AI Paper Atlas

Research map / Reinforcement learning / Visual and representation RL

Continuously Discovering Novel Strategies via Reward-Switching Policy Optimization

Zihan Zhou, Wei Fu, Bingliang Zhang, Yi Wu

ICLR 2022 · Reinforcement learning › Visual and representation RL · approach: Hierarchical skills and priors · 2 citations (OpenAlex)

Read the paper

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
Use trajectory filtering and switch to intrinsic rewards on rejected trajectories (ablation)RSPO · 4-Goals Hardhighest expected returnImproved
Replace trajectory filtering with the soft no-switch objective (ablation)RSPO · 4-Goals Hardhighest expected returnHurt
Remove intrinsic rewards (ablation)RSPO · Monster-Huntdiscovery of distinct Nash equilibriaHurt
Remove reward switching (ablation)RSPO · Monster-Huntdiscovery of distinct Nash equilibriaHurt
Use behavior-driven intrinsic reward only, without reward-driven intrinsic reward (ablation)RSPO · Monster-Huntdiscovery of the optimal Nash equilibriumHurt
Add reward-driven intrinsic reward to behavior-driven exploration (ablation)RSPO · Monster-Huntdiscovery of the optimal Nash equilibriumImproved
Add smoothed switching (ablation)RSPO · Escalationtraining stabilityImproved
Use iterative optimization rather than population-based training with the same intrinsic rewardRSPO · MuJoCopolicy diversityImproved
Set the novelty threshold too low (ablation)RSPO · HumanoidPopulation Diversity: 0.5: 0.604; 1.0: 0.676; 1.5: 0.687; 2.0: 0.748Hurt
Increase the novelty threshold α from 0.5 to 2.0 (ablation)RSPO · HumanoidPopulation Diversity: 0.5: 0.604; 1.0: 0.676; 1.5: 0.687; 2.0: 0.748Improved
Vary behavior-driven intrinsic-reward scale (ablation)RSPO · HumanoidPopulation Diversity: 0.5: 0.640; 1.0: 0.621; 5.0: 0.697; 10.0: 0.697Mixed
Turn off intrinsic rewards (ablation)RSPO · 2m_vs_1zconvergenceHurt

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