7 papers · 1 filter
GHIL-Glue: Hierarchical Control with Filtered Subgoal Images
Kyle B. Hatch, Ashwin Balakrishna, Oier Mees +8
Image and video generative models that are pre-trained on Internet-scale data can greatly increase the generalization capacity of robot learning systems. These models can function…
A Single Goal is All You Need: Skills and Exploration Emerge from Contrastive RL without Rewards, Demonstrations, or Subgoals
Grace Liu, Michael Tang, Benjamin Eysenbach
In this paper, we present empirical evidence of skills and directed exploration emerging from a simple RL algorithm long before any successful trials are observed. For example, in…
A Rate-Distortion View of Uncertainty Quantification
Ifigeneia Apostolopoulou, Benjamin Eysenbach, Frank Nielsen +1
In supervised learning, understanding an input's proximity to the training data can help a model decide whether it has sufficient evidence for reaching a reliable prediction. While…
Game-Theoretic Robust Reinforcement Learning Handles Temporally-Coupled Perturbations
Yongyuan Liang, Yanchao Sun, Ruijie Zheng +5
Deploying reinforcement learning (RL) systems requires robustness to uncertainty and model misspecification, yet prior robust RL methods typically only study noise introduced indep…
Bridging State and History Representations: Understanding Self-Predictive RL
Tianwei Ni, Benjamin Eysenbach, Erfan Seyedsalehi +4
Representations are at the core of all deep reinforcement learning (RL) methods for both Markov decision processes (MDPs) and partially observable Markov decision processes (POMDPs…
Closing the Gap between TD Learning and Supervised Learning -- A Generalisation Point of View
Raj Ghugare, Matthieu Geist, Glen Berseth +1
Some reinforcement learning (RL) algorithms can stitch pieces of experience to solve a task never seen before during training. This oft-sought property is one of the few ways in wh…