Under reward shaping (G=100, H=-100, F=0), Active Inference scored 99.52, Bayesian RL 99.77, Q-learning 95.56, with nearly identical behavior between belief-based agents.

Entities in the same semantic neighborhood but without a typed relation to this one — candidates for new edges or unrecognized duplicates.

• In the absence of prior preferences, Active Inference null model and Bayesian RL maintain exploration with average scores of 44.00 and 39.94 respectively, whereas Q-learning does not explore.finding0.862
  Table 2 first row; reward shaping section.
• Active inference agents engage in information-seeking behavior in reward-free FrozenLake environments, contrasting with Q-learning but similar to Bayesian RL.finding0.836
  Empirical demonstration on FrozenLake; shows epistemic value drives exploration absent reward signal.
• Active inference agents can learn their own reward function (prior preferences) by interacting with the environment, bypassing the need for an explicit reward signal.claim0.821
  Abstract and §3, preference learning section.
• Active inference and Bayesian model-based RL learn reward-maximizing behavior in <10 episodes in deterministic FrozenLake.finding0.818
  Discussion of Figure 3.
• Active Inference agent achieved average score 99.88 [99.64, 100.00] in deterministic FrozenLake environment across 200 trials of 500 episodes.finding0.818
  Table 1, deterministic environment row.
• In active inference, reward can simply be treated as another observation we have a preference over, rather than a special signal.claim0.816
  Abstract; central distinction.
• All three agent types (active inference, Q-learning, Bayesian RL) perform adequately in stationary FrozenLake; only active inference achieves Bayes-optimal behavior in non-stationary settings.finding0.808
  Key empirical result validating online planning capability of active inference.
• Active Inference null model (no prior preferences) achieved average score 50.03 [49.70, 50.35] in deterministic FrozenLake.finding0.806
  Table 1.