A transformer world model agent using a static patch tokenizer, warmup before imagination training, and block teacher forcing reaches 69.66% reward on Craftax-classic, beating DreamerV3 and the human expert figure.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Improving Transformer World Models for Data-Efficient RL
A transformer world model agent using a static patch tokenizer, warmup before imagination training, and block teacher forcing reaches 69.66% reward on Craftax-classic, beating DreamerV3 and the human expert figure.