finding

active

finding:active-inference-recovers-performance-within-1-episode-after-context-switch-in-non-stationary-frozenlake-while-bayesian-rl-requires-40-episodes

Active inference recovers performance within 1 episode after context switch in non-stationary FrozenLake, while Bayesian RL requires ~40 episodes.

Figure 4 and discussion in §3.

Source paper

extracted_from

Active inference: demystified and compared

(2021) · Noor Sajid · Philip J. Ball · Thomas Parr · Karl J. Friston

Neighborhood — ranked by edge-count

Claims (1)

claim

Active inference offers an attractive natural adaptation mechanism for non-stationary environments due to its Bayesian model updating properties.
supports
§3, after non-stationary results.

Related by similarity (8)

cosine ≥ 0.65 · no typed edge

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

Active inference and Bayesian model-based RL learn reward-maximizing behavior in <10 episodes in deterministic FrozenLake.finding0.876
Discussion of Figure 3.
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.finding0.865
Key empirical result validating online planning capability of active inference.
Active inference agents engage in information-seeking behavior in reward-free FrozenLake environments, contrasting with Q-learning but similar to Bayesian RL.finding0.839
Empirical demonstration on FrozenLake; shows epistemic value drives exploration absent reward signal.
Active inference achieves Bayes-optimal behavior in non-stationary environments through online belief updating.hypothesis0.820
Tested via FrozenLake experiments; predicts superior performance when environment dynamics change.
Active Inference agent achieved average score 99.88 [99.64, 100.00] in deterministic FrozenLake environment across 200 trials of 500 episodes.finding0.813
Table 1, deterministic environment row.
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.finding0.808
Table 2 first row; reward shaping section.
Bayesian model-based RL achieved average score 99.76 [99.45, 100.00] in deterministic FrozenLake.finding0.801
Table 1.
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.finding0.794
Table 2, row 3, showing equivalence when prior preferences match rewards.