Skip to content
conftrace_

bayes-adaptive markov decision process

4 papers

Explore in graph

Also known as

BAMDP

Co-occurring keywords · papers mentioning both

meta-reinforcement learning (2) uncertainty reasoning (1) contextual factor (1) human helpfulness model (1) individual factor (1) task belief (1) sparse reward setting (1) risk-averse reinforcement learning (1) potential-based reward shaping (1) conditional value at risk (1)

Papers

BAMDP Shaping: a Unified Framework for Intrinsic Motivation and Reward Shaping ICLR 2025 Learning Task Belief Similarity with Latent Dynamics for Meta-Reinforcement Learning ICLR 2025 Modeling Human Helpfulness with Individual and Contextual Factors for Robot Planning RSS 2021 Risk-Averse Bayes-Adaptive Reinforcement Learning NeurIPS 2021