Trust-pcl: An Off-policy Trust Region Method For Continuous Control

Abstract

Trust region methods, such as TRPO, are often used to stabilize policy optimization algorithms in reinforcement learning (RL). While current trust region strategies are effective for continuous control, they typically require a prohibitively large amount of on-policy interaction with the environment. To address this problem, we propose an off-policy trust region method, Trust-PCL. The algorithm is the result of observing that the optimal policy and state values of a maximum reward objective with a relative-entropy regularizer satisfy a set of multi-step pathwise consistencies along any path. Thus, Trust-PCL is able to maintain optimization stability while exploiting off-policy data to improve sample efficiency. When evaluated on a number of continuous control tasks, Trust-PCL improves the solution quality and sample efficiency of TRPO.

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keynachum2017trust

Related papers

• Adaptive Trust Region Policy Optimization: Global Convergence And Faster Rates For Regularized Mdps (2019)12.10
• Entrpo: Trust Region Policy Optimization Method With Entropy Regularization (2021)0.00
• Embedding Safety Into RL: A New Take On Trust Region Methods (2024)0.00
• Simple Policy Optimization (2024)0.00
• Hindsight Trust Region Policy Optimization (2019)0.00
• Average-reward Reinforcement Learning With Trust Region Methods (2021)0.00
• Trust Region Policy Optimisation In Multi-agent Reinforcement Learning (2021)0.00
• Truly Proximal Policy Optimization (2019)0.00