activity
20152023
most citedHow to Train Your Robot with Deep Reinforcement Learning; Lessons We've Learned

565 citations · 7.1k across the 210 of their papers we have counts for

collaborators
Showing 2023 · cs.LGShow all

17 papers · 2 filters

cs.LG2023★ 2 cited

Zero-Shot Goal-Directed Dialogue via RL on Imagined Conversations

Joey Hong, Sergey Levine, Anca Dragan

Large language models (LLMs) have emerged as powerful and general solutions to many natural language tasks. However, many of the most important applications of language generation…

cs.LG2023

Offline RL with Observation Histories: Analyzing and Improving Sample Complexity

Joey Hong, Anca Dragan, Sergey Levine

Offline reinforcement learning (RL) can in principle synthesize more optimal behavior from a dataset consisting only of suboptimal trials. One way that this can happen is by "stitc…

cs.LG2023

Contrastive Example-Based Control

Kyle Hatch, Benjamin Eysenbach, Rafael Rafailov +4

While many real-world problems that might benefit from reinforcement learning, these problems rarely fit into the MDP mold: interacting with the environment is often expensive and…

cs.LG2023★ 2 cited

HIQL: Offline Goal-Conditioned RL with Latent States as Actions

Seohong Park, Dibya Ghosh, Benjamin Eysenbach +1

Unsupervised pre-training has recently become the bedrock for computer vision and natural language processing. In reinforcement learning (RL), goal-conditioned RL can potentially p…

cs.LG2023

Confidence-Based Model Selection: When to Take Shortcuts for Subpopulation Shifts

Annie S. Chen, Yoonho Lee, Amrith Setlur +2

Effective machine learning models learn both robust features that directly determine the outcome of interest (e.g., an object with wheels is more likely to be a car), and shortcut…

cs.LG2023★ 9 cited

IDQL: Implicit Q-Learning as an Actor-Critic Method with Diffusion Policies

Philippe Hansen-Estruch, Ilya Kostrikov, Michael Janner +2

Effective offline RL methods require properly handling out-of-distribution actions. Implicit Q-learning (IQL) addresses this by training a Q-function using only dataset actions thr…