# Exploring CausalWorld: Enhancing robotic manipulation via knowledge transfer and curriculum learning

arXiv: https://arxiv.org/abs/2403.17266 · HTML: https://mlsanity.com/paper/2403.17266/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Placed in RL for robot locomotion and manipulation, one of 15 directions in Deep reinforcement learning methods.
- Builds on 27 of its 41 references that are in the map.
- First posted on arXiv 25 Mar 2024.

## Placed in

- Deep reinforcement learning methods / [RL for robot locomotion and manipulation](https://mlsanity.com/deeprl/rl-for-robot-locomotion-and-manipulation/)

## Builds on (most cited first, 27 of 27)

- [Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor](https://mlsanity.com/paper/1801.01290/) (2018)
- [Addressing Function Approximation Error in Actor-Critic Methods](https://mlsanity.com/paper/1802.09477/) (2018)
- [Do As I Can, Not As I Say: Grounding Language in Robotic Affordances](https://mlsanity.com/paper/2204.01691/) (2022)
- [CURL: Contrastive Unsupervised Representations for Reinforcement Learning](https://mlsanity.com/paper/2004.04136/) (2020)
- [Curriculum Learning for Reinforcement Learning Domains: A Framework and Survey](https://mlsanity.com/paper/2003.04960/) (2020)
- [Deep Reinforcement Learning for Robotic Manipulation with Asynchronous Off-Policy Updates](https://mlsanity.com/paper/1610.00633/) (2016)
- [Learning Hand-Eye Coordination for Robotic Grasping with Deep Learning and Large-Scale Data Collection](https://mlsanity.com/paper/1603.02199/) (2016)
- [Transfer Learning in Deep Reinforcement Learning: A Survey](https://mlsanity.com/paper/2009.07888/) (2020)
- [CausalWorld: A Robotic Manipulation Benchmark for Causal Structure and Transfer Learning](https://mlsanity.com/paper/2010.04296/) (2020)
- [Sim-to-Real Robot Learning from Pixels with Progressive Nets](https://mlsanity.com/paper/1610.04286/) (2016)
- [CoPhy: Counterfactual Learning of Physical Dynamics](https://mlsanity.com/paper/1909.12000/) (2019)
- [Causal Curiosity: RL Agents Discovering Self-supervised Experiments for Causal Representation Learning](https://mlsanity.com/paper/2010.03110/) (2020)
- [Self-Paced Deep Reinforcement Learning](https://mlsanity.com/paper/2004.11812/) (2020)
- [An Investigation into Pre-Training Object-Centric Representations for Reinforcement Learning](https://mlsanity.com/paper/2302.04419/) (2023)
- [Transferring Dexterous Manipulation from GPU Simulation to a Remote Real-World TriFinger](https://mlsanity.com/paper/2108.09779/) (2021)
- [Deep Reinforcement Learning for the Control of Robotic Manipulation: A Focussed Mini-Review](https://mlsanity.com/paper/2102.04148/) (2021)
- [Generalizing Goal-Conditioned Reinforcement Learning with Variational Causal Reasoning](https://mlsanity.com/paper/2207.09081/) (2022)
- [Stable and Safe Reinforcement Learning via a Barrier-Lyapunov Actor-Critic Approach](https://mlsanity.com/paper/2304.04066/) (2023)
- [Guided Curriculum Learning for Walking Over Complex Terrain](https://mlsanity.com/paper/2010.03848/) (2020)
- [An Optimization Framework for Task Sequencing in Curriculum Learning](https://mlsanity.com/paper/1901.11478/) (2019)
- [Multi-modal Facial Action Unit Detection with Large Pre-trained Models for the 5th Competition on Affective Behavior Analysis in-the-wild](https://mlsanity.com/paper/2303.10590/) (2023)
- [Causal Counterfactuals for Improving the Robustness of Reinforcement Learning](https://mlsanity.com/paper/2211.05551/) (2022)
- [Automatic Curriculum Learning with Gradient Reward Signals](https://mlsanity.com/paper/2312.13565/) (2023)
- [Stable and Safe Human-aligned Reinforcement Learning through Neural Ordinary Differential Equations](https://mlsanity.com/paper/2401.13148/) (2024)
- [End-to-end Reinforcement Learning of Robotic Manipulation with Robust Keypoints Representation](https://mlsanity.com/paper/2202.06027/) (2022)
- [Human Decision Makings on Curriculum Reinforcement Learning with Difficulty Adjustment](https://mlsanity.com/paper/2208.02932/) (2022)
- [Knowledge Engineering Within A Generalized Bayesian Framework](https://mlsanity.com/paper/1304.3076/) (2013)

## Built on by (most cited first, 2 of 2)

- [Moir'eXNet: Adaptive Multi-Scale Demoir'eing with Linear Attention Test-Time Training and Truncated Flow Matching Prior](https://mlsanity.com/paper/2506.15929/) (2025)
- [Knowledge capture, adaptation and composition (KCAC): A framework for cross-task curriculum learning in robotic manipulation](https://mlsanity.com/paper/2505.10522/) (2025)

## Abstract (arXiv)

This study explores a learning-based tri-finger robotic arm manipulating task, which requires complex movements and coordination among the fingers. By employing reinforcement learning, we train an agent to acquire the necessary skills for proficient manipulation. To enhance the efficiency and effectiveness of the learning process, two knowledge transfer strategies, fine-tuning and curriculum learning, were utilized within the soft actor-critic architecture. Fine-tuning allows the agent to leverage pre-trained knowledge and adapt it to new tasks. Several variations like model transfer, policy transfer, and across-task transfer were implemented and evaluated. To eliminate the need for pretraining, curriculum learning decomposes the advanced task into simpler, progressive stages, mirroring how humans learn. The number of learning stages, the context of the sub-tasks, and the transition timing were found to be the critical design parameters. The key factors of two learning strategies and corresponding effects were explored in context-aware and context-unaware scenarios, enabling us to identify the scenarios where the methods demonstrate optimal performance, derive conclusive insights, and contribute to a broader range of learning-based engineering applications.