Kei Ota, Tomoaki Oiki, Devesh Jha, Toshisada Mariyama, Daniel Nikovski
We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
Deep reinforcement learning (RL) algorithms have recently achieved remarkable successes in various sequential decision making tasks, leveraging advances in methods for training large deep networks. However, these methods usually require large amounts of training data, which is often a big problem for real-world applications. One natural question to ask is whether learning good representations for states and using larger networks helps in learning better policies. In this paper, we try to study if increasing input dimensionality helps improve performance and sample efficiency of model-free deep RL algorithms. To do so, we propose an online feature extractor network (OFENet) that uses neural nets to produce good representations to be used as inputs to deep RL algorithms. Even though the high dimensionality of input is usually supposed to make learning of RL agents more difficult, we show that the RL agents in fact learn more efficiently with the high-dimensional representation than with the lower-dimensional state observations. We believe that stronger feature propagation together with larger networks (and thus larger search space) allows RL agents to learn more complex functions of states and thus improves the sample efficiency. Through numerical experiments, we show that the proposed method outperforms several other state-of-the-art algorithms in terms of both sample efficiency and performance.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2003.01629")
get_code_for_paper("2003.01629")
have("2003.01629")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/2003.01629.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/2003.01629)
Connect an agent — have() is free.