conftrace_

policy inference

3 papers

Explore in graph

Co-occurring keywords

imitation learning (744) action sequence (23) robot policy (8) action generation (19) action sequence generation (3) bpe tokenization (7) multi-source datum (10) denoising diffusion bridge model (1) behavior estimation (2) sparse reward (141)

Papers

Prior Does Matter: Visual Navigation via Denoising Diffusion Bridge Models CVPR 2025
Subwords as Skills: Tokenization for Sparse-Reward Reinforcement Learning NIPS 2024
Behavior Estimation from Multi-Source Data for Offline Reinforcement Learning AAAI 2023