Research map / Reinforcement learning / Visual and representation RL
Deriving Subgoals Autonomously to Accelerate Learning in Sparse Reward Domains
Michael Dann, Fabio Zambetta, John Thangarajah
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 changed | Where | Measured | Effect |
|---|---|---|---|
| add pellet intrinsic rewards from derived subgoal partitions (ablation) | DQN · Montezuma's Revenge | score: 0 -> 2,500 | Improved |
| add pellet intrinsic rewards (ablation) | DQN · Venture | average score | Improved |
| add pellet intrinsic rewards (ablation) | DQN · Freeway | average score: 33.3 -> 33.4 | Mixed |
| add pellet intrinsic rewards (ablation) | DQN · Battlezone and Robot Tank | score | No clear effect |
| fix epsilon=1 after 500 rewardless actions (improved baseline exploration) | DQN baseline · Venture | average score | Improved |
Closest papers by meaning
- Redeeming intrinsic rewards via constrained optimization (NeurIPS 2022 · similarity 0.88)
- DISCOVER: Automated Curricula for Sparse-Reward Reinforcement Learning (NeurIPS 2025 · similarity 0.87)
- On Learning Intrinsic Rewards for Policy Gradient Methods (NeurIPS 2018 · similarity 0.87)
- On Bonus Based Exploration Methods In The Arcade Learning Environment (ICLR 2020 · similarity 0.87)
- Successor-Predecessor Intrinsic Exploration (NeurIPS 2023 · similarity 0.87)
- Action-Dependent Optimality-Preserving Reward Shaping (ICML 2025 · similarity 0.87)
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.
