TAAC: Temporally Abstract Actor-Critic for Continuous Control

Abstract

We present temporally abstract actor-critic (TAAC), a simple but effective off-policy RL algorithm that incorporates closed-loop temporal abstraction into the actor-critic framework. TAAC adds a second-stage binary policy to choose between the previous action and a new action output by an actor. Crucially, its "act-or-repeat" decision hinges on the actually sampled action instead of the expected behavior of the actor. This post-acting switching scheme let the overall policy make more informed decisions. TAAC has two important features: a) persistent exploration, and b) a new compare-through Q operator for multi-step TD backup, specially tailored to the action repetition scenario. We demonstrate TAAC's advantages over several strong baselines across 14 continuous control tasks. Our surprising finding reveals that while achieving top performance, TAAC is able to "mine" a significant number of repeated actions with the trained policy even on continuous tasks whose problem structures on the surface seem to repel action repetition. This suggests that aside from encouraging persistent exploration, action repetition can find its place in a good policy behavior. Code is available at https://github.com/hnyu/taac.

arXiv commentNeurIPS 2021 camera-ready version

References in corpus (17)

• Continuous control with deep reinforcement learning
• Trust Region Policy Optimization
• Soft Actor-Critic Algorithms and Applications
• Hindsight Experience Replay
• Learning by Playing - Solving Sparse Reward Tasks from Scratch
• FeUdal Networks for Hierarchical Reinforcement Learning
• Data-Efficient Hierarchical Reinforcement Learning
• Multi-Goal Reinforcement Learning: Challenging Robotics Environments and Request for Research
• Parametrized Deep Q-Networks Learning: Reinforcement Learning with Discrete-Continuous Hybrid Action Space
• Learning Multi-Level Hierarchies with Hindsight
• Relative Entropy Regularized Policy Iteration
• Discrete and Continuous Action Representation for Practical RL in Video Games
• Learning to Repeat: Fine Grained Action Repetition for Deep Reinforcement Learning
• Hierarchical Reinforcement Learning By Discovering Intrinsic Options
• Hybrid Actor-Critic Reinforcement Learning in Parameterized Action Space
• Towards Automatic Actor-Critic Solutions to Continuous Control
• Addressing Action Oscillations through Learning Policy Inertia

Cited by in corpus (1)

• Towards Automatic Actor-Critic Solutions to Continuous Control