When to Go, and When to Explore: The Benefit of Post-Exploration in Intrinsic Motivation
Go-Explore achieved breakthrough performance on challenging reinforcement learning (RL) tasks with sparse rewards. The key insight of Go-Explore was that successful exploration requires an agent to first return to an interesting state ('Go'), and only then explore into unknown terrain ('Explore'). We refer to such exploration after a goal is reached as 'post-exploration'. In this paper we present a systematic study of post-exploration, answering open questions that the Go-Explore paper did not answer yet. First, we study the isolated potential of post-exploration, by turning it on and off within the same algorithm. Subsequently, we introduce new methodology to adaptively decide when to post-explore and for how long to post-explore. Experiments on a range of MiniGrid environments show that post-exploration indeed boosts performance (with a bigger impact than tuning regular exploration parameters), and this effect is further enhanced by adaptively deciding when and for how long to post-explore. In short, our work identifies adaptive post-exploration as a promising direction for RL exploration research.
Code (0)
등록된 구현이 없습니다.
Tasks
Reinforcement Learning (RL)Methods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
First Go, then Post-Explore: the Benefits of Post-Exploration in Intrinsic Motivation
Go-Explore achieved breakthrough performance on challenging reinforcement learning (RL) tasks with sparse rewards. The key insight of Go-Explore was that successful exploration requires an agent to first return to an int…
continuous-controlContinuous ControlMuJoCoReinforcement Learning (RL)Hess-MC2: Sequential Monte Carlo Squared using Hessian Information and Second Order Proposals
When performing Bayesian inference using Sequential Monte Carlo (SMC) methods, two considerations arise: the accuracy of the posterior approximation and computational efficiency. To address computational demands, Sequent…
Computational EfficiencyBayesian InferenceAlgorithms for Adaptive Experiments that Trade-off Statistical Analysis with Reward: Combining Uniform Random Assignment and Reward Maximization
Multi-armed bandit algorithms like Thompson Sampling (TS) can be used to conduct adaptive experiments, in which maximizing reward means that data is used to progressively assign participants to more effective arms. Such …
Thompson SamplingLearning latent state representation for speeding up exploration
Exploration is an extremely challenging problem in reinforcement learning, especially in high dimensional state and action spaces and when only sparse rewards are available. Effective representations can indicate which c…
Reinforcement LearningRepresentation LearningOn weighted uncertainty sampling in active learning
This note explores probabilistic sampling weighted by uncertainty in active learning. This method has been previously used and authors have tangentially remarked on its efficacy. The scheme has several benefits: (1) it i…
Active Learning