[2202.05607] Online Decision Transformer

Abstract:Recent work has shown that offline reinforcement learning (RL) can be formulated as a sequence modeling problem (Chen et al., 2021; Janner et al., 2021) and solved via approaches similar to large-scale language modeling. However, any practical instantiation of RL also involves an online component, where policies pretrained on passive offline datasets are finetuned via taskspecific interactions with the environment. We propose Online Decision Transformers (ODT), an RL algorithm based on sequence modeling that blends offline pretraining with online finetuning in a unified framework. Our framework uses sequence-level entropy regularizers in conjunction with autoregressive modeling objectives for sample-efficient exploration and finetuning. Empirically, we show that ODT is competitive with the state-of-the-art in absolute performance on the D4RL benchmark but shows much more significant gains during the finetuning procedure.

View PDF HTML (experimental) Abstract:Recent work has shown that offline reinforcement learning (RL) can be formulated as a sequence modeling problem (Chen et al., 2021; Janner et al., 2021) and solved via approaches similar to large-scale language modeling. However, any practical instantiation of RL also involves an online component, where policies pretrained on passive offline datasets are finetuned via taskspecific interactions with the environment. We propose Online Decision Transformers (ODT), an RL algorithm based on sequence modeling that blends offline pretraining with online…

saved by

• Emanuel Ruzak

related reading

• 2106.01345arxiv.org
• [2305.18290] Direct Preference Optimization: Your Language Model is Secretly a Reward Modelarxiv.org
• [2602.19362] LLMs Can Learn to Reason Via Off-Policy RLarxiv.org
• [2103.06326] S4RL: Surprisingly Simple Self-Supervision for Offline Reinforcement Learningarxiv.org
• [2212.07677] Transformers learn in-context by gradient descentarxiv.org
• [2604.13010] Lightning OPD: Efficient Post-Training for Large Reasoning Models with Offline On-Policy Distillationarxiv.org
• [2510.13786] The Art of Scaling Reinforcement Learning Compute for LLMsarxiv.org
• 2109.10813.pdfarxiv.org
• [2210.13382] Emergent World Representations: Exploring a Sequence Model Trained on a Synthetic Taskarxiv.org
• Do Language Models Need Sleep? Offline Recurrence for Improved Online Inferencearxiv.org
• You Can Learn Tokenization End-to-End with Reinforcement Learningarxiv.org
• [2307.04354] Policy Finetuning in Reinforcement Learning via Design of Experiments using Offline Dataar5iv.labs.arxiv.org