mcmachado / count_based_exploration_sr
☆29Updated 5 years ago
Related projects: ⓘ
- Options of Interest: Temporal Abstraction with Interest Functions AAAI 2020☆25Updated 4 years ago
- Option Critic with subgoal discovery by spectral decomposition of the Successor Features Matrix or clustering in Successor features space…☆23Updated 5 years ago
- This code implements Prioritized Level Replay, a method for sampling training levels for reinforcement learning agents that exploits the …☆83Updated 3 years ago
- Efficient Exploration via State Marginal Matching (2019)☆66Updated 5 years ago
- Learning Laplacian Representations in Reinforcement Learning☆17Updated 3 years ago
- Count based exploration with the successor representation for Unity ML's Pyramid☆13Updated 5 years ago
- Implementation of the skill discovery algorithm described in ICLR submission "Option Discovery using Deep Skill Chaining"☆28Updated 4 years ago
- Safe Policy Improvement with Baseline Bootstrapping☆25Updated 4 years ago
- Disagreement-Regularized Imitation Learning☆30Updated 3 years ago
- Implementation of "Sample-Efficient Deep Reinforcement Learning via Episodic Backward Update", NeurIPS 2019.☆16Updated 4 years ago
- Implementation of the Prioritized Option-Critic on the Four-Rooms Environment☆15Updated 6 years ago
- Estimating Q(s,s') with Deep Deterministic Dynamics Gradients☆30Updated 4 years ago
- E-MAML, and RL-MAML baseline implemented in Tensorflow v1☆15Updated 4 years ago
- Simple implementation of V-MPO proposed in https://arxiv.org/abs/1909.12238☆44Updated 3 years ago
- ☆23Updated last year
- A3C style Option-Critic with deliberation cost☆39Updated 6 years ago
- ☆39Updated 3 years ago
- Proximal Policy Option-Critic☆21Updated 5 years ago
- Safe Option-Critic: Learning Safety in the Option-Critic Architecture☆18Updated 5 years ago
- Code accompanying NeurIPS 2019 paper: "Distributional Policy Optimization - An Alternative Approach for Continuous Control"☆21Updated 4 years ago
- Revisiting Rainbow☆73Updated 3 years ago
- Code for Optimistic Exploration even with a Pessimistic Initialisation☆14Updated 4 years ago
- Maximum Entropy-Regularized Multi-Goal Reinforcement Learning (ICML 2019)☆22Updated 5 years ago
- Learning Action-Value Gradients in Model-based Policy Optimization☆31Updated 3 years ago
- ☆53Updated 6 months ago
- Implementation of Tactical Optimistic and Pessimistic value estimation☆24Updated last year
- ☆34Updated last year
- Code for "Explore, Discover and Learn: Unsupervised Discovery of State-Covering Skills"☆36Updated 4 years ago
- Implementation of VALOR (Variational Option Discovery Algorithms)☆10Updated 5 years ago
- 📴 OffCon^3: SOTA PyTorch SAC and TD3 Implementations (arxiv: 2101.11331)☆24Updated 3 years ago