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.
Imitating interactive intelligence.arXiv preprint arXiv:2012.05672
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
representative citing papers
Perceiver IO is a general architecture that processes arbitrary structured inputs and outputs with linear scaling and achieves strong results on GLUE, Sintel optical flow, multi-task reasoning, and StarCraft II without task-specific components.
PPD integrates PPO into policy distillation so the student collects and uses its own rewards, yielding better sample efficiency and robustness than standard student-distill or teacher-distill on ATARI, Mujoco, and Procgen tasks.
Ranked preference modeling outperforms imitation learning for language model alignment and scales more favorably with model size.
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.
-
Perceiver IO: A General Architecture for Structured Inputs & Outputs
Perceiver IO is a general architecture that processes arbitrary structured inputs and outputs with linear scaling and achieves strong results on GLUE, Sintel optical flow, multi-task reasoning, and StarCraft II without task-specific components.
-
Proximal Policy Distillation
PPD integrates PPO into policy distillation so the student collects and uses its own rewards, yielding better sample efficiency and robustness than standard student-distill or teacher-distill on ATARI, Mujoco, and Procgen tasks.
-
A General Language Assistant as a Laboratory for Alignment
Ranked preference modeling outperforms imitation learning for language model alignment and scales more favorably with model size.