AI Research 技术调研
Search
搜索
暗色模式
亮色模式
探索
标签: sample-efficiency
此标签下有13条笔记。
2026年7月16日
3D-MVP: 3D Multiview Pretraining for Robotic Manipulation
3d-pretraining
masked-autoencoder
multi-view-transformer
rvt
objaverse
representation-learning
rlbench
colosseum
sample-efficiency
2026年7月16日
3D Diffusion Policy (DP3): Generalizable Visuomotor Policy Learning via Simple 3D Representations
diffusion-policy
imitation-learning
point-cloud
manipulation
dexterous-hand
3d-representation
visuomotor
sample-efficiency
RSS2024
任务
演示/任务
2026年7月16日
Equivariant Diffusion Policy
diffusion-policy
equivariance
SO2-symmetry
imitation-learning
manipulation
sample-efficiency
escnn
mimicgen
CoRL2024
2026年7月16日
Render and Diffuse: Aligning Image and Action Spaces for Diffusion-based Behaviour Cloning
behavior-cloning
diffusion-policy
action-diffusion
rendered-action-representation
spatial-generalization
sample-efficiency
rlbench
vision-transformer
ddim
gripper-rendering
2026年7月16日
SGRv2: Leveraging Locality to Boost Sample Efficiency in Robotic Manipulation
manipulation
action-locality
point-wise-features
sample-efficiency
imitation-learning
rlbench
maniskill2
mimicgen
keyframe-control
dense-control
2026年7月16日
Model-Based Reinforcement Learning for Atari
world-model
model-based-rl
video-prediction
atari
stochastic-discrete-latent
sample-efficiency
dyna
ppo
tensor2tensor
2026年7月16日
Mastering Atari Games with Limited Data (EfficientZero)
world-model
model-based-rl
muzero
mcts
sample-efficiency
self-supervised
atari-100k
simsiam
value-prefix
off-policy-correction
2026年7月16日
Transformers are Sample-Efficient World Models (IRIS)
world-model
model-based-rl
transformer
discrete-autoencoder
vqvae
autoregressive
image-tokens
atari-100k
sample-efficiency
latent-imagination
Superhuman
2026年7月16日
HarmonyDream: Task Harmonization Inside World Models
world-model
model-based-rl
multi-task-learning
loss-balancing
dreamer
atari-100k
meta-world
rlbench
sample-efficiency
2026年7月16日
STORM: Efficient Stochastic Transformer based World Models for Reinforcement Learning
world-model
model-based-rl
transformer
categorical-vae
atari-100k
imagination
actor-critic
sample-efficiency
2026年7月16日
Transformer-based World Models Are Happy With 100k Interactions (TWM)
world-model
model-based-rl
transformer-xl
atari-100k
sample-efficiency
latent-imagination
autoregressive
actor-critic
kl-balancing
2026年7月16日
EfficientZero V2: Mastering Discrete and Continuous Control with Limited Data
world-model
model-based-rl
mcts
gumbel-search
sample-efficiency
continuous-control
atari-100k
dmcontrol
off-policy-correction
2026年7月16日
ReZero: Boosting MCTS-based Algorithms by Backward-view and Entire-buffer Reanalyze
reinforcement-learning
mcts
muzero
efficientzero
reanalyze
sample-efficiency
tree-search
bandit-theory
lightzero