conftrace_

conservative policy iteration

6 papers

Explore in graph

Also known as

CPI

Co-occurring keywords · papers mentioning both

off-policy learning (3) value iteration (2) policy gradient (2) performance bound (1) tabular setting (1) neural network (1) actor critic (1) stochastic mixture (1) in-sample optimal policy (1) soft clipping (1)

Papers

Iteratively Refined Behavior Regularization for Offline Reinforcement Learning NeurIPS 2024 The Sufficiency of Off-Policyness and Soft Clipping: PPO Is Still Insufficient according to an Off-Policy Measure AAAI 2023 Variance-Reduced Conservative Policy Iteration ALT 2023 Cautious Actor-Critic ACML 2021 Deep Conservative Policy Iteration AAAI 2020 Approximate Policy Iteration Schemes: A Comparison ICML 2014