policy
An agent's strategy for choosing what to do in a given situation; one of the four components of the base agent model.
As defined in Richard Sutton – Father of RL thinks LLMs are a dead end
Where it comes up · 4
- Rich Sutton, The OaK Architecture: A Vision of SuperIntelligence from Experience - RLC 20258 claims
- Richard Sutton – Father of RL thinks LLMs are a dead end3 claims
- Richard Sutton – Father of RL thinks LLMs are a dead end2 claims
- Metas AI Boss Says He DONE With LLMS...2 claims
Most important claims · 10 of 15Search all claims for “policy” →
- The base common model of the agent has four parts: a policy (what to do in the current situation), a value function (learned via TD learning, producing a number for how well things are going used to adjust the policy), a perception/state-representation component, and a transition model of the world (belief about consequences of actions, learned richly from all sensation, not just reward).Richard Sutton – Father of RL thinks LLMs are a dead end
- A basic model of an agent has four parts: a policy that says what to do in a situation, a value function that is learned with TD learning and produces a number about how well it's going, a perception component that constructs state representation, and a transition model of the world that represents what will happen if you take an action.Richard Sutton – Father of RL thinks LLMs are a dead end
- Repeated successful accomplishment of a task gradually compiles System 2 reasoning into System 1 reactive policies, allowing automatic execution without planning.Metas AI Boss Says He DONE With LLMS...
- An option is a pair consisting of a policy (way of behaving) and a termination function (decision to stop behaving), and the agent learns what happens when it follows each option to form a high-level transition model that enables planning with larger temporal jumpsRich Sutton, The OaK Architecture: A Vision of SuperIntelligence from Experience - RLC 2025
- Anything that can be learned can also be planned—general value functions used to learn models and values can equally be used to plan, because planning just applies value iteration to a different set of states, meaning there is mathematical unity across learning and planningRich Sutton, The OaK Architecture: A Vision of SuperIntelligence from Experience - RLC 2025
- Current AI systems have System 1 (reactive) capabilities and are only beginning to develop System 2 (planning and reasoning), but achieving true System 2 reasoning requires a fundamentally different architecture from current LLM-based approaches.Metas AI Boss Says He DONE With LLMS...
- The subproblem is to maximize the expected sum of rewards received while following an option plus a reward-weighted contribution of the feature value at termination, minus any penalty from bad terminal states, creating a trade-off between feature attainment and reward preservation.Rich Sutton, The OaK Architecture: A Vision of SuperIntelligence from Experience - RLC 2025
- A reward-respecting sub-problem of feature attainment takes a feature index i, a kappa parameter (intensity of wanting that feature), and creates a problem to drive the world to a state where the feature is high without losing too much main reward, formalized as a policy and termination function that maximize cumulative reward plus the feature value at terminationRich Sutton, The OaK Architecture: A Vision of SuperIntelligence from Experience - RLC 2025
- The big world perspective states that the world is much larger and more complex than the agent—containing billions of other agents and countless atomic details—making it impossible for the agent to hold complete world knowledge, thereby necessitating approximate value functions, policies, and transition modelsRich Sutton, The OaK Architecture: A Vision of SuperIntelligence from Experience - RLC 2025
- The base common model of an agent has four parts: a policy (what to do in the current situation), a value function (a learned number indicating how well things are going, used to adjust the policy), a perception component (constructing the state representation), and a transition model of the world (predicting the consequences of actions), the last of which is learned richly from all sensation rather than from reward.Richard Sutton – Father of RL thinks LLMs are a dead end