Pith. sign in

Offline Reinforcement Learning

1 Pith paper cite this work. Polarity classification is still indexing.

1 Pith paper citing it

citation-role summary

background 1

citation-polarity summary

fields

cs.LG 1

years

2025 1

verdicts

CONDITIONAL 1

roles

background 1

polarities

background 1

representative citing papers

TROFI: Trajectory-Ranked Offline Inverse Reinforcement Learning

cs.LG · 2025-06-27 · conditional · novelty 5.0

TROFI learns a reward model from ranked trajectories, labels an offline dataset with it, and trains a TD3+BC policy, matching ground-truth-reward performance on many D4RL tasks without a hand-coded reward or expert demonstrations.

citing papers explorer

Showing 1 of 1 citing paper.

  • TROFI: Trajectory-Ranked Offline Inverse Reinforcement Learning cs.LG · 2025-06-27 · conditional · none · ref 13

    TROFI learns a reward model from ranked trajectories, labels an offline dataset with it, and trains a TD3+BC policy, matching ground-truth-reward performance on many D4RL tasks without a hand-coded reward or expert demonstrations.