reinforcement-learning

What happened + What you expected to happen

The shim tune.create_scheduler() does not properly parse the keyword parameters passed in a dictionary for the pb2 scheduler. For this call

pb2_parm_dict = {"time_attr": "time_total_s", "metric": "metric_score", "mode": "min",
                 "hyperparam_bounds": {"param1": [0, 1]}}

pb2_scheduler = create_scheduler("pb2", **pb2_pa

Continuation of issue #2474 as discussed here

Is there a way to train a bidirectional RNN (like LSTM or GRU) on trax nowadays?

The following applies to DDPG and TD3, and possibly other models. The following libraries were installed in a virtual environment:

numpy==1.16.4
stable-baselines==2.10.0
gym==0.14.0
tensorflow==1.14.0

Episode rewards do not seem to be updated in model.learn() before callback.on_step(). Depending on which callback.locals variable is used, this means that:

• episode rewards may n

🐛 Bug

The documentation of DQN agent (https://stable-baselines3.readthedocs.io/en/master/modules/dqn.html) specifies that log_interval parameter is "The number of timesteps before logging". However, when set to 1 (or any other value) the logging is not made at that pace but is instead made every log_interval episode (and not timesteps). In the example below this is made every 200 timesteps.