Accelerating Policy Gradient by Estimating Value Function from Prior Computation in Deep Reinforcement Learning
This is an incremental improvement for reinforcement learning practitioners aiming to reduce training time and resource usage.
The paper tackles the problem of sample inefficiency in on-policy policy gradient methods by estimating value functions from prior computations, such as Q-networks from DQN or related environments, and shows improved sample efficiency in several tasks.
This paper investigates the use of prior computation to estimate the value function to improve sample efficiency in on-policy policy gradient methods in reinforcement learning. Our approach is to estimate the value function from prior computations, such as from the Q-network learned in DQN or the value function trained for different but related environments. In particular, we learn a new value function for the target task while combining it with a value estimate from the prior computation. Finally, the resulting value function is used as a baseline in the policy gradient method. This use of a baseline has the theoretical property of reducing variance in gradient computation and thus improving sample efficiency. The experiments show the successful use of prior value estimates in various settings and improved sample efficiency in several tasks.