conftrace_

successor measure

4 papers

Explore in graph

Co-occurring keywords · papers mentioning both

proto-value network (1) behavior foundation model (1) policy-independent basis (1) reward-free interaction (1) visit distribution (1) forward-backward representation (1) near-optimal policy (1) auxiliary task (1) affine combination (1) unsupervised reinforcement learning (1)

Papers

Proto Successor Measure: Representing the Behavior Space of an RL Agent ICML 2025 Unsupervised Zero-Shot Reinforcement Learning via Dual-Value Forward-Backward Representation ICLR 2025 Fast Imitation via Behavior Foundation Models ICLR 2024 Proto-Value Networks: Scaling Representation Learning with Auxiliary Tasks ICLR 2023