Pieter Abbeel

One-Shot Learning of Manipulation Skills with Online Dynamics Adaptation and Neural Network Priors

2015 · arXiv (Cornell University)

One of the key challenges in applying reinforcement learning to complex robotic control tasks is the need to gather large amounts of experience in order to find an effective policy for the task at hand. …

Adversarial Attacks on Neural Network Policies

2017 · arXiv (Cornell University)

Machine learning classifiers are known to be vulnerable to inputs maliciously constructed by adversaries to force misclassification. Such adversarial examples have been extensively studied in the context of computer vision applications. In this work, we …

Imitation from Observation: Learning to Imitate Behaviors from Raw Video via Context Translation

2017 · arXiv (Cornell University)

Imitation learning is an effective approach for autonomous systems to acquire control policies when an explicit reward function is unavailable, using supervision provided as demonstrations from an expert, typically a human operator. However, standard imitation …

Domain Randomization for Transferring Deep Neural Networks from Simulation to the Real World

2017 · arXiv (Cornell University)

Bridging the 'reality gap' that separates simulated robotics from experiments on hardware could accelerate robotic research through improved data availability. This paper explores domain randomization, a simple technique for training models on simulated images that …

Stochastic Latent Actor-Critic: Deep Reinforcement Learning with a Latent Variable Model

2019 · arXiv (Cornell University)

Deep reinforcement learning (RL) algorithms can use high-capacity deep networks to learn directly from image observations. However, these high-dimensional observation spaces present a number of challenges in practice, since the policy must now solve two …

Robust Reinforcement Learning using Adversarial Populations

2020 · arXiv (Cornell University)

Reinforcement Learning (RL) is an effective tool for controller design but can struggle with issues of robustness, failing catastrophically when the underlying system dynamics are perturbed. The Robust RL formulation tackles this by adding worst-case …

Scenic4RL: Programmatic Modeling and Generation of Reinforcement Learning Environments

2021 · arXiv (Cornell University)

The capability of a reinforcement learning (RL) agent heavily depends on the diversity of the learning scenarios generated by the environment. Generation of diverse realistic scenarios is challenging for real-time strategy (RTS) environments. The RTS …

Teachable Reinforcement Learning via Advice Distillation

2022 · arXiv (Cornell University)

Training automated agents to complete complex tasks in interactive environments is challenging: reinforcement learning requires careful hand-engineering of reward functions, imitation learning requires specialized infrastructure and access to a human expert, and learning from intermediate …

CIC: Contrastive Intrinsic Control for Unsupervised Skill Discovery

2022 · arXiv (Cornell University)

We introduce Contrastive Intrinsic Control (CIC), an algorithm for unsupervised skill discovery that maximizes the mutual information between state-transitions and latent skill vectors. CIC utilizes contrastive learning between state-transitions and skills to learn behavior embeddings …

DayDreamer: World Models for Physical Robot Learning

2022 · arXiv (Cornell University)

To solve tasks in complex environments, robots need to learn from experience. Deep reinforcement learning is a common approach to robot learning but requires a large amount of trial and error to learn, limiting its …

Learning Interactive Real-World Simulators

2023 · arXiv (Cornell University)

Generative models trained on internet data have revolutionized how text, image, and video content can be created. Perhaps the next milestone for generative models is to simulate realistic experience in response to actions taken by …

DreamSmooth: Improving Model-based Reinforcement Learning via Reward Smoothing

2023 · arXiv (Cornell University)

Model-based reinforcement learning (MBRL) has gained much attention for its ability to learn complex behaviors in a sample-efficient way: planning actions by generating imaginary trajectories with predicted rewards. Despite its success, we found that surprisingly, …

Incentivizing Exploration In Reinforcement Learning With Deep Predictive Models

2015 · arXiv (Cornell University)

Achieving efficient and scalable exploration in complex domains poses a major challenge in reinforcement learning. While Bayesian and PAC-MDP approaches to the exploration problem offer strong formal guarantees, they are often impractical in higher dimensions …