Stefano Albrecht, Max Taylor-Davies, Sabrina Mccallum, Alessandro Suglia
We lifted 2 functions out of this paper's own repositories and ran 0 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.
| Repository | Role | Ran |
|---|---|---|
| uoe-agents/feedback-dt | canonical | 0 of 2 |
| Function | Status | Where it lives |
|---|---|---|
| get_file_path | Not yet run | uoe-agents/feedback-dt/src/dataset/minari_storage.py pointer only (licence: NONE) · get_code("c3a9c026710e6419") |
| name_dataset | Not yet run | uoe-agents/feedback-dt/src/dataset/minari_storage.py pointer only (licence: NONE) · get_code("83ace4fccfc2f2f7") |
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
Despite numerous successes, the field of reinforcement learning (RL) remains far from matching the impressive generalisation power of human behaviour learning. One possible way to help bridge this gap be to provide RL agents with richer, more human-like feedback expressed in natural language. To investigate this idea, we first extend BabyAI to automatically generate language feedback from the environment dynamics and goal condition success. Then, we modify the Decision Transformer architecture to take advantage of this additional signal. We find that training with language feedback either in place of or in addition to the return-to-go or goal descriptions improves agents' generalisation performance, and that agents can benefit from feedback even when this is only available during training, but not at inference. 1
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2312.04736")
get_code_for_paper("2312.04736")
have("2312.04736")
Connect an agent — have() is free.