P3O: Policy-on Policy-off Policy Optimization
This addresses the problem of high sample complexity in RL for researchers and practitioners, offering an incremental improvement by combining existing approaches more efficiently.
The paper tackles the challenge of merging on-policy and off-policy reinforcement learning to reduce sample complexity, introducing P3O, which interleaves updates without extra hyper-parameters and shows effectiveness in reducing sample complexity on Atari-2600 and MuJoCo benchmarks.
On-policy reinforcement learning (RL) algorithms have high sample complexity while off-policy algorithms are difficult to tune. Merging the two holds the promise to develop efficient algorithms that generalize across diverse environments. It is however challenging in practice to find suitable hyper-parameters that govern this trade off. This paper develops a simple algorithm named P3O that interleaves off-policy updates with on-policy updates. P3O uses the effective sample size between the behavior policy and the target policy to control how far they can be from each other and does not introduce any additional hyper-parameters. Extensive experiments on the Atari-2600 and MuJoCo benchmark suites show that this simple technique is effective in reducing the sample complexity of state-of-the-art algorithms. Code to reproduce experiments in this paper is at https://github.com/rasoolfa/P3O.