We lifted 3 functions out of this paper's own repositories and ran 3 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 |
|---|---|---|
| copy not recorded | — | 2 of 2 |
| ChristosKap/policy_consolidation | reimplementation | 1 of 1 |
| Function | Status | Where it lives |
|---|---|---|
| constfn | Ran | this paper's copy was not recorded; identical code first harvested from daochenzha/rapid pointer only · get_code("8758308dc6c0727f") |
| sf01 | Ran | this paper's copy was not recorded; identical code first harvested from daochenzha/rapid pointer only · get_code("baf2a28d376d7803") |
| sf012 | Ran | ChristosKap/policy_consolidation/tc.py pointer only (licence: NONE) · get_code("79447120b9dfe9d7") |
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
We propose a method for tackling catastrophic forgetting in deep reinforcement learning that is \textit{agnostic} to the timescale of changes in the distribution of experiences, does not require knowledge of task boundaries, and can adapt in \textit{continuously} changing environments. In our \textit{policy consolidation} model, the policy network interacts with a cascade of hidden networks that simultaneously remember the agent's policy at a range of timescales and regularise the current policy by its own history, thereby improving its ability to learn without forgetting. We find that the model improves continual learning relative to baselines on a number of continuous control tasks in single-task, alternating two-task, and multi-agent competitive self-play settings.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("1902.00255")
get_code_for_paper("1902.00255")
have("1902.00255")
Connect an agent — have() is free.