vub-ai-lab / bdpi
Sample-Efficient Reinforcement Learning with Bootstrapped Dual Policy Iteration
☆25Updated 5 years ago
Related projects ⓘ
Alternatives and complementary repositories for bdpi
- A comparison of parameter space noise methods for exploration in deep reinforcement learning☆27Updated 5 years ago
- Modifiable OpenAI Gym environments for studying generalization in RL☆86Updated 5 years ago
- Code for "Divide-and-Conquer Reinforcement Learning"☆60Updated 5 years ago
- Efficient Exploration via State Marginal Matching (2019)☆66Updated 5 years ago
- ☆26Updated 5 years ago
- Autoregressive policies for continuous control reinforcement learning☆28Updated 5 years ago
- OpenAI Gym Wrapper for DeepMind Control Suite☆71Updated 2 years ago
- ☆35Updated 6 years ago
- Estimating Q(s,s') with Deep Deterministic Dynamics Gradients☆32Updated 4 years ago
- Easy MDPs and grid worlds with accessible transition dynamics to do exact calculations☆48Updated 2 years ago
- Inferring beliefs about dynamics from behavior☆28Updated 6 years ago
- Intrinsic Motivation and Automatic Curricula via Asymmetric Self-Play☆14Updated 6 years ago
- ☆13Updated 7 years ago
- Code for reproducing experiments in Model-Based Active Exploration, ICML 2019☆78Updated 5 years ago
- ☆47Updated 4 years ago
- Deep Reinforcement Learning algorithms implemented in PyTorch☆49Updated 6 years ago
- OpenAI Gym environment for DART robotics simulator.☆22Updated 6 years ago
- Convert DeepMind Control Suite to OpenAI gym environments.☆83Updated 4 years ago
- Baselines and memory-based scenarios for the ViZDoom simulator☆33Updated last year
- Simple tools for statistical analyses in RL experiments☆66Updated 6 years ago
- A simple Gridworld environment for Open AI gym☆24Updated 6 years ago
- Disagreement-Regularized Imitation Learning☆30Updated 3 years ago
- Maximum Entropy-Regularized Multi-Goal Reinforcement Learning (ICML 2019)☆23Updated 5 years ago
- Code for experimenting with state and action abstractions in reinforcement learning.☆30Updated 3 years ago
- (Experimental) Inverse reinforcement learning from trajectories generated by multiple agents with different (but correlated) rewards☆26Updated 5 years ago
- Leave No Trace is an algorithm for safe reinforcement learning.☆15Updated 6 years ago
- Code for Multi-Agent Common Knowledge Reinforcement Learning (NeurIPS 2019)☆33Updated 4 years ago
- A collection of multi-agent reinforcement learning OpenAI gym environments☆44Updated 4 years ago
- Implementation of the Fast Efficient Hyperparameter Tuning for Policy Gradient Methods https://arxiv.org/abs/1902.06583☆17Updated 5 years ago