2 papers
cs.LG2026
Chunking the Critic: A Transformer-based Soft Actor-Critic with N-Step Returns
Dong Tian, Onur Celik, Gerhard Neumann
We introduce a sequence-conditioned critic for Soft Actor-Critic (SAC) that models trajectory context with a lightweight Transformer and trains on aggregated -step targets. Unli…
cs.LG2025
TOP-ERL: Transformer-based Off-Policy Episodic Reinforcement Learning
Ge Li, Dong Tian, Hongyi Zhou +3
This work introduces Transformer-based Off-Policy Episodic Reinforcement Learning (TOP-ERL), a novel algorithm that enables off-policy updates in the ERL framework. In ERL, policie…