IMOL 2023 presentation: Towards Inferential Social Learning in Teachable Autotelic Agents

Data collection in SB3

Advantage Actor Critic

From Policy Gradient to Actor-Critic: Introduction (RLVS 2021 version)

Policy Gradient and Actor-Critic: wrap-up (RLVS 2021 version)

Policy Gradient and Reward Weighted Regression (RLVS 2021 version)

SAC and TQC (RLVS 2021 version)

DDPG and TD3 (RLVS 2021 version)

Proximal Policy Optimization (RVLS 2021 version)

TRPO and ACKTR (RLVS 2021 version)

On-Policy versus Off-Policy (RLVS 2021 version)

The bias-variance trade-off in Reinforcement Learning (RLVS 2021 version)

From Policy Gradient with baseline to Actor-Critic (RLVS 2021 version)

Policy Gradient Derivation (part 3/3) (RLVS 2021 version)

Policy Gradient Derivation (part 2/3) (RLVS 2021 version)

Policy Gradient derivation (part 1/3) (RLVS 2021 version)

The Policy Search Problem (RLVS 2021 version)

Coding tips for the Basic Policy Gradient lab

Policy Gradient in practice: empirical study of some phenomena

Modern Policy Search: an overview

Radial Basis Function Networks: useful tips for labs

TRPO, ACKTR and PPO (V2)

Dynamic Programming (V2)

Soft Actor Critic (V2)

Advanced Gradient Descent

Advantage Weighted Regression

Hindsight Experience Replay

Policy Gradient Class

Deep Reinforcement Learning Class: Conclusion

Soft Actor Critic