AI Paper Atlas

Research map / Reinforcement learning / Visual and representation RL

LESSON: Learning to Integrate Exploration Strategies for Reinforcement Learning via an Option Framework

Woojun Kim, Jeonghye Kim, Youngchul Sung

ICML 2023 · Reinforcement learning › Visual and representation RL · approach: Hierarchical skills and priors · 0 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
Adaptively integrate greedy, random, temporally extended random, and intrinsic-reward exploration policies using an option frameworkDQN-based reinforcement learning · MiniGrid and Atari 2600 environmentsperformanceImproved
Replace adaptive selection with equal-probability selection among exploration strategiesDQN exploration · MiniGrid and Atari 2600 environmentsperformanceHurt
Learn options from scratch instead of using predefined intra-policies (ablation)LESSON · MiniGridperformanceHurt
Remove the greedy policy from the intra-policy set (ablation)LESSON · MiniGrid tasksperformanceHurt
Remove the most effective exploration policy for an environment (ablation)LESSON · MiniGrid tasksperformanceHurt
Set the intrinsic-reward coefficient too low (ablation)LESSON behavior policy · Sparse-reward taskslearning speedHurt
Set the intrinsic-reward coefficient too high (ablation)LESSON behavior policy · Tasks with extrinsic rewardslearning speedHurt
Replace the RND-based exploration policy with a PixelCNN pseudo-count policyLESSON · Montezuma's Revengelearning speedImproved
Use a learned mixture of randomness-based and history-based exploration rather than PixelCNN count-based exploration aloneLESSON · Montezuma's RevengeperformanceImproved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy