Decision Transformer casts RL as autoregressive sequence modeling conditioned on desired returns, past states and actions, matching or exceeding offline RL baselines on Atari, Gym and Key-to-Door tasks.
arXiv preprint arXiv:2006.03662 , year=
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
representative citing papers
NEO induces compositional latent programs as world theories from observations and executes them to enable explanation-driven generalization.
A Goal-Conditioned Decision Transformer is adapted for offline multi-goal RL and shown to outperform online baselines on a new Franka Emika Panda dataset.
citing papers explorer
-
Decision Transformer: Reinforcement Learning via Sequence Modeling
Decision Transformer casts RL as autoregressive sequence modeling conditioned on desired returns, past states and actions, matching or exceeding offline RL baselines on Atari, Gym and Key-to-Door tasks.
-
Learning to Theorize the World from Observation
NEO induces compositional latent programs as world theories from observations and executes them to enable explanation-driven generalization.
-
Goal-Conditioned Decision Transformer for Multi-Goal Offline Reinforcement Learning
A Goal-Conditioned Decision Transformer is adapted for offline multi-goal RL and shown to outperform online baselines on a new Franka Emika Panda dataset.