conftrace_

n-step return

7 papers

Explore in graph

Also known as

NSR

Co-occurring keywords · papers mentioning both

variance reduction (2) value function (2) temporal difference learning (2) reinforcement learning (2) transformer-based critic (1) compound returns (1) minibatched experience replay (1) q-value propagation (1) value function transfer (1) complex-backup update (1)

Papers

TOP-ERL: Transformer-based Off-Policy Episodic Reinforcement Learning ICLR 2025 Averaging n-step Returns Reduces Variance in Reinforcement Learning ICML 2024 A Long N-step Surrogate Stage Reward for Deep Reinforcement Learning NeurIPS 2023 Offline Reinforcement Learning at Multiple Frequencies CoRL 2022 Value Function Transfer for Deep Multi-Agent Reinforcement Learning Based on N-Step Returns IJCAI 2019 Beyond the One-Step Greedy Approach in Reinforcement Learning ICML 2018 TD_gamma: Re-evaluating Complex Backups in Temporal Difference Learning NeurIPS 2011