Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

Online Decision Transformer

About

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.

Qinqing Zheng, Amy Zhang, Aditya Grover• 2022

Related benchmarks

TaskDatasetResultRank
LocomotionD4RL walker2d-medium-expert
Normalized Score3.04e+3
90
LocomotionD4RL Walker2d medium--
70
LocomotionD4RL HalfCheetah Medium-Replay--
68
LocomotionD4RL hopper-medium-expert--
28
LocomotionD4RL hopper medium-replay
Test Return698.8
22
LocomotionD4RL halfcheetah-medium-expert
Test Return3.57e+3
22
LocomotionD4RL Cheetah Medium
Mean Return4.24e+3
17
Online Fine-tuningD4RL MuJoCo and Maze2D online fine-tuning v2 v0
Normalized Return97.5
14
LocomotionD4RL walker2d medium-replay
Mean Return1.38e+3
12
Showing 9 of 9 rows

Other info

Follow for update