings. Our method works by splitting neural networks into an arb…
Reducing Neural Network Parameter Initialization Into an SMT Problem
Mohamad H. Danesh
Training a neural network (NN) depends on multiple factors, including but not limited to the initial weights. In this paper, we focus on initializing deep NN parameters such that i…
Re-understanding Finite-State Representations of Recurrent Policy Networks
Mohamad H. Danesh, Anurag Koul, Alan Fern +1
We introduce an approach for understanding control policies represented as recurrent neural networks. Recent work has approached this problem by transforming such recurrent policy…