Fast and Data Efficient Reinforcement Learning from Pixels via Non-Parametric Value Approximation

7 Mar 2022  ·  Alexander Long, Alan Blair, Herke van Hoof ·

We present Nonparametric Approximation of Inter-Trace returns (NAIT), a Reinforcement Learning algorithm for discrete action, pixel-based environments that is both highly sample and computation efficient. NAIT is a lazy-learning approach with an update that is equivalent to episodic Monte-Carlo on episode completion, but that allows the stable incorporation of rewards while an episode is ongoing. We make use of a fixed domain-agnostic representation, simple distance based exploration and a proximity graph-based lookup to facilitate extremely fast execution. We empirically evaluate NAIT on both the 26 and 57 game variants of ATARI100k where, despite its simplicity, it achieves competitive performance in the online setting with greater than 100x speedup in wall-time.

PDF Abstract

Datasets


Results from the Paper


Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Atari Games 100k Atari 100k NAIT Mean Human-Normalized Score 0.362 # 14
Medium Human-Normalized Score 0.312 # 10

Methods


No methods listed for this paper. Add relevant methods here