AI RESEARCH
Approximate Next Policy Sampling: Replacing Conservative Target Policy Updates in Deep RL
arXiv CS.LG
•
ArXi:2605.05481v1 Announce Type: new We revisit a classic "chicken-and-egg" problem in reinforcement learning: to safely improve a policy, the value function must be accurate on the state-visitation distribution of the updated policy. That distribution over states is unknown and cannot be sampled for the purposes of