Research map / Reinforcement learning / Visual and representation RL
CausalWorld: A Robotic Manipulation Benchmark for Causal Structure and Transfer Learning
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 |
|---|---|---|---|
| Randomize goal position and orientation each episode instead of keeping the default task fixed | CausalWorld pushing agents · Pushing, goal-pose evaluation (P5) | fractional success | Helped |
| Train with full randomization of all task variables instead of a fixed task | CausalWorld pushing agents · Pushing, training environments | fractional success | Hurt |
| Train on a fixed default task | CausalWorld pushing agents · Pushing, initial-pose evaluation (P4) | fractional success | Helped |
| Train on a fixed default task rather than randomizing goal poses | CausalWorld pushing agents · Pushing, goal-pose evaluation (P5) | fractional success | Hurt |
| Use a hand-designed dense reward instead of sparse reward only | PPO, SAC, and TD3 in CausalWorld · Pushing, Picking, Pick and Place, and Stacking2 | fractional success | Helped |
| Train model-free RL methods on single-block tasks | PPO, SAC, and TD3 in CausalWorld · Pushing, Picking, and Pick and Place | fractional success | Helped |
| Train model-free RL methods on two-block stacking | PPO, SAC, and TD3 in CausalWorld · Stacking2 | fractional success | Hurt |
Closest papers by meaning
- GravMAD: Grounded Spatial Value Maps Guided Action Diffusion for Generalized 3D Manipulation (ICLR 2025 · similarity 0.89)
- Multi-Stage Manipulation with Demonstration-Augmented Reward, Policy, and World Model Learning (ICML 2025 · similarity 0.88)
- Rapidly Adapting Policies to the Real-World via Simulation-Guided Fine-Tuning (ICLR 2025 · similarity 0.88)
- Dream to Manipulate: Compositional World Models Empowering Robot Imitation Learning with Imagination (ICLR 2025 · similarity 0.88)
- Generalizable Domain Adaptation for Sim-and-Real Policy Co-Training (NeurIPS 2025 · similarity 0.88)
- Self-Improving Embodied Foundation Models (NeurIPS 2025 · 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.