Unverified50% confidenceFactExact time
PPRS (Progress Potential Reward Shaping) computes the reward for each step based on the potential increment of a potential function Φ, and is a concrete instance of the potential-based shaping framework proved by Ng et al. in 1999, satisfying reward shaping invariance.
1
Sources
50%
Confidence
Long-term
Relevance
10/14/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedPotential-based reward shaping guarantees that the optimal policy remains unchanged.64% similarUnverifiedThe authors applied the same scheduler to dynamic potential search to obtain Probabilistic Dynamic Potential Search (PDPS), whose shared success effect depends on the specific domain and bound settings, and does not take effect consistently in all cases.62% similarUnverified模型在PPO优化中通过增加输出长度获取更高奖励的现象被称为reward hacking（奖励攻击）62% similarUnverifiedReward shaping refers to adding extra, denser guiding reward signals on top of the original sparse reward to help agents learn faster and more correctly.61% similarUnverifiedThe NGU algorithm superimposes external rewards with two types of intrinsic rewards: a short-term reward based on intra-episode novelty and a long-term reward based on lifetime novelty.61% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1024906API
curl https://kongchang.com/api/v1/knowledge/claims/1024906MCP
get_claim(id=1024906)