Pith. sign in

Successor features for transfer in reinforcement learning

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

1 Pith paper citing it

fields

cs.LG 1

years

2025 1

verdicts

CONDITIONAL 1

representative citing papers

SR-Reward: Taking The Path More Traveled

cs.LG · 2025-01-04 · conditional · novelty 6.0

SR-Reward replaces the environment reward with the L2 norm of a successor representation learned from demonstrations, enabling offline RL without reward labels.

citing papers explorer

Showing 1 of 1 citing paper.

  • SR-Reward: Taking The Path More Traveled cs.LG · 2025-01-04 · conditional · none · ref 4

    SR-Reward replaces the environment reward with the L2 norm of a successor representation learned from demonstrations, enabling offline RL without reward labels.