Alchemy: A Benchmark And Analysis Toolkit For Meta-reinforcement Learning Agents

Abstract

There has been rapidly growing interest in meta-learning as a method for increasing the flexibility and sample efficiency of reinforcement learning. One problem in this area of research, however, has been a scarcity of adequate benchmark tasks. In general, the structure underlying past benchmarks has either been too simple to be inherently interesting, or too ill-defined to support principled analysis. In the present work, we introduce a new benchmark for meta-RL research, emphasizing transparency and potential for in-depth analysis as well as structural richness. Alchemy is a 3D video game, implemented in Unity, which involves a latent causal structure that is resampled procedurally from episode to episode, affording structure learning, online inference, hypothesis testing and action sequencing based on abstract domain knowledge. We evaluate a pair of powerful RL agents on Alchemy and present an in-depth analysis of one of these agents. Results clearly indicate a frank and specific fa

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keywang2021alchemy

Related papers

• Fightladder: A Benchmark For Competitive Multi-agent Reinforcement Learning (2024)0.00
• On The Effectiveness Of Fine-tuning Versus Meta-reinforcement Learning (2022)0.00
• First-explore, Then Exploit: Meta-learning To Solve Hard Exploration-exploitation Trade-offs (2023)0.00
• A Tutorial On Meta-reinforcement Learning (2023)10.85
• RL\(^3\): Boosting Meta Reinforcement Learning Via RL Inside RL\(^2\) (2023)0.00
• Massively Multiagent Minigames For Training Generalist Agents (2024)0.00
• Simplified Action Decoder For Deep Multi-agent Reinforcement Learning (2019)4.03
• Toybox: Better Atari Environments For Testing Reinforcement Learning Agents (2018)0.00