Jason Yan

activity

20212026

most citedHow Far I'll Go: Offline Goal-Conditioned Reinforcement Learning via

f

-Advantage Regression

2 citations · 4 across the 5 of their papers we have counts for

collaborators

Showing cs.LGShow all

2 papers · 1 filter

cs.LG2023

TOM: Learning Policy-Aware Models for Model-Based Reinforcement Learning via Transition Occupancy Matching

Yecheng Jason Ma, Kausik Sivakumar, Jason Yan +2

Standard model-based reinforcement learning (MBRL) approaches fit a transition model of the environment to all past experience, but this wastes model capacity on data that is irrel…

cs.LG2022★ 2 cited

How Far I'll Go: Offline Goal-Conditioned Reinforcement Learning via $f$ -Advantage Regression

Yecheng Jason Ma, Jason Yan, Dinesh Jayaraman +1

Offline goal-conditioned reinforcement learning (GCRL) promises general-purpose skill learning in the form of reaching diverse goals from purely offline datasets. We propose $\text…

TOM: Learning Policy-Aware Models for Model-Based Reinforcement Learning via Transition Occupancy Matching

How Far I'll Go: Offline Goal-Conditioned Reinforcement Learning via f-Advantage Regression

How Far I'll Go: Offline Goal-Conditioned Reinforcement Learning via $f$ -Advantage Regression