AI Paper Atlas

Research map / Reinforcement learning / Visual and representation RL

FinRL-Meta: Market Environments and Benchmarks for Data-Driven Financial Reinforcement Learning

NeurIPS 2022 · Reinforcement learning › Visual and representation RL · approach: Task structure and curricula for meta-RL · 48 citations (OpenAlex)

Read the paperCheck your idea against 108,967 papers

AI-extracted summary. Written by AI from the paper's title only (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
combine PPO, A2C and DDPG into a rolling-window ensemble agent instead of single agentsDRL stock trading agent · DJIA stock trading 2020/07/01-2022/03/31Sharpe ratio: 1.37 -> 1.53 vs best single agent A2CHelped
ensemble vs DJIA index buy-and-holdEnsemble agent · DJIA stock trading 2020/07/01-2022/03/31annual return: 19.7% -> 25.9%Helped
ensemble vs DJIA index on drawdownEnsemble agent · DJIA stock trading 2020/07/01-2022/03/31max drawdown: -11.3% -> -11.4%No clear effect
single PPO or DDPG agent vs DJIA indexPPO/DDPG · DJIA stock trading 2020/07/01-2022/03/31Sharpe ratio: 1.32 -> 0.99 (PPO), 0.88 (DDPG)Hurt

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy