We lifted 7 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 |
|---|---|---|
| adaptive-rl/adarl-code | canonical | 0 of 7 |
| Function | Status | Where it lives |
|---|---|---|
| default_hps | Not yet run | adaptive-rl/adarl-code/utils/misc/hyper_params.py code served (permissive licence) · get_code("4bcd115491915109") |
| encode_batch | Not yet run | adaptive-rl/adarl-code/utils/misc/data_handler.py code served (permissive licence) · get_code("ca982b5a7e036ad1") |
| encode_obs | Not yet run | adaptive-rl/adarl-code/utils/policy/extract.py code served (permissive licence) · get_code("e2eff668b62a975c") |
| env_init | Not yet run | adaptive-rl/adarl-code/utils/misc/env_init.py code served (permissive licence) · get_code("1902625ea14d31a5") |
| extract_theta | Not yet run | adaptive-rl/adarl-code/utils/policy/extract.py code served (permissive licence) · get_code("4ec49be2c9c0cd3d") |
| load_raw_data_list | Not yet run | adaptive-rl/adarl-code/utils/misc/data_handler.py code served (permissive licence) · get_code("b1ad350eba285138") |
| next_batch | Not yet run | adaptive-rl/adarl-code/utils/misc/data_handler.py code served (permissive licence) · get_code("8071583e658235f1") |
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
One practical challenge in reinforcement learning (RL) is how to make quick adaptations when faced with new environments. In this paper, we propose a principled framework for adaptive RL, called \textit{AdaRL}, that adapts reliably and efficiently to changes across domains with a few samples from the target domain, even in partially observable environments. Specifically, we leverage a parsimonious graphical representation that characterizes structural relationships over variables in the RL system. Such graphical representations provide a compact way to encode what and where the changes across domains are, and furthermore inform us with a minimal set of changes that one has to consider for the purpose of policy adaptation. We show that by explicitly leveraging this compact representation to encode changes, we can efficiently adapt the policy to the target domain, in which only a few samples are needed and further policy optimization is avoided. We illustrate the efficacy of AdaRL through a series of experiments that vary factors in the observation, transition, and reward functions for Cartpole and Atari games.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2107.02729")
get_code_for_paper("2107.02729")
have("2107.02729")
Connect an agent — have() is free.