We lifted 8 functions out of this paper's own repositories and ran 2 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 |
|---|---|---|
| longtermrisk/marltoolbox | pwc_unofficial | 1 of 7 |
| tobiasbaumann1/amd | extension | 1 of 1 |
| Function | Status | Where it lives |
|---|---|---|
| add_env_hp | Ran | tobiasbaumann1/amd/marltoolbox/examples/tune_class_api/amd.py code served (permissive licence) · get_code("5337ea56ed7ba2dd") |
| intprod | Ran | longtermrisk/marltoolbox/marltoolbox/algos/adaptive_mechanism_design/planning_agent.py code served (permissive licence) · get_code("fe097265b3baf872") |
| convert_from_rllib_env_format | Not yet run | longtermrisk/marltoolbox/marltoolbox/algos/adaptive_mechanism_design/agent.py code served (permissive licence) · get_code("6012d34fca2b02f1") |
| convert_to_rllib_env_format | Not yet run | longtermrisk/marltoolbox/marltoolbox/algos/adaptive_mechanism_design/agent.py code served (permissive licence) · get_code("65ec64cc18350329") |
| get_step_log | Not yet run | longtermrisk/marltoolbox/marltoolbox/algos/alternating_offers/logging_utils.py code served (permissive licence) · get_code("62e51c87a4f87750") |
| numel | Not yet run | longtermrisk/marltoolbox/marltoolbox/algos/adaptive_mechanism_design/planning_agent.py code served (permissive licence) · get_code("d5e89c5936ecd7a3") |
| safe_div | Not yet run | longtermrisk/marltoolbox/marltoolbox/algos/alternating_offers/logging_utils.py code served (permissive licence) · get_code("acb5dbef1523670c") |
| var_shape | Not yet run | longtermrisk/marltoolbox/marltoolbox/algos/adaptive_mechanism_design/agent.py code served (permissive licence) · get_code("ccad0a0cb6b5ce17") |
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
In the future, artificial learning agents are likely to become increasingly widespread in our society. They will interact with both other learning agents and humans in a variety of complex settings including social dilemmas. We consider the problem of how an external agent can promote cooperation between artificial learners by distributing additional rewards and punishments based on observing the learners' actions. We propose a rule for automatically learning how to create right incentives by considering the players' anticipated parameter updates. Using this learning rule leads to cooperation with high social welfare in matrix games in which the agents would otherwise learn to defect with high probability. We show that the resulting cooperative outcome is stable in certain games even if the planning agent is turned off after a given number of episodes, while other games require ongoing intervention to maintain mutual cooperation. However, even in the latter case, the amount of necessary additional incentives decreases over time.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("1806.04067")
get_code_for_paper("1806.04067")
have("1806.04067")
Connect an agent — have() is free.