SimBelief trains a latent task-belief metric with learned dynamics to speed up task inference and adaptation in sparse-reward meta-RL, outperforming baselines on MuJoCo and panda-gym.
Contrabar: Contrastive bayes-adaptive deep rl
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.AI 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
Learning Task Belief Similarity with Latent Dynamics for Meta-Reinforcement Learning
SimBelief trains a latent task-belief metric with learned dynamics to speed up task inference and adaptation in sparse-reward meta-RL, outperforming baselines on MuJoCo and panda-gym.