Timezone: »

Striving for Simplicity and Performance in Off-Policy DRL: Output Normalization and Non-Uniform Sampling
Che Wang · Yanqiu Wu · Quan Vuong · Keith Ross

Tue Jul 14 06:00 PM -- 06:45 PM & Wed Jul 15 04:00 AM -- 04:45 AM (PDT) @ Virtual

We aim to develop off-policy DRL algorithms that not only exceed state-of-the-art performance but are also simple and minimalistic. For standard continuous control benchmarks, Soft Actor-Critic (SAC), which employs entropy maximization, currently provides state-of-the-art performance. We first demonstrate that the entropy term in SAC addresses action saturation due to the bounded nature of the action spaces, with this insight, we propose a streamlined algorithm with a simple normalization scheme or with inverted gradients. We show that both approaches can match SAC's sample efficiency performance without the need of entropy maximization, we then propose a simple non-uniform sampling method for selecting transitions from the replay buffer during training. Extensive experimental results demonstrate that our proposed sampling scheme leads to state of the art sample efficiency on challenging continuous control tasks. We combine all of our findings into one simple algorithm, which we call Streamlined Off Policy with Emphasizing Recent Experience, for which we provide robust public-domain code.

Author Information

Che Wang (New York University)
Yanqiu Wu (New York University)
Quan Vuong (University of California San Diego)
Keith Ross (New York University Shanghai)

More from the Same Authors