CompoFormer adaptively composes prior task policies in a Decision Transformer to improve stability and plasticity in continual offline RL, and the paper introduces the OCW benchmark.
Merging decision transformers: Weight averaging for form- ing multi-task policies
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Continual Task Learning through Adaptive Policy Self-Composition
CompoFormer adaptively composes prior task policies in a Decision Transformer to improve stability and plasticity in continual offline RL, and the paper introduces the OCW benchmark.