Benchmarking Deep Reinforcement Learning for Continuous Control
This work addresses the problem of quantifying progress in continuous control for researchers, providing a common benchmark to facilitate reproducibility and adoption, though it is incremental as it builds on existing methods by standardizing evaluation.
The authors tackled the lack of a standardized benchmark for evaluating deep reinforcement learning in continuous control tasks, resulting in a comprehensive benchmark suite that includes diverse tasks like cart-pole swing-up and 3D humanoid locomotion, with findings from systematic algorithm evaluations.
Recently, researchers have made significant progress combining the advances in deep learning for learning feature representations with reinforcement learning. Some notable examples include training agents to play Atari games based on raw pixel data and to acquire advanced manipulation skills using raw sensory inputs. However, it has been difficult to quantify progress in the domain of continuous control due to the lack of a commonly adopted benchmark. In this work, we present a benchmark suite of continuous control tasks, including classic tasks like cart-pole swing-up, tasks with very high state and action dimensionality such as 3D humanoid locomotion, tasks with partial observations, and tasks with hierarchical structure. We report novel findings based on the systematic evaluation of a range of implemented reinforcement learning algorithms. Both the benchmark and reference implementations are released at https://github.com/rllab/rllab in order to facilitate experimental reproducibility and to encourage adoption by other researchers.