Unverified50% confidenceFactExact time
The temporal difference (TD) residual is defined as the immediate reward plus the discounted value estimate of the next state, minus the value estimate of the current state.
1
Sources
50%
Confidence
Long-term
Relevance
10/22/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedUnder trajectory-level sparse rewards, the TD residual propagates backward along the entire trajectory, causing the credit of early actions to be diluted or even distorted by later outcomes.66% similarUnverifiedThe margin is defined as the difference between the threshold and the current value of the staleness signal; the larger the margin, the smaller the difference between the current input and the input at the last refresh, and the smaller the approximation error introduced by reusing old activations.64% similarUnverifiedRETD does not modify the follow-on trace or importance sampling ratios; it stores the emphatic TD signal in a leaky scalar state and releases the correction signal through a delay mechanism.64% similarUnverifiedLonger context means higher time-to-first-token (TTFT), and token count is directly linearly correlated with inference costs.63% similarVerifiedInference latency is typically decomposed into two core metrics: time to first token (TTFT) and subsequent token generation throughput.62% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1083959API
curl https://kongchang.com/api/v1/knowledge/claims/1083959MCP
get_claim(id=1083959)