Never Give Up: Learning Directed Exploration Strategies

We propose a reinforcement learning agent to solve hard exploration games by learning a range of directed exploratory policies. We construct an episodic memory-based intrinsic reward using k-nearest neighbors over the agent's recent experience to train the directed exploratory policies, thereby...

Full description

Saved in:
Bibliographic Details
Published in:arXiv.org 2020-02
Main Authors: Adrià Puigdomènech Badia, Sprechmann, Pablo, Vitvitskyi, Alex, Guo, Daniel, Piot, Bilal, Kapturowski, Steven, Tieleman, Olivier, Arjovsky, Martín, Pritzel, Alexander, Bolt, Andew, Blundell, Charles
Format: Article
Language:English
Subjects:
Algorithms
Exploitation
Exploration
Game theory
Games
Inverse dynamics
Machine learning
Neural networks
Policies
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:We propose a reinforcement learning agent to solve hard exploration games by learning a range of directed exploratory policies. We construct an episodic memory-based intrinsic reward using k-nearest neighbors over the agent's recent experience to train the directed exploratory policies, thereby encouraging the agent to repeatedly revisit all states in its environment. A self-supervised inverse dynamics model is used to train the embeddings of the nearest neighbour lookup, biasing the novelty signal towards what the agent can control. We employ the framework of Universal Value Function Approximators (UVFA) to simultaneously learn many directed exploration policies with the same neural network, with different trade-offs between exploration and exploitation. By using the same neural network for different degrees of exploration/exploitation, transfer is demonstrated from predominantly exploratory policies yielding effective exploitative policies. The proposed method can be incorporated to run with modern distributed RL agents that collect large amounts of experience from many actors running in parallel on separate environment instances. Our method doubles the performance of the base agent in all hard exploration in the Atari-57 suite while maintaining a very high score across the remaining games, obtaining a median human normalised score of 1344.0%. Notably, the proposed method is the first algorithm to achieve non-zero rewards (with a mean score of 8,400) in the game of Pitfall! without using demonstrations or hand-crafted features.
ISSN:2331-8422