Unverified50% confidenceSolutionExact time
Dreamer's policy learning adopts the Actor-Critic framework: the Actor outputs an action distribution based on the imagined latent state s_t, and the Critic estimates the value of that state; gradients are backpropagated through the world model's latent trajectory, but the world model parameters are usually frozen to avoid the policy optimization signal contaminating the world model's learning objective, thereby maintaining training stability.
1
Sources
50%
Confidence
Long-term
Relevance
10/12/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedThe cost of freezing the world model training strategy is: if the world model itself has bias, the policy will overfit to that bias, i.e., the phenomenon of 'model exploitation' occurs.71% similarUnverifiedUsing next view prediction as a training objective forces the model to learn spatial consistency, view transformation relationships, and the implicit structure of scenes.70% similarUnverifiedPrediction capability is typically implemented by learning a transition model: given the current state and action, the model predicts the next state.69% similarUnverifiedTraditional draft model training schemes require consuming the target model's hidden states and performing distillation on the target model's logits, creating a strong binding dependency on the target model.69% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1011065API
curl https://kongchang.com/api/v1/knowledge/claims/1011065MCP
get_claim(id=1011065)