policy
Decision_Transformer_Sequence-Modeling_Deep_Reinforcement_Learning
Delavari-Alireza · PyTorch
or hover any field below to flag it
Overview
Name
Decision_Transformer_Sequence-Modeling_Deep_Reinforcement_Learning
Author
Delavari-Alireza
Framework
PyTorch
License
MIT
Skill type
manipulation
Evidence level
untested
Task description
This repository delivers a from‑scratch Python 3.11 implementation of Decision Transformers, recasting offline RL as conditional sequence modeling with decoder‑only architectures (e.g., GPT‑2 or any Hugging Face decoder). Experiments span synthetic random walks, continuous control, manipulation, and
Spaces
Action space
other · 0-dim · 0Hz
Observation space
- type: other
Links
HuggingFace repo
null
Paper (arXiv)
null
Compatible robots
3+17 mentioned but not in catalog yetCompatible environments
0No environments list Decision_Transformer_Sequence-Modeling_Deep_Reinforcement_Learning yet.
Datasets that reference this policy
0No datasets reference Decision_Transformer_Sequence-Modeling_Deep_Reinforcement_Learning yet.