├── Acrobot ├── README ├── acrobot_AIQ_without_entropy.jl ├── acrobot_active_inference.jl ├── acrobot_active_inference_entropy.jl ├── acrobot_active_inference_q_expectation.jl ├── acrobot_active_inference_tmodel.jl ├── acrobot_actor_critic.jl ├── acrobot_q_learning.jl ├── acrobot_standard_policy_gradients.jl └── analysis.jl ├── LunarLander ├── README ├── analysis.jl ├── lunar_lander_active_inference.jl ├── lunar_lander_active_inference_entropy.jl ├── lunar_lander_active_inference_q_expectation.jl ├── lunar_lander_actor_critic.jl ├── lunar_lander_policy_gradient.jl ├── lunar_lander_q_learning.jl └── lunar_lander_tmodel.jl ├── README.md ├── active_inference.jl ├── active_inference_action_specific_Tmodel.jl ├── active_inference_learned_precision.jl ├── active_inference_with_Tmodel.jl ├── active_inference_with_entropy_loss.jl ├── animations.jl ├── animations ├── README ├── acrobot_anim.jl ├── animations.jl ├── cartpole_anim.jl ├── lunar_lander_PG_anim.jl └── lunar_lander_anim.jl ├── cartpole_q_learning.jl ├── off_policy_active_inference.jl ├── results ├── README ├── analysis_2.jl └── prelim_results_analysis.jl └── standard_policy_gradient.jl /Acrobot/README: -------------------------------------------------------------------------------- 1 | 2 | -------------------------------------------------------------------------------- /Acrobot/acrobot_AIQ_without_entropy.jl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/BerenMillidge/DeepActiveInference/HEAD/Acrobot/acrobot_AIQ_without_entropy.jl -------------------------------------------------------------------------------- /Acrobot/acrobot_active_inference.jl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/BerenMillidge/DeepActiveInference/HEAD/Acrobot/acrobot_active_inference.jl -------------------------------------------------------------------------------- /Acrobot/acrobot_active_inference_entropy.jl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/BerenMillidge/DeepActiveInference/HEAD/Acrobot/acrobot_active_inference_entropy.jl -------------------------------------------------------------------------------- /Acrobot/acrobot_active_inference_q_expectation.jl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/BerenMillidge/DeepActiveInference/HEAD/Acrobot/acrobot_active_inference_q_expectation.jl -------------------------------------------------------------------------------- /Acrobot/acrobot_active_inference_tmodel.jl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/BerenMillidge/DeepActiveInference/HEAD/Acrobot/acrobot_active_inference_tmodel.jl -------------------------------------------------------------------------------- /Acrobot/acrobot_actor_critic.jl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/BerenMillidge/DeepActiveInference/HEAD/Acrobot/acrobot_actor_critic.jl -------------------------------------------------------------------------------- /Acrobot/acrobot_q_learning.jl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/BerenMillidge/DeepActiveInference/HEAD/Acrobot/acrobot_q_learning.jl -------------------------------------------------------------------------------- /Acrobot/acrobot_standard_policy_gradients.jl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/BerenMillidge/DeepActiveInference/HEAD/Acrobot/acrobot_standard_policy_gradients.jl -------------------------------------------------------------------------------- /Acrobot/analysis.jl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/BerenMillidge/DeepActiveInference/HEAD/Acrobot/analysis.jl -------------------------------------------------------------------------------- /LunarLander/README: -------------------------------------------------------------------------------- 1 | 2 | -------------------------------------------------------------------------------- /LunarLander/analysis.jl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/BerenMillidge/DeepActiveInference/HEAD/LunarLander/analysis.jl -------------------------------------------------------------------------------- /LunarLander/lunar_lander_active_inference.jl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/BerenMillidge/DeepActiveInference/HEAD/LunarLander/lunar_lander_active_inference.jl -------------------------------------------------------------------------------- /LunarLander/lunar_lander_active_inference_entropy.jl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/BerenMillidge/DeepActiveInference/HEAD/LunarLander/lunar_lander_active_inference_entropy.jl -------------------------------------------------------------------------------- /LunarLander/lunar_lander_active_inference_q_expectation.jl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/BerenMillidge/DeepActiveInference/HEAD/LunarLander/lunar_lander_active_inference_q_expectation.jl -------------------------------------------------------------------------------- /LunarLander/lunar_lander_actor_critic.jl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/BerenMillidge/DeepActiveInference/HEAD/LunarLander/lunar_lander_actor_critic.jl -------------------------------------------------------------------------------- /LunarLander/lunar_lander_policy_gradient.jl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/BerenMillidge/DeepActiveInference/HEAD/LunarLander/lunar_lander_policy_gradient.jl -------------------------------------------------------------------------------- /LunarLander/lunar_lander_q_learning.jl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/BerenMillidge/DeepActiveInference/HEAD/LunarLander/lunar_lander_q_learning.jl -------------------------------------------------------------------------------- /LunarLander/lunar_lander_tmodel.jl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/BerenMillidge/DeepActiveInference/HEAD/LunarLander/lunar_lander_tmodel.jl -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/BerenMillidge/DeepActiveInference/HEAD/README.md -------------------------------------------------------------------------------- /active_inference.jl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/BerenMillidge/DeepActiveInference/HEAD/active_inference.jl -------------------------------------------------------------------------------- /active_inference_action_specific_Tmodel.jl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/BerenMillidge/DeepActiveInference/HEAD/active_inference_action_specific_Tmodel.jl -------------------------------------------------------------------------------- /active_inference_learned_precision.jl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/BerenMillidge/DeepActiveInference/HEAD/active_inference_learned_precision.jl -------------------------------------------------------------------------------- /active_inference_with_Tmodel.jl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/BerenMillidge/DeepActiveInference/HEAD/active_inference_with_Tmodel.jl -------------------------------------------------------------------------------- /active_inference_with_entropy_loss.jl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/BerenMillidge/DeepActiveInference/HEAD/active_inference_with_entropy_loss.jl -------------------------------------------------------------------------------- /animations.jl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/BerenMillidge/DeepActiveInference/HEAD/animations.jl -------------------------------------------------------------------------------- /animations/README: -------------------------------------------------------------------------------- 1 | 2 | -------------------------------------------------------------------------------- /animations/acrobot_anim.jl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/BerenMillidge/DeepActiveInference/HEAD/animations/acrobot_anim.jl -------------------------------------------------------------------------------- /animations/animations.jl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/BerenMillidge/DeepActiveInference/HEAD/animations/animations.jl -------------------------------------------------------------------------------- /animations/cartpole_anim.jl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/BerenMillidge/DeepActiveInference/HEAD/animations/cartpole_anim.jl -------------------------------------------------------------------------------- /animations/lunar_lander_PG_anim.jl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/BerenMillidge/DeepActiveInference/HEAD/animations/lunar_lander_PG_anim.jl -------------------------------------------------------------------------------- /animations/lunar_lander_anim.jl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/BerenMillidge/DeepActiveInference/HEAD/animations/lunar_lander_anim.jl -------------------------------------------------------------------------------- /cartpole_q_learning.jl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/BerenMillidge/DeepActiveInference/HEAD/cartpole_q_learning.jl -------------------------------------------------------------------------------- /off_policy_active_inference.jl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/BerenMillidge/DeepActiveInference/HEAD/off_policy_active_inference.jl -------------------------------------------------------------------------------- /results/README: -------------------------------------------------------------------------------- 1 | 2 | -------------------------------------------------------------------------------- /results/analysis_2.jl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/BerenMillidge/DeepActiveInference/HEAD/results/analysis_2.jl -------------------------------------------------------------------------------- /results/prelim_results_analysis.jl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/BerenMillidge/DeepActiveInference/HEAD/results/prelim_results_analysis.jl -------------------------------------------------------------------------------- /standard_policy_gradient.jl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/BerenMillidge/DeepActiveInference/HEAD/standard_policy_gradient.jl --------------------------------------------------------------------------------