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.
When an agent cannot represent a perfectly accurate model of its environment's dynamics, model-based reinforcement learning (MBRL) can fail catastrophically. Planning involves composing the predictions of the model; when flawed predictions are composed, even minor errors can compound and render the model useless for planning. Hallucinated Replay (Talvitie 2014) trains the model to "correct" itself when it produces errors, substantially improving MBRL with flawed models. This paper theoretically analyzes this approach, illuminates settings in which it is likely to be effective or ineffective, and presents a novel error bound, showing that a model's ability to self-correct is more tightly related to MBRL performance than one-step prediction error. These results inspire an MBRL algorithm for deterministic MDPs with performance guarantees that are robust to model class limitations.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("1612.06018")
get_code_for_paper("1612.06018")
have("1612.06018")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/1612.06018.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/1612.06018)
Connect an agent — have() is free.