Diversity is All You Need: Learning Skills without a Reward Function

Abstract

Intelligent creatures can explore their environments and learn useful skills without supervision. In this paper, we propose DIAYN ('Diversity is All You Need'), a method for learning useful skills without a reward function. Our proposed method learns skills by maximizing an information theoretic objective using a maximum entropy policy. On a variety of simulated robotic tasks, we show that this simple objective results in the unsupervised emergence of diverse skills, such as walking and jumping. In a number of reinforcement learning benchmark environments, our method is able to learn a skill that solves the benchmark task despite never receiving the true task reward. We show how pretrained skills can provide a good parameter initialization for downstream tasks, and can be composed hierarchically to solve complex, sparse reward tasks. Our results suggest that unsupervised discovery of skills can serve as an effective pretraining mechanism for overcoming challenges of exploration and data efficiency in reinforcement learning.

Videos and code for our experiments are available at: https://sites.google.com/view/diayn

Cited by in corpus (21)

• A Survey of Zero-shot Generalisation in Deep Reinforcement Learning
• COBRA: Data-Efficient Model-Based RL through Unsupervised Object Discovery and Curiosity-Driven Exploration
• Planning to Explore via Self-Supervised World Models
• Contingency-Aware Exploration in Reinforcement Learning
• GeneraLight: Improving Environment Generalization of Traffic Signal Control via Meta Reinforcement Learning
• Quantifying the effects of environment and population diversity in multi-agent reinforcement learning
• Structure in Deep Reinforcement Learning: A Survey and Open Problems
• Self-Supervised Exploration via Disagreement
• Transforming task representations to perform novel tasks
• VFunc: a Deep Generative Model for Functions
• Skill Disentanglement for Imitation Learning from Suboptimal Demonstrations
• Reinforcement Learning by Guided Safe Exploration
• Disentangled Cumulants Help Successor Representations Transfer to New Tasks
• Disentangling causal effects for hierarchical reinforcement learning
• Autonomous learning and chaining of motor primitives using the Free Energy Principle
• PBCS : Efficient Exploration and Exploitation Using a Synergy between Reinforcement Learning and Motion Planning
• Pre-trained Word Embeddings for Goal-conditional Transfer Learning in Reinforcement Learning
• Being curious about the answers to questions: novelty search with learned attention
• On the Possibility of Rewarding Structure Learning Agents: Mutual Information on Linguistic Random Sets
• Hindsight Reward Tweaking via Conditional Deep Reinforcement Learning
• Reinforcement Learning for Robust Missile Autopilot Design