Methods › Reinforcement Learning › RL Transformers › CoBERL
Contrastive BERT
CoBERL
Introduced by Andrea Banino et al. in CoBERL: Contrastive BERT for Reinforcement Learning
archive 2025-07-28 Description, source and code snippet are the archive's method entry.
Contrastive BERT is a reinforcement learning agent that combines a new contrastive loss and a hybrid LSTM-transformer architecture to tackle the challenge of improving data efficiency for RL. It uses bidirectional masked prediction in combination with a generalization of recent contrastive methods to learn better representations for transformers in RL, without the need of hand engineered data augmentations.
For the architecture, a residual network is used to encode observations into embeddings Yₜ. Yₜ is fed through a causally masked GTrXL transformer, which computes the predicted masked inputs Xₜ and passes those together with Yₜ to a learnt gate. The output of the gate is passed through a single LSTM layer to produce the values that we use for computing the RL loss. A contrastive loss is computed using predicted masked inputs Xₜ and Yₜ as targets. For this, we do not use the causal mask of the Transformer.
Papers archive 2025-07-28
1 shown of 1, newest first. Repository counts are the archive's code-links table. A Syntology line states what Syntology ran from that paper's harvested code; it is per sample and not a correctness claim.
-
CoBERL: Contrastive BERT for Reinforcement Learning 12 Jul 2021 · 2 repositories · arXiv:2107.05431Syntology ran 3 of 3 samples · 0 unverified
Tasks archive 2025-07-28
3 tasks the archive attaches to papers tagged with this method, by distinct papers. A task without a page in the catalog is plain text.
Usage over time archive 2025-07-28
Components: the archive holds no method-to-method composition, so PwC's Components table cannot be rebuilt; the Papers list carries no Results column for the same reason (the archive does not join its leaderboard rows to method tags).
Categories archive 2025-07-28
Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections