Research map / Reinforcement learning / MDPs and planning
Exploration Conscious Reinforcement Learning Revisited
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 |
|---|---|---|---|
| Optimize the policy for ε-greedy exploration rather than the standard optimality criterion | DDQN · Atari test games | reward: Breakout: 402 -> 390; FishingDer: -37 -> -3; Frostbite: 1720 -> 2686; Qbert: 15627 -> 16082; Riverraid: 9049 -> 12846 | Mixed |
| Optimize the policy for Gaussian exploration noise | DDPG · MuJoCo train tasks | reward: Ant: 809 -> 1013; HalfCheetah: 2255 -> 3848; Hopper: 1864 -> 2566; Humanoid: 1281 -> 1703; InPendulum: 694 -> 998; Walke | Helped |
| Optimize the policy for Gaussian exploration noise | DDPG · MuJoCo test tasks | reward: Ant: 1611 -> 1924; HalfCheetah: 2729 -> 4579; Hopper: 3099 -> 3071; Humanoid: 1688 -> 2154; InPendulum: 999 -> 1000; Wal | Mixed |
| Use the surrogate rather than expected exploration-conscious update | α-DDQN · Atari train and test games | reward: Breakout test: 390 -> 392; FishingDer test: -19 -> -3; Frostbite test: 1638 -> 2686; Qbert test: 15780 -> 16082; Riverra | Mixed |
| Use the surrogate rather than expected exploration-conscious update | σ-DDPG · MuJoCo train and test tasks | reward: Ant train: 1013 -> 993; HalfCheetah train: 2634 -> 3848; Hopper train: 1866 -> 2566; Humanoid train: 1416 -> 1703; InPen | Mixed |
Closest papers by meaning
- Model-Free Active Exploration in Reinforcement Learning (NeurIPS 2023 · similarity 0.90)
- Reward-Free Exploration for Reinforcement Learning (ICML 2020 · similarity 0.89)
- Beyond Optimism: Exploration With Partially Observable Rewards (NeurIPS 2024 · similarity 0.89)
- Exploration in Reinforcement Learning with Deep Covering Options (ICLR 2020 · similarity 0.89)
- Decoupling Exploration and Policy Optimization: Uncertainty Guided Tree Search for Hard Exploration (NeurIPS 2026 · similarity 0.88)
- Bayesian Exploration Networks (ICML 2024 · similarity 0.88)
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.