Deep Curiosity Search: Intra-Life Exploration Can Improve Performance on Challenging Deep Reinforcement Learning Problems

TL;DR

Deep Curiosity Search (DeepCS) enhances reinforcement learning by promoting intra-life exploration, leading to improved performance on challenging sparse- and dense-reward games, surpassing or matching state-of-the-art methods.

Contribution

DeepCS introduces intra-life exploration rewards, a novel approach that improves performance across various challenging RL environments compared to prior across-training novelty methods.

Findings

DeepCS matches state-of-the-art on Montezuma's Revenge.

DeepCS doubles A2C performance on Seaquest.

DeepCS improves exploration on multiple hard games.

Abstract

Traditional exploration methods in RL require agents to perform random actions to find rewards. But these approaches struggle on sparse-reward domains like Montezuma's Revenge where the probability that any random action sequence leads to reward is extremely low. Recent algorithms have performed well on such tasks by encouraging agents to visit new states or perform new actions in relation to all prior training episodes (which we call across-training novelty). But such algorithms do not consider whether an agent exhibits intra-life novelty: doing something new within the current episode, regardless of whether those behaviors have been performed in previous episodes. We hypothesize that across-training novelty might discourage agents from revisiting initially non-rewarding states that could become important stepping stones later in training. We introduce Deep Curiosity Search (DeepCS), which encourages intra-life exploration by rewarding agents for visiting as many different states as possible within each episode, and show that DeepCS matches the performance of current state-of-the-art methods on Montezuma's Revenge. We further show that DeepCS improves exploration on Amidar, Freeway, Gravitar, and Tutankham (many of which are hard exploration games). Surprisingly, DeepCS doubles A2C performance on Seaquest, a game we would not have expected to benefit from intra-life exploration because the arena is small and already easily navigated by naive exploration techniques. In one run, DeepCS achieves a maximum training score of 80,000 points on Seaquest, higher than any methods other than Ape-X. The strong performance of DeepCS on these sparse- and dense-reward tasks suggests that encouraging intra-life novelty is an interesting, new approach for improving performance in Deep RL and motivates further research into hybridizing across-training and intra-life exploration methods.