SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2403.09930 · ICML · 2024

Quality-Diversity Actor-Critic: Learning High-Performing and Diverse Behaviors via Value and Successor Features Critics

Antoine Cully, Luca Grillotti, Maxence Faldor, Borja González León

arXiv · PDF · Open in the Atlas

Code that ran

We lifted 3 functions out of this paper's own repositories and ran 1 of them in a sandbox. "Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results.

RepositoryRoleRan
adaptive-intelligent-robotics/QDAC canonical 1 of 3
FunctionStatusWhere it lives
get_override_config Ran adaptive-intelligent-robotics/QDAC/main_qdac_mb.py
code served (permissive licence) · get_code("88ea68f4b60a6c90")
get_act Not yet run adaptive-intelligent-robotics/QDAC/dreamerv3/nets.py
code served (permissive licence) · get_code("03dd934385b4d240")
load_repertoire_ppga Not yet run adaptive-intelligent-robotics/QDAC/main_adaptation_wall.py
code served (permissive licence) · get_code("bc0b8932775f840b")

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

A key aspect of intelligence is the ability to demonstrate a broad spectrum of behaviors for adapting to unexpected situations. Over the past decade, advancements in deep reinforcement learning have led to groundbreaking achievements to solve complex continuous control tasks. However, most approaches return only one solution specialized for a specific problem. We introduce Quality-Diversity Actor-Critic (QDAC), an offpolicy actor-critic deep reinforcement learning algorithm that leverages a value function critic and a successor features critic to learn high-performing and diverse behaviors. In this framework, the actor optimizes an objective that seamlessly unifies both critics using constrained optimization to (1) maximize return, while (2) executing diverse skills. Compared with other Quality-Diversity methods, QDAC achieves significantly higher performance and more diverse behaviors on six challenging continuous control locomotion tasks. We also demonstrate that we can harness the learned skills to adapt better than other baselines to five perturbed environments. Finally, qualitative analyses showcase a range of remarkable behaviors: adaptive-intelligent-robotics.github.io/QDAC.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2403.09930")
get_code_for_paper("2403.09930")
have("2403.09930")

Connect an agent — have() is free.