Ateachh2[H] inanepisodek, thealgorithmsh, k, selects ah, k h, k(sh, k, ), and costsrh(sh, k,ah, k)andch(sh, k,ah, k). Wewillalsoshowthat k from (10) (onceitbecomes feasible) willindeedbeasafepolicy (see Proposition 5).

However, instead of gradients, the critic is, typically, only trained to accurately predict expected returns, which, on their own, are useless for policy optimization.

A wide array of control applications, ranging from medical to engineering, fundamentally deals with critical systems, i.e., systems of vital importance where the control actions have to guarantee no harm to the system functionality. Examples include managing nuclear fusion [Degrave et al., 2022], performing robotic surgeries [Datta et al., 2021], and devising patient treatment strategies [Komorowski et al., 2018].

High sample complexity has long been a challenge for RL.

In reinforcement learning, continuous time is often discretized by a time scale δ, to which the resulting performance is known to be highly sensitive. In this work, we seek tofind aδ-invariantalgorithm for policygradient (PG) methods, which performs well regardless of the value ofδ. We first identify the underlying reasons that cause PG methods to fail asδ 0, proving that the variance of the PG estimator can diverge to infinity in stochastic environments under a certain assumption of stochasticity. While durative actions or action repetition can be employed to haveδ-invariance, previous action repetition methods cannot immediately react to unexpected situations in stochastic environments. We thus propose a novelδ-invariant method namedSafe Action Repetition (SAR) applicable to any existing PG algorithm. SAR can handle the stochasticity of environments byadaptivelyreacting tochanges instates during action repetition.

Proximal policy optimization (PPO) is one of the most popular deep reinforcement learning (RL) methods, achieving state-of-the-art performance across a wide range of challenging tasks. However, as a model-free RL method, the success of PPO relies heavily on the effectiveness of its exploratory policy search. In this paper, we give an in-depth analysis on the exploration behavior of PPO, and show that PPO is prone to suffer from the risk of lack of exploration especially under the case of bad initialization, which may lead to the failure of training or being trapped in bad local optima. To address these issues, we proposed a novel policy optimization method, named Trust Region-Guided PPO (TRGPPO), which adaptively adjusts the clipping range within the trust region. We formally show that this method not only improves the exploration ability within the trust region but enjoys a better performance bound compared to the original PPO as well. Extensive experiments verify the advantage of the proposed method.